{"id":"28a60a5b-f7ae-4df7-a2cf-67a8fd01abf6","entityType":"agent","slug":"clawhub-dlazyai-dlazy-jimeng-t2i","name":"文生图 即梦 Jimeng T2I","canonicalUrl":"https://www.xpersona.co/agent/clawhub-dlazyai-dlazy-jimeng-t2i","canonicalPath":"/agent/clawhub-dlazyai-dlazy-jimeng-t2i","generatedAt":"2026-10-09T23:24:48.267Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T05:01:18.549Z","emptyReason":null},"description":"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 4.7K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-jimeng-t2i","sourceUrl":"https://clawhub.ai/dlazyai/dlazy-jimeng-t2i","homepage":"https://clawhub.ai/dlazyai/skills/dlazy-jimeng-t2i","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/dlazyai/dlazy-jimeng-t2i","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/dlazyai/skills/dlazy-jimeng-t2i","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":73,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"文生图 即梦 Jimeng T2I technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T05:01:18.549Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T05:01:18.549Z","emptyReason":null},"stars":null,"forks":null,"downloads":4688,"packageName":null,"latestVersion":"1.3.26","tractionLabel":"4.7K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T05:01:18.549Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T05:01:18.549Z","lastCrawledAt":"2026-10-09T05:01:18.549Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T05:01:18.549Z","lastVerifiedAt":null,"highlights":[{"version":"1.3.26","createdAt":"2026-10-08T01:17:41.305Z","changelog":"例行版本更新 2026-10-08","fileCount":4,"zipByteSize":8392},{"version":"1.3.25","createdAt":"2026-10-04T01:16:37.029Z","changelog":"例行版本更新 2026-10-04","fileCount":4,"zipByteSize":8372},{"version":"1.3.24","createdAt":"2026-10-02T04:58:27.900Z","changelog":"例行版本更新 2026-10-02","fileCount":4,"zipByteSize":8253},{"version":"1.3.23","createdAt":"2026-09-30T01:15:21.907Z","changelog":"例行版本更新 2026-09-30","fileCount":4,"zipByteSize":8264},{"version":"1.3.22","createdAt":"2026-09-28T02:13:47.633Z","changelog":"例行版本更新 2026-09-28","fileCount":4,"zipByteSize":8293},{"version":"1.3.21","createdAt":"2026-09-28T01:16:03.641Z","changelog":"例行版本更新 2026-09-28","fileCount":4,"zipByteSize":8364},{"version":"1.3.20","createdAt":"2026-09-24T06:50:07.089Z","changelog":"例行版本更新 2026-09-24","fileCount":4,"zipByteSize":8331},{"version":"1.3.19","createdAt":"2026-09-22T01:13:17.337Z","changelog":"例行版本更新 2026-09-22","fileCount":4,"zipByteSize":8530}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-jimeng-t2i","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-jimeng-t2i` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/dlazyai/dlazy-jimeng-t2i before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-jimeng-t2i/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-jimeng-t2i/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-jimeng-t2i/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-jimeng-t2i/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-jimeng-t2i/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-jimeng-t2i/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T23:24:48.263Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-jimeng-t2i/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-jimeng-t2i/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-jimeng-t2i/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-jimeng-t2i/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T05:01:18.549Z","emptyReason":null},"readme":"Skill: 文生图 即梦 Jimeng T2I\n\nOwner: dlazyai\n\nSummary: Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\n\nTags: latest:1.3.26\n\nVersion history:\n\nv1.3.26 | 2026-10-08T01:17:41.305Z | user\n\n例行版本更新 2026-10-08\n\nv1.3.25 | 2026-10-04T01:16:37.029Z | user\n\n例行版本更新 2026-10-04\n\nv1.3.24 | 2026-10-02T04:58:27.900Z | user\n\n例行版本更新 2026-10-02\n\nv1.3.23 | 2026-09-30T01:15:21.907Z | user\n\n例行版本更新 2026-09-30\n\nv1.3.22 | 2026-09-28T02:13:47.633Z | user\n\n例行版本更新 2026-09-28\n\nv1.3.21 | 2026-09-28T01:16:03.641Z | user\n\n例行版本更新 2026-09-28\n\nv1.3.20 | 2026-09-24T06:50:07.089Z | user\n\n例行版本更新 2026-09-24\n\nv1.3.19 | 2026-09-22T01:13:17.337Z | user\n\n例行版本更新 2026-09-22\n\nv1.3.18 | 2026-09-20T01:19:12.984Z | user\n\n例行版本更新 2026-09-20\n\nv1.3.17 | 2026-09-18T01:41:04.991Z | user\n\n例行版本更新 2026-09-18\n\nv1.3.16 | 2026-09-14T01:15:50.702Z | user\n\n例行版本更新 2026-09-14\n\nv1.3.15 | 2026-09-10T01:13:06.934Z | user\n\n例行版本更新 2026-09-10\n\nv1.3.14 | 2026-09-08T01:14:14.268Z | user\n\n例行版本更新 2026-09-08\n\nv1.3.13 | 2026-09-07T01:18:39.544Z | user\n\n例行版本更新 2026-09-07\n\nv1.3.12 | 2026-09-04T01:19:31.793Z | user\n\n例行版本更新 2026-09-04\n\nv1.3.11 | 2026-09-02T01:14:01.948Z | user\n\n例行版本更新 2026-09-02\n\nv1.3.10 | 2026-08-31T02:54:25.658Z | user\n\n源码仓库迁移至 github.com/dlazy-ai/cli\n\nv1.3.9 | 2026-08-24T09:25:30.610Z | user\n\nRestore Chinese display name\n\nv1.3.8 | 2026-08-17T09:08:04.575Z | user\n\nRestore Chinese display name\n\nv1.3.7 | 2026-08-10T05:49:22.241Z | user\n\nRestore Chinese display name\n\nv1.3.6 | 2026-08-10T04:03:52.376Z | user\n\nRestore Chinese display name\n\nv1.3.5 | 2026-07-21T02:21:36.210Z | auto\n\n- Updated CLI dependency to @dlazy/cli version 1.2.3.\n- Changed all install and usage instructions to reference the new pinned version.\n- Removed the unused skill-card.md file for a cleaner repository.\n\nv1.3.4 | 2026-07-17T10:40:39.643Z | auto\n\n- Updated CLI integration to use @dlazy/cli version 1.2.2 (was 1.2.0).\n- Adjusted install and usage instructions to reflect the updated CLI version.\n- Removed the redundant skill-card.md file.\n- Minor metadata and formatting improvements in documentation.\n\nv1.2.2 | 2026-07-17T08:46:32.969Z | auto\n\n- Removed the file: skill-card.md\n- No other changes to functionality or documentation.\n\nv1.3.3 | 2026-07-09T01:49:42.035Z | user\n\nset Chinese display name for CN search\n\nv1.3.2 | 2026-07-09T01:49:28.991Z | user\n\nset Chinese display name for CN search\n\nv1.3.1 | 2026-07-09T01:32:43.693Z | user\n\nset Chinese display name for CN search\n\nv1.3.0 | 2026-07-07T19:47:32.973Z | auto\n\n- Update version to 1.3.0.\n- Documentation (SKILL.md, SKILL-cn.md) refreshed; no command or API changes.\n- No functional changes; this is a documentation update release.\n\nv1.2.1 | 2026-07-07T18:36:39.189Z | auto\n\n- Added a Chinese description to the main SKILL.md for bilingual clarity.\n- Updated version to 1.2.1.\n- Removed the redundant skill-card.md file.\n\nv1.2.0 | 2026-06-02T09:55:29.517Z | auto\n\n- Updated dLazy CLI dependency to version 1.2.0 for installs and usage.\n- Output format: modelId in JSON response changed from \"jimeng-t2i-v40\" to \"jimeng-t2i\".\n- Removed deprecated skill-card.md file.\n- Minor metadata and documentation updates for clarity and version consistency.\n\nv1.1.2 | 2026-06-02T01:38:27.585Z | user\n\nUpdate model skills (names/params refreshed); add search-audio/image/video\n\nv1.1.1 | 2026-05-06T14:06:31.691Z | auto\n\n- Bumped version to 1.1.1.\n- Documentation files updated (SKILL.md, SKILL-cn.md).\n- No functional or interface changes; content refresh/maintenance only.\n\nv1.1.0 | 2026-05-01T07:49:39.211Z | auto\n\n- Added support and documentation for the new device-code authentication flow via dlazy login.\n- Updated authentication section to recommend dlazy login as the primary method, with manual API key entry now shown as an alternative.\n- No changes to core commands or functionality.\n\nv1.0.9 | 2026-04-30T10:19:56.978Z | user\n\nSync to CLI 1.0.9 with cliWarning support\n\nv1.0.5 | 2026-04-29T02:34:39.996Z | user\n\nbump @dlazy/cli to 1.0.8\n\nv1.0.4 | 2026-04-27T08:02:49.420Z | user\n\nReduce false-positive scanner alerts: drop 'plaintext' wording from API key storage docs; remove persistsApiKey/network metadata flags in favour of neutral configLocation/apiEndpoints; rewrite Data & Privacy section as factual How-It-Works description without alarming warnings; emphasise that keys can be rotated/revoked at any time from the dLazy dashboard.\n\nv1.0.3 | 2026-04-27T07:41:31.419Z | user\n\nAdd provenance metadata (homepage/source/author/npm), document API key storage location (~/.dlazy/config.json) and DLAZY_API_KEY env var alternative, add Data & Privacy section, recommend 'npx @dlazy/cli@1.0.6' install alternative, normalise Chinese auth-error instruction wording.\n\nv1.0.2 | 2026-04-24T04:03:21.065Z | auto\n\n- Updated to version 1.0.2.\n- Clarified API key instructions for improved guidance.\n- Minor edits to agent guidance and formatting for clarity.\n\nv1.0.1 | 2026-04-24T03:28:32.561Z | auto\n\n- Added a dedicated Authentication section with instructions for setting and obtaining the dLazy API key.\n- Updated installation instructions to use @dlazy/cli@1.0.6.\n- Improved documentation for obtaining the API key from the dashboard.\n- No changes to the command usage or output format.\n\nv1.0.0 | 2026-04-21T07:15:58.543Z | auto\n\nInitial release of dlazy-jimeng-t2i.\n\n- Enables fast text-to-image generation using the Jimeng model.\n- Provides support for multiple image sizes and input methods.\n- Includes detailed CLI usage, sample commands, and error handling guidelines.\n- Handles authentication and credit balance scenarios with user instructions.\n\nArchive index:\n\nArchive v1.3.26: 4 files, 8392 bytes\n\nFiles: skill-card.md (2038b), SKILL-cn.md (7366b), SKILL.md (7450b), _meta.json (136b)\n\nFile v1.3.26:SKILL.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When invoking this skill, use dlazy jimeng-t2i -h for help.\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\r\n\r\n## Trigger Keywords\r\n\r\n- jimeng\r\n- generate image, text to image\r\n- draw a picture\r\n\r\n## Authentication\r\n\r\nAll requests require a dLazy API key. The recommended way to authenticate is:\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\r\n\r\n### Alternative: Set the Key Manually\r\n\r\nIf you already have an API key, you can save it directly:\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\r\n\r\n### Getting Your API Key Manually\r\n\r\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\r\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. Copy the key shown in the API Key section\r\n\r\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\r\n\r\n## About & Provenance\r\n\r\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **Maintainer**: dlazyai\r\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\r\n- **Homepage**: [dlazy.com](https://dlazy.com)\r\n\r\nYou can install on demand without persisting a global binary by running:\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\r\n\r\n## How It Works\r\n\r\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\r\n\r\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\r\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\r\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\r\n\r\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\r\n\r\n## Usage\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\nRun the `dlazy jimeng-t2i` command to get results.\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    Prompt\r\n  --images [images...]                 Images [image: url or local path] (max 10)\r\n  --size [size]                        Size [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## Output Format\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## Command Examples\r\n\r\n```bash\r\n# basic call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image '/path/to/image.png'\r\n\r\n# complex call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## Error Handling\r\n\r\n| Code | Error Type                         | Example Message                                                                                                          |\r\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\r\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\r\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\r\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\r\n\r\n> **AGENT CRITICAL INSTRUCTION**: \r\n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nFile v1.3.26:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-jimeng-t2i\",\n  \"version\": \"1.3.26\",\n  \"publishedAt\": 1791422261305\n}\n\nFile v1.3.26:skill-card.md\n\n## Description:\n\nHelps an agent generate images from text prompts with Jimeng through the dLazy CLI, with optional reference images.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and teams use this skill to request Jimeng text-to-image generation, optionally providing reference images and saving the result.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and explicitly supplied local media may be sent to the dLazy hosted service.\n\nMitigation: Confirm the user wants to use dLazy and avoid sending sensitive content without approval.\n\nRisk: Image generation may consume account credits.\n\nMitigation: Use the available dry-run cost estimate when appropriate and confirm before costly requests.\n\nRisk: The CLI can save an API key locally.\n\nMitigation: Protect local credentials and rotate or revoke the key if it is exposed.\n\nRisk: Installing a third-party npm CLI introduces package supply-chain exposure.\n\nMitigation: Review the pinned package source before installing in sensitive environments.\n\n## Reference(s):\n\n- [dLazy CLI source linked in skill metadata](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Guidance]\n\n**Output Format:** [Text guidance with CLI examples; the CLI returns JSON containing generated image URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Optional local download of generated images; asynchronous jobs can return a task ID.]\n\n## Skill Version(s):\n\n1.3.26 (source: ClawHub release metadata; supplied skill frontmatter lists 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.26:SKILL-cn.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，可以使用 dlazy jimeng-t2i -h 查看帮助信息。\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\n使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\r\n\r\n## 触发关键词\r\n\r\n- 即梦\r\n- jimeng\r\n- 生成图片、文生图\r\n- 画一张图\r\n\r\n## 身份验证 (Authentication)\r\n\r\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\r\n\r\n### 备选：手动设置 API Key\r\n\r\n如果你已有 API key，也可以直接保存：\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\r\n\r\n### 手动获取 API Key\r\n\r\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\r\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. 复制 API Key 区域显示的密钥\r\n\r\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\r\n\r\n## 关于与来源 (Provenance)\r\n\r\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **维护者**: dlazyai\r\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\r\n- **官网**: [dlazy.com](https://dlazy.com)\r\n\r\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\r\n\r\n## 工作原理\r\n\r\n此技能是 dLazy 托管 API 的轻量封装。调用时：\r\n\r\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\r\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\r\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\r\n\r\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\r\n\r\n## 使用方法\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\n执行 `dlazy jimeng-t2i` 命令获取结果。\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    提示词\r\n  --images [images...]                 参考图 [image: url or local path] (max 10)\r\n  --size [size]                        尺寸 [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## 输出格式\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## 命令示例\r\n\r\n```bash\r\n# 基础调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image '/path/to/image.png'\r\n\r\n# 复杂调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## 错误处理\r\n\r\n| Code | 错误类型                         | 示例信息                                                                                                                 |\r\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\r\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\r\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\r\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\r\n\r\n> **智能体关键指令**: \r\n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nArchive v1.3.25: 4 files, 8372 bytes\n\nFiles: skill-card.md (1986b), SKILL-cn.md (7366b), SKILL.md (7450b), _meta.json (136b)\n\nFile v1.3.25:SKILL.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When invoking this skill, use dlazy jimeng-t2i -h for help.\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\r\n\r\n## Trigger Keywords\r\n\r\n- jimeng\r\n- generate image, text to image\r\n- draw a picture\r\n\r\n## Authentication\r\n\r\nAll requests require a dLazy API key. The recommended way to authenticate is:\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\r\n\r\n### Alternative: Set the Key Manually\r\n\r\nIf you already have an API key, you can save it directly:\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\r\n\r\n### Getting Your API Key Manually\r\n\r\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\r\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. Copy the key shown in the API Key section\r\n\r\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\r\n\r\n## About & Provenance\r\n\r\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **Maintainer**: dlazyai\r\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\r\n- **Homepage**: [dlazy.com](https://dlazy.com)\r\n\r\nYou can install on demand without persisting a global binary by running:\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\r\n\r\n## How It Works\r\n\r\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\r\n\r\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\r\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\r\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\r\n\r\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\r\n\r\n## Usage\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\nRun the `dlazy jimeng-t2i` command to get results.\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    Prompt\r\n  --images [images...]                 Images [image: url or local path] (max 10)\r\n  --size [size]                        Size [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## Output Format\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## Command Examples\r\n\r\n```bash\r\n# basic call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image '/path/to/image.png'\r\n\r\n# complex call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## Error Handling\r\n\r\n| Code | Error Type                         | Example Message                                                                                                          |\r\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\r\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\r\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\r\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\r\n\r\n> **AGENT CRITICAL INSTRUCTION**: \r\n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nFile v1.3.25:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-jimeng-t2i\",\n  \"version\": \"1.3.25\",\n  \"publishedAt\": 1791076597029\n}\n\nFile v1.3.25:skill-card.md\n\n## Description:\n\nHelps agents generate Jimeng images from text prompts through the dLazy service.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to direct an agent to generate images from text prompts, optionally with reference images.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and explicitly supplied local media may be sent to dLazy, with generated images hosted by dLazy.\n\nMitigation: Avoid sending sensitive prompts or files without authorization and review the service terms before use.\n\nRisk: API calls may consume account credits.\n\nMitigation: Check the estimated cost with the dry-run option before submitting a request.\n\nRisk: The CLI may persist an API key in local configuration.\n\nMitigation: Use a revocable key or supply DLAZY_API_KEY per invocation to reduce persistent credential storage.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-jimeng-t2i)\n- [dLazy CLI package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy CLI repository (linked in skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy service](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Guidance, Text]\n\n**Output Format:** [Markdown or text with shell commands and image links]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [The CLI may return hosted image URLs or an asynchronous task ID; images can optionally be saved locally.]\n\n## Skill Version(s):\n\n1.3.25 (source: server-resolved release; bundled skill frontmatter lists 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.25:SKILL-cn.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，可以使用 dlazy jimeng-t2i -h 查看帮助信息。\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\n使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\r\n\r\n## 触发关键词\r\n\r\n- 即梦\r\n- jimeng\r\n- 生成图片、文生图\r\n- 画一张图\r\n\r\n## 身份验证 (Authentication)\r\n\r\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\r\n\r\n### 备选：手动设置 API Key\r\n\r\n如果你已有 API key，也可以直接保存：\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\r\n\r\n### 手动获取 API Key\r\n\r\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\r\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. 复制 API Key 区域显示的密钥\r\n\r\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\r\n\r\n## 关于与来源 (Provenance)\r\n\r\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **维护者**: dlazyai\r\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\r\n- **官网**: [dlazy.com](https://dlazy.com)\r\n\r\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\r\n\r\n## 工作原理\r\n\r\n此技能是 dLazy 托管 API 的轻量封装。调用时：\r\n\r\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\r\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\r\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\r\n\r\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\r\n\r\n## 使用方法\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\n执行 `dlazy jimeng-t2i` 命令获取结果。\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    提示词\r\n  --images [images...]                 参考图 [image: url or local path] (max 10)\r\n  --size [size]                        尺寸 [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## 输出格式\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## 命令示例\r\n\r\n```bash\r\n# 基础调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image '/path/to/image.png'\r\n\r\n# 复杂调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## 错误处理\r\n\r\n| Code | 错误类型                         | 示例信息                                                                                                                 |\r\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\r\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\r\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\r\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\r\n\r\n> **智能体关键指令**: \r\n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nArchive v1.3.24: 4 files, 8253 bytes\n\nFiles: skill-card.md (1730b), SKILL-cn.md (7366b), SKILL.md (7450b), _meta.json (136b)\n\nFile v1.3.24:SKILL.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When invoking this skill, use dlazy jimeng-t2i -h for help.\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\r\n\r\n## Trigger Keywords\r\n\r\n- jimeng\r\n- generate image, text to image\r\n- draw a picture\r\n\r\n## Authentication\r\n\r\nAll requests require a dLazy API key. The recommended way to authenticate is:\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\r\n\r\n### Alternative: Set the Key Manually\r\n\r\nIf you already have an API key, you can save it directly:\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\r\n\r\n### Getting Your API Key Manually\r\n\r\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\r\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. Copy the key shown in the API Key section\r\n\r\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\r\n\r\n## About & Provenance\r\n\r\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **Maintainer**: dlazyai\r\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\r\n- **Homepage**: [dlazy.com](https://dlazy.com)\r\n\r\nYou can install on demand without persisting a global binary by running:\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\r\n\r\n## How It Works\r\n\r\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\r\n\r\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\r\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\r\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\r\n\r\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\r\n\r\n## Usage\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\nRun the `dlazy jimeng-t2i` command to get results.\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    Prompt\r\n  --images [images...]                 Images [image: url or local path] (max 10)\r\n  --size [size]                        Size [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## Output Format\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## Command Examples\r\n\r\n```bash\r\n# basic call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image '/path/to/image.png'\r\n\r\n# complex call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## Error Handling\r\n\r\n| Code | Error Type                         | Example Message                                                                                                          |\r\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\r\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\r\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\r\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\r\n\r\n> **AGENT CRITICAL INSTRUCTION**: \r\n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nFile v1.3.24:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-jimeng-t2i\",\n  \"version\": \"1.3.24\",\n  \"publishedAt\": 1790917107900\n}\n\nFile v1.3.24:skill-card.md\n\n## Description:\n\nGenerates images from text prompts with Jimeng through the dLazy service.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to request Jimeng-generated images from text prompts, optionally using reference images.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and supplied local media may be sent to dLazy's hosted service.\n\nMitigation: Avoid sending sensitive prompts or files; review inputs before invoking the CLI.\n\nRisk: Authentication may save an API key in local CLI configuration.\n\nMitigation: Protect local credentials and rotate or revoke the key if exposed.\n\nRisk: Generation requests may consume account credits.\n\nMitigation: Check estimated costs with dry-run before making paid requests.\n\n## Reference(s):\n\n- [dLazy CLI repository](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy service](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Text, Image URLs]\n\n**Output Format:** [JSON response with generated image URLs; optionally a saved image file]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Asynchronous requests can return a task ID for later polling.]\n\n## Skill Version(s):\n\n1.3.24 (source: ClawHub release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.24:SKILL-cn.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，可以使用 dlazy jimeng-t2i -h 查看帮助信息。\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\n使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\r\n\r\n## 触发关键词\r\n\r\n- 即梦\r\n- jimeng\r\n- 生成图片、文生图\r\n- 画一张图\r\n\r\n## 身份验证 (Authentication)\r\n\r\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\r\n\r\n### 备选：手动设置 API Key\r\n\r\n如果你已有 API key，也可以直接保存：\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\r\n\r\n### 手动获取 API Key\r\n\r\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\r\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. 复制 API Key 区域显示的密钥\r\n\r\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\r\n\r\n## 关于与来源 (Provenance)\r\n\r\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **维护者**: dlazyai\r\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\r\n- **官网**: [dlazy.com](https://dlazy.com)\r\n\r\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\r\n\r\n## 工作原理\r\n\r\n此技能是 dLazy 托管 API 的轻量封装。调用时：\r\n\r\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\r\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\r\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\r\n\r\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\r\n\r\n## 使用方法\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\n执行 `dlazy jimeng-t2i` 命令获取结果。\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    提示词\r\n  --images [images...]                 参考图 [image: url or local path] (max 10)\r\n  --size [size]                        尺寸 [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## 输出格式\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## 命令示例\r\n\r\n```bash\r\n# 基础调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image '/path/to/image.png'\r\n\r\n# 复杂调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## 错误处理\r\n\r\n| Code | 错误类型                         | 示例信息                                                                                                                 |\r\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\r\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\r\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\r\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\r\n\r\n> **智能体关键指令**: \r\n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nArchive v1.3.23: 4 files, 8264 bytes\n\nFiles: skill-card.md (1790b), SKILL-cn.md (7366b), SKILL.md (7450b), _meta.json (136b)\n\nFile v1.3.23:SKILL.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When invoking this skill, use dlazy jimeng-t2i -h for help.\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\r\n\r\n## Trigger Keywords\r\n\r\n- jimeng\r\n- generate image, text to image\r\n- draw a picture\r\n\r\n## Authentication\r\n\r\nAll requests require a dLazy API key. The recommended way to authenticate is:\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\r\n\r\n### Alternative: Set the Key Manually\r\n\r\nIf you already have an API key, you can save it directly:\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\r\n\r\n### Getting Your API Key Manually\r\n\r\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\r\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. Copy the key shown in the API Key section\r\n\r\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\r\n\r\n## About & Provenance\r\n\r\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **Maintainer**: dlazyai\r\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\r\n- **Homepage**: [dlazy.com](https://dlazy.com)\r\n\r\nYou can install on demand without persisting a global binary by running:\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\r\n\r\n## How It Works\r\n\r\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\r\n\r\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\r\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\r\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\r\n\r\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\r\n\r\n## Usage\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\nRun the `dlazy jimeng-t2i` command to get results.\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    Prompt\r\n  --images [images...]                 Images [image: url or local path] (max 10)\r\n  --size [size]                        Size [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## Output Format\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## Command Examples\r\n\r\n```bash\r\n# basic call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image '/path/to/image.png'\r\n\r\n# complex call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## Error Handling\r\n\r\n| Code | Error Type                         | Example Message                                                                                                          |\r\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\r\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\r\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\r\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\r\n\r\n> **AGENT CRITICAL INSTRUCTION**: \r\n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nFile v1.3.23:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-jimeng-t2i\",\n  \"version\": \"1.3.23\",\n  \"publishedAt\": 1790730921907\n}\n\nFile v1.3.23:skill-card.md\n\n## Description:\n\nGenerates images from text prompts with Jimeng through the dLazy service, with optional reference images.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to generate images from text prompts and optional reference images.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and referenced local media are sent to dLazy's hosted service.\n\nMitigation: Avoid submitting sensitive prompts or local files; review what is sent before generation.\n\nRisk: The external CLI requires an API key and may be installed globally.\n\nMitigation: Use the on-demand npx option if preferred, and rotate or revoke the API key through the dLazy dashboard when necessary.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-jimeng-t2i)\n- [dLazy CLI repository (listed in skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy service](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Images, JSON]\n\n**Output Format:** [JSON response with image URLs; optionally saved image files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Asynchronous requests may return a task ID before an image is available.]\n\n## Skill Version(s):\n\n1.3.23 (source: ClawHub release metadata; skill frontmatter lists 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.23:SKILL-cn.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，可以使用 dlazy jimeng-t2i -h 查看帮助信息。\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\n使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\r\n\r\n## 触发关键词\r\n\r\n- 即梦\r\n- jimeng\r\n- 生成图片、文生图\r\n- 画一张图\r\n\r\n## 身份验证 (Authentication)\r\n\r\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\r\n\r\n### 备选：手动设置 API Key\r\n\r\n如果你已有 API key，也可以直接保存：\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\r\n\r\n### 手动获取 API Key\r\n\r\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\r\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. 复制 API Key 区域显示的密钥\r\n\r\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\r\n\r\n## 关于与来源 (Provenance)\r\n\r\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **维护者**: dlazyai\r\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\r\n- **官网**: [dlazy.com](https://dlazy.com)\r\n\r\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\r\n\r\n## 工作原理\r\n\r\n此技能是 dLazy 托管 API 的轻量封装。调用时：\r\n\r\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\r\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\r\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\r\n\r\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\r\n\r\n## 使用方法\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\n执行 `dlazy jimeng-t2i` 命令获取结果。\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    提示词\r\n  --images [images...]                 参考图 [image: url or local path] (max 10)\r\n  --size [size]                        尺寸 [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## 输出格式\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## 命令示例\r\n\r\n```bash\r\n# 基础调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image '/path/to/image.png'\r\n\r\n# 复杂调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## 错误处理\r\n\r\n| Code | 错误类型                         | 示例信息                                                                                                                 |\r\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\r\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\r\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\r\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\r\n\r\n> **智能体关键指令**: \r\n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nArchive v1.3.22: 4 files, 8293 bytes\n\nFiles: skill-card.md (1823b), SKILL-cn.md (7366b), SKILL.md (7450b), _meta.json (136b)\n\nFile v1.3.22:SKILL.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When invoking this skill, use dlazy jimeng-t2i -h for help.\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\r\n\r\n## Trigger Keywords\r\n\r\n- jimeng\r\n- generate image, text to image\r\n- draw a picture\r\n\r\n## Authentication\r\n\r\nAll requests require a dLazy API key. The recommended way to authenticate is:\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\r\n\r\n### Alternative: Set the Key Manually\r\n\r\nIf you already have an API key, you can save it directly:\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\r\n\r\n### Getting Your API Key Manually\r\n\r\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\r\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. Copy the key shown in the API Key section\r\n\r\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\r\n\r\n## About & Provenance\r\n\r\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **Maintainer**: dlazyai\r\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\r\n- **Homepage**: [dlazy.com](https://dlazy.com)\r\n\r\nYou can install on demand without persisting a global binary by running:\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\r\n\r\n## How It Works\r\n\r\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\r\n\r\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\r\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\r\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\r\n\r\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\r\n\r\n## Usage\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\nRun the `dlazy jimeng-t2i` command to get results.\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    Prompt\r\n  --images [images...]                 Images [image: url or local path] (max 10)\r\n  --size [size]                        Size [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## Output Format\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## Command Examples\r\n\r\n```bash\r\n# basic call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image '/path/to/image.png'\r\n\r\n# complex call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## Error Handling\r\n\r\n| Code | Error Type                         | Example Message                                                                                                          |\r\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\r\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\r\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\r\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\r\n\r\n> **AGENT CRITICAL INSTRUCTION**: \r\n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nFile v1.3.22:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-jimeng-t2i\",\n  \"version\": \"1.3.22\",\n  \"publishedAt\": 1790561627633\n}\n\nFile v1.3.22:skill-card.md\n\n## Description:\n\nHelps agents generate images from text prompts using Jimeng through dLazy.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to turn text prompts and optional reference images into generated images with Jimeng via dLazy.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected local media may be sent to dLazy's cloud service.\n\nMitigation: Avoid sending sensitive prompts or files unless their use with dLazy is approved.\n\nRisk: Login can save a dLazy API key locally, and global installation leaves a CLI installed.\n\nMitigation: Protect local credentials and use the pinned npx option when a global CLI install is unnecessary.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-jimeng-t2i)\n- [dLazy CLI repository (skill metadata link; not verified skill provenance)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Shell commands, JSON, Image files]\n\n**Output Format:** [Text guidance and CLI commands; JSON results with image URLs or optionally saved image files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Async requests may return a task ID instead of immediate image URLs.]\n\n## Skill Version(s):\n\n1.3.22 (source: ClawHub release metadata; bundled frontmatter says 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.22:SKILL-cn.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，可以使用 dlazy jimeng-t2i -h 查看帮助信息。\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\n使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\r\n\r\n## 触发关键词\r\n\r\n- 即梦\r\n- jimeng\r\n- 生成图片、文生图\r\n- 画一张图\r\n\r\n## 身份验证 (Authentication)\r\n\r\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\r\n\r\n### 备选：手动设置 API Key\r\n\r\n如果你已有 API key，也可以直接保存：\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\r\n\r\n### 手动获取 API Key\r\n\r\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\r\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. 复制 API Key 区域显示的密钥\r\n\r\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\r\n\r\n## 关于与来源 (Provenance)\r\n\r\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **维护者**: dlazyai\r\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\r\n- **官网**: [dlazy.com](https://dlazy.com)\r\n\r\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\r\n\r\n## 工作原理\r\n\r\n此技能是 dLazy 托管 API 的轻量封装。调用时：\r\n\r\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\r\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\r\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\r\n\r\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\r\n\r\n## 使用方法\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\n执行 `dlazy jimeng-t2i` 命令获取结果。\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    提示词\r\n  --images [images...]                 参考图 [image: url or local path] (max 10)\r\n  --size [size]                        尺寸 [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## 输出格式\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## 命令示例\r\n\r\n```bash\r\n# 基础调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image '/path/to/image.png'\r\n\r\n# 复杂调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## 错误处理\r\n\r\n| Code | 错误类型                         | 示例信息                                                                                                                 |\r\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\r\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\r\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\r\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\r\n\r\n> **智能体关键指令**: \r\n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nArchive v1.3.21: 4 files, 8364 bytes\n\nFiles: skill-card.md (1972b), SKILL-cn.md (7366b), SKILL.md (7450b), _meta.json (136b)\n\nFile v1.3.21:SKILL.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When invoking this skill, use dlazy jimeng-t2i -h for help.\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\r\n\r\n## Trigger Keywords\r\n\r\n- jimeng\r\n- generate image, text to image\r\n- draw a picture\r\n\r\n## Authentication\r\n\r\nAll requests require a dLazy API key. The recommended way to authenticate is:\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\r\n\r\n### Alternative: Set the Key Manually\r\n\r\nIf you already have an API key, you can save it directly:\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\r\n\r\n### Getting Your API Key Manually\r\n\r\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\r\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. Copy the key shown in the API Key section\r\n\r\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\r\n\r\n## About & Provenance\r\n\r\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **Maintainer**: dlazyai\r\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\r\n- **Homepage**: [dlazy.com](https://dlazy.com)\r\n\r\nYou can install on demand without persisting a global binary by running:\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\r\n\r\n## How It Works\r\n\r\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\r\n\r\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\r\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\r\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\r\n\r\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\r\n\r\n## Usage\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\nRun the `dlazy jimeng-t2i` command to get results.\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    Prompt\r\n  --images [images...]                 Images [image: url or local path] (max 10)\r\n  --size [size]                        Size [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## Output Format\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## Command Examples\r\n\r\n```bash\r\n# basic call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image '/path/to/image.png'\r\n\r\n# complex call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## Error Handling\r\n\r\n| Code | Error Type                         | Example Message                                                                                                          |\r\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\r\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\r\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\r\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\r\n\r\n> **AGENT CRITICAL INSTRUCTION**: \r\n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nFile v1.3.21:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-jimeng-t2i\",\n  \"version\": \"1.3.21\",\n  \"publishedAt\": 1790558163641\n}\n\nFile v1.3.21:skill-card.md\n\n## Description:\n\nGenerates images from text prompts with Jimeng through dLazy's hosted service.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and developers use this skill to generate images from text prompts, optionally supplying reference images through dLazy's hosted Jimeng service.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Running a third-party CLI package.\n\nMitigation: Review the package before use and run the pinned @dlazy/cli@1.2.3 version; use npx if a persistent global install is unwanted.\n\nRisk: The CLI stores an API key in local configuration by default.\n\nMitigation: Use DLAZY_API_KEY for per-run credentials if local key storage is unwanted.\n\nRisk: Prompts and selected local reference files are sent to dLazy's hosted service.\n\nMitigation: Avoid sensitive prompts and local files unless you are comfortable sharing them with the service.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-jimeng-t2i)\n- [dLazy CLI source (listed in skill metadata; import provenance unavailable)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Guidance]\n\n**Output Format:** [Markdown with shell commands and JSON result examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [The CLI returns image URLs or an asynchronous task ID; an optional save flag downloads the image.]\n\n## Skill Version(s):\n\n1.3.21 (source: ClawHub release; artifact frontmatter lists 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.21:SKILL-cn.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，可以使用 dlazy jimeng-t2i -h 查看帮助信息。\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\n使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\r\n\r\n## 触发关键词\r\n\r\n- 即梦\r\n- jimeng\r\n- 生成图片、文生图\r\n- 画一张图\r\n\r\n## 身份验证 (Authentication)\r\n\r\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\r\n\r\n### 备选：手动设置 API Key\r\n\r\n如果你已有 API key，也可以直接保存：\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\r\n\r\n### 手动获取 API Key\r\n\r\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\r\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. 复制 API Key 区域显示的密钥\r\n\r\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\r\n\r\n## 关于与来源 (Provenance)\r\n\r\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **维护者**: dlazyai\r\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\r\n- **官网**: [dlazy.com](https://dlazy.com)\r\n\r\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\r\n\r\n## 工作原理\r\n\r\n此技能是 dLazy 托管 API 的轻量封装。调用时：\r\n\r\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\r\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\r\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\r\n\r\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\r\n\r\n## 使用方法\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\n执行 `dlazy jimeng-t2i` 命令获取结果。\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    提示词\r\n  --images [images...]                 参考图 [image: url or local path] (max 10)\r\n  --size [size]                        尺寸 [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## 输出格式\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## 命令示例\r\n\r\n```bash\r\n# 基础调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image '/path/to/image.png'\r\n\r\n# 复杂调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## 错误处理\r\n\r\n| Code | 错误类型                         | 示例信息                                                                                                                 |\r\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\r\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\r\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\r\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\r\n\r\n> **智能体关键指令**: \r\n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nArchive v1.3.20: 4 files, 8331 bytes\n\nFiles: skill-card.md (2019b), SKILL-cn.md (7366b), SKILL.md (7450b), _meta.json (136b)\n\nFile v1.3.20:SKILL.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When invoking this skill, use dlazy jimeng-t2i -h for help.\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\r\n\r\n## Trigger Keywords\r\n\r\n- jimeng\r\n- generate image, text to image\r\n- draw a picture\r\n\r\n## Authentication\r\n\r\nAll requests require a dLazy API key. The recommended way to authenticate is:\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\r\n\r\n### Alternative: Set the Key Manually\r\n\r\nIf you already have an API key, you can save it directly:\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\r\n\r\n### Getting Your API Key Manually\r\n\r\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\r\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. Copy the key shown in the API Key section\r\n\r\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\r\n\r\n## About & Provenance\r\n\r\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **Maintainer**: dlazyai\r\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\r\n- **Homepage**: [dlazy.com](https://dlazy.com)\r\n\r\nYou can install on demand without persisting a global binary by running:\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\r\n\r\n## How It Works\r\n\r\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\r\n\r\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\r\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\r\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\r\n\r\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\r\n\r\n## Usage\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\nRun the `dlazy jimeng-t2i` command to get results.\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    Prompt\r\n  --images [images...]                 Images [image: url or local path] (max 10)\r\n  --size [size]                        Size [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## Output Format\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## Command Examples\r\n\r\n```bash\r\n# basic call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image '/path/to/image.png'\r\n\r\n# complex call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## Error Handling\r\n\r\n| Code | Error Type                         | Example Message                                                                                                          |\r\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\r\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\r\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\r\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\r\n\r\n> **AGENT CRITICAL INSTRUCTION**: \r\n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nFile v1.3.20:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-jimeng-t2i\",\n  \"version\": \"1.3.20\",\n  \"publishedAt\": 1790232607089\n}\n\nFile v1.3.20:skill-card.md\n\n## Description:\n\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to generate Jimeng text-to-image outputs from prompts, optional reference images, and size parameters through the dLazy CLI.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts, parameters, and selected local media files may be sent to dLazy hosted services.\n\nMitigation: Avoid using private files or sensitive prompt content unless the user accepts dLazy processing.\n\nRisk: The dLazy CLI can store an API key in a local configuration file.\n\nMitigation: Use per-invocation credentials or the pinned npx command when a persistent global CLI or saved key is not desired.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dlazyai/skills/dlazy-jimeng-t2i)\n- [dLazy CLI source](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy service homepage](https://dlazy.com)\n- [dLazy CLI homepage from ClawHub metadata](https://github.com/dlazy-ai/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, API Calls, JSON, Files, Configuration instructions, Guidance]\n\n**Output Format:** [JSON responses with generated image URLs, optional downloaded image files, and Markdown guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires a dLazy API key and sends prompts, selected media files, and generation parameters to dLazy-hosted services.]\n\n## Skill Version(s):\n\n1.3.20 (source: ClawHub release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.20:SKILL-cn.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，可以使用 dlazy jimeng-t2i -h 查看帮助信息。\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\n使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\r\n\r\n## 触发关键词\r\n\r\n- 即梦\r\n- jimeng\r\n- 生成图片、文生图\r\n- 画一张图\r\n\r\n## 身份验证 (Authentication)\r\n\r\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\r\n\r\n### 备选：手动设置 API Key\r\n\r\n如果你已有 API key，也可以直接保存：\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\r\n\r\n### 手动获取 API Key\r\n\r\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\r\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. 复制 API Key 区域显示的密钥\r\n\r\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\r\n\r\n## 关于与来源 (Provenance)\r\n\r\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **维护者**: dlazyai\r\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\r\n- **官网**: [dlazy.com](https://dlazy.com)\r\n\r\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\r\n\r\n## 工作原理\r\n\r\n此技能是 dLazy 托管 API 的轻量封装。调用时：\r\n\r\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\r\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\r\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\r\n\r\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\r\n\r\n## 使用方法\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\n执行 `dlazy jimeng-t2i` 命令获取结果。\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    提示词\r\n  --images [images...]                 参考图 [image: url or local path] (max 10)\r\n  --size [size]                        尺寸 [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## 输出格式\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## 命令示例\r\n\r\n```bash\r\n# 基础调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image '/path/to/image.png'\r\n\r\n# 复杂调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## 错误处理\r\n\r\n| Code | 错误类型                         | 示例信息                                                                                                                 |\r\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\r\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\r\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\r\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\r\n\r\n> **智能体关键指令**: \r\n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nArchive v1.3.19: 4 files, 8530 bytes\n\nFiles: skill-card.md (2447b), SKILL-cn.md (7366b), SKILL.md (7450b), _meta.json (136b)\n\nFile v1.3.19:SKILL.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When invoking this skill, use dlazy jimeng-t2i -h for help.\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\r\n\r\n## Trigger Keywords\r\n\r\n- jimeng\r\n- generate image, text to image\r\n- draw a picture\r\n\r\n## Authentication\r\n\r\nAll requests require a dLazy API key. The recommended way to authenticate is:\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\r\n\r\n### Alternative: Set the Key Manually\r\n\r\nIf you already have an API key, you can save it directly:\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\r\n\r\n### Getting Your API Key Manually\r\n\r\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\r\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. Copy the key shown in the API Key section\r\n\r\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\r\n\r\n## About & Provenance\r\n\r\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **Maintainer**: dlazyai\r\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\r\n- **Homepage**: [dlazy.com](https://dlazy.com)\r\n\r\nYou can install on demand without persisting a global binary by running:\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\r\n\r\n## How It Works\r\n\r\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\r\n\r\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\r\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\r\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\r\n\r\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\r\n\r\n## Usage\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\nRun the `dlazy jimeng-t2i` command to get results.\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    Prompt\r\n  --images [images...]                 Images [image: url or local path] (max 10)\r\n  --size [size]                        Size [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## Output Format\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## Command Examples\r\n\r\n```bash\r\n# basic call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image '/path/to/image.png'\r\n\r\n# complex call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## Error Handling\r\n\r\n| Code | Error Type                         | Example Message                                                                                                          |\r\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\r\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\r\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\r\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\r\n\r\n> **AGENT CRITICAL INSTRUCTION**: \r\n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nFile v1.3.19:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-jimeng-t2i\",\n  \"version\": \"1.3.19\",\n  \"publishedAt\": 1790039597337\n}\n\nFile v1.3.19:skill-card.md\n\n## Description:\n\nText-to-image generation with Jimeng that helps agents convert prompts into high-quality generated images.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to generate images from text prompts through the dLazy Jimeng text-to-image CLI. It can also use up to 10 reference image URLs or local paths when the user chooses to provide them.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts, generation parameters, and supplied media paths may be sent to dLazy cloud services.\n\nMitigation: Use only when the user accepts dLazy cloud processing, and avoid sending sensitive prompts or media unless that use is approved.\n\nRisk: Local media paths passed as inputs may be uploaded to files.dlazy.com for model access.\n\nMitigation: Review local file paths before invocation and confirm that uploaded media is appropriate for third-party processing.\n\nRisk: The dLazy CLI may store an API key in the local user configuration.\n\nMitigation: Prefer per-invocation credentials or protect and rotate the API key using dLazy account controls.\n\nRisk: Global installation of the npm CLI persists executable code on the system.\n\nMitigation: Prefer the pinned npx invocation or review the pinned npm package before global installation.\n\n## Reference(s):\n\n- [dLazy CLI source](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy homepage](https://dlazy.com)\n- [ClawHub skill page](https://clawhub.ai/dlazyai/skills/dlazy-jimeng-t2i)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, JSON, Files, Guidance]\n\n**Output Format:** [JSON response with generated image URLs, optional downloaded image files, and brief agent guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Supports dry-run mode, asynchronous generation IDs, polling, timeout control, and saving generated assets to a local path.]\n\n## Skill Version(s):\n\n1.3.19 (source: server release metadata; artifact frontmatter lists 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.19:SKILL-cn.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，可以使用 dlazy jimeng-t2i -h 查看帮助信息。\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\n使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\r\n\r\n## 触发关键词\r\n\r\n- 即梦\r\n- jimeng\r\n- 生成图片、文生图\r\n- 画一张图\r\n\r\n## 身份验证 (Authentication)\r\n\r\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\r\n\r\n### 备选：手动设置 API Key\r\n\r\n如果你已有 API key，也可以直接保存：\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\r\n\r\n### 手动获取 API Key\r\n\r\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\r\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. 复制 API Key 区域显示的密钥\r\n\r\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\r\n\r\n## 关于与来源 (Provenance)\r\n\r\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **维护者**: dlazyai\r\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\r\n- **官网**: [dlazy.com](https://dlazy.com)\r\n\r\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\r\n\r\n## 工作原理\r\n\r\n此技能是 dLazy 托管 API 的轻量封装。调用时：\r\n\r\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\r\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\r\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\r\n\r\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\r\n\r\n## 使用方法\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\n执行 `dlazy jimeng-t2i` 命令获取结果。\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    提示词\r\n  --images [images...]                 参考图 [image: url or local path] (max 10)\r\n  --size [size]                        尺寸 [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## 输出格式\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## 命令示例\r\n\r\n```bash\r\n# 基础调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image '/path/to/image.png'\r\n\r\n# 复杂调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## 错误处理\r\n\r\n| Code | 错误类型                         | 示例信息                                                                                                                 |\r\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\r\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\r\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\r\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\r\n\r\n> **智能体关键指令**: \r\n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nArchive v1.3.18: 4 files, 8453 bytes\n\nFiles: skill-card.md (2183b), SKILL-cn.md (7366b), SKILL.md (7450b), _meta.json (136b)\n\nFile v1.3.18:SKILL.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When invoking this skill, use dlazy jimeng-t2i -h for help.\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\r\n\r\n## Trigger Keywords\r\n\r\n- jimeng\r\n- generate image, text to image\r\n- draw a picture\r\n\r\n## Authentication\r\n\r\nAll requests require a dLazy API key. The recommended way to authenticate is:\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\r\n\r\n### Alternative: Set the Key Manually\r\n\r\nIf you already have an API key, you can save it directly:\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\r\n\r\n### Getting Your API Key Manually\r\n\r\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\r\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. Copy the key shown in the API Key section\r\n\r\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\r\n\r\n## About & Provenance\r\n\r\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **Maintainer**: dlazyai\r\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\r\n- **Homepage**: [dlazy.com](https://dlazy.com)\r\n\r\nYou can install on demand without persisting a global binary by running:\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\r\n\r\n## How It Works\r\n\r\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\r\n\r\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\r\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read them — the same flow as any cloud-based generation API.\r\n- Generated output URLs returned by the API are hosted on `files.dlazy.com`.\r\n\r\nThis is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See [dlazy.com](https://dlazy.com) for the full service terms.\r\n\r\n## Usage\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\nRun the `dlazy jimeng-t2i` command to get results.\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    Prompt\r\n  --images [images...]                 Images [image: url or local path] (max 10)\r\n  --size [size]                        Size [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## Output Format\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## Command Examples\r\n\r\n```bash\r\n# basic call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image '/path/to/image.png'\r\n\r\n# complex call:\r\ndlazy jimeng-t2i --prompt 'prompt text' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## Error Handling\r\n\r\n| Code | Error Type                         | Example Message                                                                                                          |\r\n| ---- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | Unauthorized (No API Key)          | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | Missing required parameter         | `error: required option '--prompt <prompt>' not specified`                                                              |\r\n| 502  | Local file read error              | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                          |\r\n| 503  | API request failed (no balance)    | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API request failed (server error)  | `HTTP status code error (500 server crash)`                                                                             |\r\n| 504  | Asynchronous task execution failed | `=== Generation Failed ===` / `{Specific error reason returned by backend, for example \"Prompt violates safety policy\"}` |\r\n\r\n> **AGENT CRITICAL INSTRUCTION**: \r\n> 1. If the execution result returns `code: \"insufficient_balance\"`, you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: [https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. If the execution result returns `code: \"unauthorized\"` or indicates missing API key, you MUST inform the user to get their API key from [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) and save it using `dlazy auth set <key>` and resume the task.\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nFile v1.3.18:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-jimeng-t2i\",\n  \"version\": \"1.3.18\",\n  \"publishedAt\": 1789867152984\n}\n\nFile v1.3.18:skill-card.md\n\n## Description:\n\nText-to-image generation with Jimeng that converts prompts into generated image outputs through the dLazy CLI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to have an agent generate Jimeng text-to-image assets from prompts, optionally with reference images and local save paths.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts, parameters, and local media paths may be sent to dLazy's hosted API and media storage.\n\nMitigation: Avoid submitting private prompts or files unless intended, and review the service terms before using the hosted generation workflow.\n\nRisk: Authentication can save a dLazy API key in the local CLI configuration.\n\nMitigation: Use trusted machines for saved credentials, use DLAZY_API_KEY for one-off invocations when appropriate, and rotate or revoke keys from the dLazy dashboard if needed.\n\nRisk: A global install persists the dLazy CLI on the system.\n\nMitigation: Use npx @dlazy/cli@1.2.3 for on-demand execution if a persistent global CLI install is not desired.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/dlazyai/skills/dlazy-jimeng-t2i)\n- [dLazy CLI Source](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm Package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy Homepage](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Configuration, Guidance, JSON, Files]\n\n**Output Format:** [Markdown instructions with bash commands and JSON command output]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Generated images are returned as hosted URLs and can be saved to a local path with --save.]\n\n## Skill Version(s):\n\n1.3.18 (source: server release evidence; artifact frontmatter reports 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.18:SKILL-cn.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，可以使用 dlazy jimeng-t2i -h 查看帮助信息。\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\n使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\r\n\r\n## 触发关键词\r\n\r\n- 即梦\r\n- jimeng\r\n- 生成图片、文生图\r\n- 画一张图\r\n\r\n## 身份验证 (Authentication)\r\n\r\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\r\n\r\n### 备选：手动设置 API Key\r\n\r\n如果你已有 API key，也可以直接保存：\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\r\n\r\n### 手动获取 API Key\r\n\r\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\r\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. 复制 API Key 区域显示的密钥\r\n\r\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\r\n\r\n## 关于与来源 (Provenance)\r\n\r\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **维护者**: dlazyai\r\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\r\n- **官网**: [dlazy.com](https://dlazy.com)\r\n\r\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\r\n\r\n## 工作原理\r\n\r\n此技能是 dLazy 托管 API 的轻量封装。调用时：\r\n\r\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\r\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\r\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\r\n\r\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\r\n\r\n## 使用方法\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\n执行 `dlazy jimeng-t2i` 命令获取结果。\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    提示词\r\n  --images [images...]                 参考图 [image: url or local path] (max 10)\r\n  --size [size]                        尺寸 [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async completion (default: \"1800\")\r\n  --save <path>                        Download the result asset to this local path (mkdir + retry handled for you)\r\n  -h, --help                           display help for command\r\n```\r\n\r\n> Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.\r\n\r\n## 输出格式\r\n\r\n```json\r\n{\r\n  \"ok\": true,\r\n  \"result\": {\r\n    \"tool\": \"jimeng-t2i\",\r\n    \"modelId\": \"jimeng-t2i-v40\",\r\n    \"outputs\": [\r\n      {\r\n        \"type\": \"image\",\r\n        \"id\": \"o_xxxxxxxx\",\r\n        \"url\": \"https://files.dlazy.com/result.png\",\r\n        \"mimeType\": \"image/png\"\r\n      }\r\n    ]\r\n  }\r\n}\r\n```\r\n\r\n> Async tasks (when `--no-wait` is passed) return `outputs: []` and a `task: { generateId, status }` field instead. Use `dlazy status <generateId> --wait` to poll.\r\n\r\n## 命令示例\r\n\r\n```bash\r\n# 基础调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image '/path/to/image.png'\r\n\r\n# 复杂调用：\r\ndlazy jimeng-t2i --prompt '提示词内容' --image 'https://files.dlazy.com/image.png'\r\n```\r\n\r\n## 错误处理\r\n\r\n| Code | 错误类型                         | 示例信息                                                                                                                 |\r\n| ---- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |\r\n| 401  | 未授权 (API Key缺失或无效)       | `ok: false, code: \"unauthorized\", message: \"API key is missing or invalid\"`                                                              |\r\n| 501  | 缺少必填参数                     | `error: required option '--prompt <prompt>' not specified`                                                               |\r\n| 502  | 本地文件读取失败                 | `Error: Image file/Video file not found: C:\\path\\to\\your\\file`                                                           |\r\n| 503  | API 请求失败（余额不足）         | `ok: false, code: \"insufficient_balance\"` |\r\n| 503  | API 请求失败（服务端错误）       | `HTTP status code error (500 server crash)`                                                                              |\r\n| 504  | 异步任务执行失败                 | `=== Generation Failed ===` / `{后端返回的具体失败原因，比如 \"Prompt violates safety policy\"}`                             |\r\n\r\n> **智能体关键指令**: \r\n> 1. 如果执行结果返回 `code: \"insufficient_balance\"` 且提示余额不足（Insufficient balance），您必须明确告知用户当前积分不足，并引导用户点击以下链接前往充值：[https://dlazy.com/dashboard/organization/settings?tab=credits](https://dlazy.com/dashboard/organization/settings?tab=credits)\r\n> 2. 如果执行结果返回 `code: \"unauthorized\"` 或提示缺少 API Key，您必须明确告知用户前往 [https://dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key) 获取 API Key 并使用 `dlazy auth set <key>` 保存，然后继续执行任务。\r\n\r\n## Tips\r\n\r\nVisit https://dlazy.com for more information.\n\nArchive v1.3.17: 4 files, 8486 bytes\n\nFiles: skill-card.md (2366b), SKILL-cn.md (7366b), SKILL.md (7450b), _meta.json (136b)\n\nFile v1.3.17:SKILL.md\n\n---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When invoking this skill, use dlazy jimeng-t2i -h for help.\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\r\n\r\n## Trigger Keywords\r\n\r\n- jimeng\r\n- generate image, text to image\r\n- draw a picture\r\n\r\n## Authentication\r\n\r\nAll requests require a dLazy API key. The recommended way to authenticate is:\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\r\n\r\n### Alternative: Set the Key Manually\r\n\r\nIf you already have an API key, you can save it directly:\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user","readmeExcerpt":"Skill: 文生图 即梦 Jimeng T2I Owner: dlazyai Summary: Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。 Tags: latest:1.3.26 Version history: v1.3.26 | 2026-10-08T01:17:41.305Z | user 例行版本更新 2026-10-08 v1.3.25 | 2026-10-04T01:16:37.029Z | user 例行版本更新 2026-10-04 v1.3.24 | 2026-10-02T04:58:27.900Z | user 例行版本更新 2026-10-02 v1.3.23 | 2026-09-30T01:15:21.9","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"When invoking this skill, use dlazy jimeng-t2i -h for help.\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\nText-to-image generation with Jimeng, quickly converting text to high-quality images.\r\n\r\n## Trigger Keywords\r\n\r\n- jimeng\r\n- generate image, text to image\r\n- draw a picture\r\n\r\n## Authentication\r\n\r\nAll requests require a dLazy API key. The recommended way to authenticate is:\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\nThis runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.\r\n\r\n### Alternative: Set the Key Manually\r\n\r\nIf you already have an API key, you can save it directly:\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nThe CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\\.dlazy\\config.json` on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.\r\n\r\n### Getting Your API Key Manually\r\n\r\n1. Sign in or create an account at [dlazy.com](https://dlazy.com)\r\n2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. Copy the key shown in the API Key section\r\n\r\nEach key is scoped to your dLazy organization and can be **rotated or revoked at any time** from the same dashboard.\r\n\r\n## About & Provenance\r\n\r\n- **CLI source code**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **Maintainer**: dlazyai\r\n- **npm package**: `@dlazy/cli` (pinned to `1.2.3` in this skill's install spec)\r\n- **Homepage**: [dlazy.com](https://dlazy.com)\r\n\r\nYou can install on demand without persisting a global binary by running:\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\nOr, if you prefer a global install, the skill's `metadata.clawdbot.install` field declares the exact pinned version (`npm install -g @dlazy/cli@1.2.3`). Review the GitHub source before installing.\r\n\r\n## How It Works\r\n\r\nThis skill is a thin client over the dLazy hosted API. When you invoke it:\r\n\r\n- Prompts and parameters you provide are sent to the dLazy API endpoint (`api.dlazy.com`) for inference.\r\n- Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (`files.dlazy.com`) so the model can read th"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-jimeng-t2i\",\n  \"version\": \"1.3.26\",\n  \"publishedAt\": 1791422261305\n}"},{"path":"skill-card.md","content":"## Description:\n\nHelps an agent generate images from text prompts with Jimeng through the dLazy CLI, with optional reference images.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nCreators and teams use this skill to request Jimeng text-to-image generation, optionally providing reference images and saving the result.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and explicitly supplied local media may be sent to the dLazy hosted service.\n\nMitigation: Confirm the user wants to use dLazy and avoid sending sensitive content without approval.\n\nRisk: Image generation may consume account credits.\n\nMitigation: Use the available dry-run cost estimate when appropriate and confirm before costly requests.\n\nRisk: The CLI can save an API key locally.\n\nMitigation: Protect local credentials and rotate or revoke the key if it is exposed.\n\nRisk: Installing a third-party npm CLI introduces package supply-chain exposure.\n\nMitigation: Review the pinned package source before installing in sensitive environments.\n\n## Reference(s):\n\n- [dLazy CLI source linked in skill metadata](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Guidance]\n\n**Output Format:** [Text guidance with CLI examples; the CLI returns JSON containing generated image URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Optional local download of generated images; asynchronous jobs can return a task ID.]\n\n## Skill Version(s):\n\n1.3.26 (source: ClawHub release metadata; supplied skill frontmatter lists 1.3.5)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."},{"path":"SKILL-cn.md","content":"---\r\nname: dlazy-jimeng-t2i\r\nversion: 1.3.5\r\ndescription: \"使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\"\r\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当调用此技能时，可以使用 dlazy jimeng-t2i -h 查看帮助信息。\"}}\r\n---\r\n\r\n# 文生图 即梦 Jimeng T2I\r\n\r\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\r\n\r\n\r\n使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。\r\n\r\n## 触发关键词\r\n\r\n- 即梦\r\n- jimeng\r\n- 生成图片、文生图\r\n- 画一张图\r\n\r\n## 身份验证 (Authentication)\r\n\r\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\r\n\r\n```bash\r\ndlazy login\r\n```\r\n\r\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\r\n\r\n### 备选：手动设置 API Key\r\n\r\n如果你已有 API key，也可以直接保存：\r\n\r\n```bash\r\ndlazy auth set YOUR_API_KEY\r\n```\r\n\r\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\r\n\r\n### 手动获取 API Key\r\n\r\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\r\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\r\n3. 复制 API Key 区域显示的密钥\r\n\r\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\r\n\r\n## 关于与来源 (Provenance)\r\n\r\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\r\n- **维护者**: dlazyai\r\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.2.3` 版本）\r\n- **官网**: [dlazy.com](https://dlazy.com)\r\n\r\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\r\n\r\n```bash\r\nnpx @dlazy/cli@1.2.3 <command>\r\n```\r\n\r\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\r\n\r\n## 工作原理\r\n\r\n此技能是 dLazy 托管 API 的轻量封装。调用时：\r\n\r\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\r\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\r\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\r\n\r\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。完整服务条款请参见 [dlazy.com](https://dlazy.com)。\r\n\r\n## 使用方法\r\n\r\n**CRITICAL INSTRUCTION FOR AGENT**:\r\n执行 `dlazy jimeng-t2i` 命令获取结果。\r\n\r\n```bash\r\ndlazy jimeng-t2i -h\r\n\r\nOptions:\r\n  --prompt [prompt]                    提示词\r\n  --images [images...]                 参考图 [image: url or local path] (max 10)\r\n  --size [size]                        尺寸 [default: 1440*2560] (choices: \"1024*1024\", \"2048*2048\", \"2304*1728\", \"2496*1664\", \"2560*1440\", \"3024*1296\", \"1728*2304\", \"1664*2496\", \"1440*2560\", \"1296*3024\", \"4096*4096\", \"4694*3520\", \"4992*3328\", \"5404*3040\", \"6198*2656\", \"3520*4694\", \"3328*4992\", \"3040*5404\", \"2656*6198\")\r\n  --dry-run                            Print payload + cost estimate without calling API\r\n  --no-wait                            Return generateId immediately for async tasks\r\n  --timeout <seconds>                  Max seconds to wait for async comple"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1341,"uniquenessScore":44,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T05:01:18.549Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T05:01:18.549Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T23:24:48.267Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}