{"id":"70f24b87-d7e1-469d-9db8-7cd4b4d20e94","entityType":"agent","slug":"clawhub-dlazyai-dlazy-image-storyboard","name":"分镜图工作流 Image Storyboard","canonicalUrl":"https://www.xpersona.co/agent/clawhub-dlazyai-dlazy-image-storyboard","canonicalPath":"/agent/clawhub-dlazyai-dlazy-image-storyboard","generatedAt":"2026-10-10T05:44:40.370Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:38:24.507Z","emptyReason":null},"description":"A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 4.9K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-image-storyboard","sourceUrl":"https://clawhub.ai/dlazyai/dlazy-image-storyboard","homepage":"https://clawhub.ai/dlazyai/skills/dlazy-image-storyboard","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/dlazyai/dlazy-image-storyboard","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/dlazyai/skills/dlazy-image-storyboard","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":74,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"分镜图工作流 Image Storyboard technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:38:24.507Z","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":"2026-10-09T04:38:24.507Z","emptyReason":null},"stars":null,"forks":null,"downloads":4881,"packageName":null,"latestVersion":"1.3.27","tractionLabel":"4.9K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:38:24.507Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T04:38:24.507Z","lastCrawledAt":"2026-10-09T04:38:24.507Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T04:38:24.507Z","lastVerifiedAt":null,"highlights":[{"version":"1.3.27","createdAt":"2026-10-08T01:15:33.845Z","changelog":"例行版本更新 2026-10-08","fileCount":4,"zipByteSize":11315},{"version":"1.3.26","createdAt":"2026-10-04T01:14:24.850Z","changelog":"例行版本更新 2026-10-04","fileCount":4,"zipByteSize":11216},{"version":"1.3.25","createdAt":"2026-10-02T04:56:52.042Z","changelog":"例行版本更新 2026-10-02","fileCount":4,"zipByteSize":11178},{"version":"1.3.24","createdAt":"2026-09-30T01:13:13.777Z","changelog":"例行版本更新 2026-09-30","fileCount":4,"zipByteSize":11210},{"version":"1.3.23","createdAt":"2026-09-28T02:12:19.246Z","changelog":"例行版本更新 2026-09-28","fileCount":4,"zipByteSize":11160},{"version":"1.3.22","createdAt":"2026-09-28T01:14:34.460Z","changelog":"例行版本更新 2026-09-28","fileCount":4,"zipByteSize":11180},{"version":"1.3.21","createdAt":"2026-09-24T01:51:02.497Z","changelog":"例行版本更新 2026-09-24","fileCount":4,"zipByteSize":11306},{"version":"1.3.20","createdAt":"2026-09-22T01:11:58.587Z","changelog":"例行版本更新 2026-09-22","fileCount":4,"zipByteSize":11325}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-image-storyboard","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-image-storyboard` 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-image-storyboard 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-image-storyboard/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-storyboard/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-storyboard/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-storyboard/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-storyboard/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-storyboard/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T05:44:40.366Z"}},"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-image-storyboard/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-storyboard/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-storyboard/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-storyboard/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":"2026-10-09T04:38:24.507Z","emptyReason":null},"readme":"Skill: 分镜图工作流 Image Storyboard\n\nOwner: dlazyai\n\nSummary: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\n\nTags: latest:1.3.27\n\nVersion history:\n\nv1.3.27 | 2026-10-08T01:15:33.845Z | user\n\n例行版本更新 2026-10-08\n\nv1.3.26 | 2026-10-04T01:14:24.850Z | user\n\n例行版本更新 2026-10-04\n\nv1.3.25 | 2026-10-02T04:56:52.042Z | user\n\n例行版本更新 2026-10-02\n\nv1.3.24 | 2026-09-30T01:13:13.777Z | user\n\n例行版本更新 2026-09-30\n\nv1.3.23 | 2026-09-28T02:12:19.246Z | user\n\n例行版本更新 2026-09-28\n\nv1.3.22 | 2026-09-28T01:14:34.460Z | user\n\n例行版本更新 2026-09-28\n\nv1.3.21 | 2026-09-24T01:51:02.497Z | user\n\n例行版本更新 2026-09-24\n\nv1.3.20 | 2026-09-22T01:11:58.587Z | user\n\n例行版本更新 2026-09-22\n\nv1.3.19 | 2026-09-20T01:17:38.539Z | user\n\n例行版本更新 2026-09-20\n\nv1.3.18 | 2026-09-18T01:39:30.502Z | user\n\n例行版本更新 2026-09-18\n\nv1.3.17 | 2026-09-14T01:14:12.892Z | user\n\n例行版本更新 2026-09-14\n\nv1.3.16 | 2026-09-10T01:11:26.906Z | user\n\n例行版本更新 2026-09-10\n\nv1.3.15 | 2026-09-08T01:12:11.830Z | user\n\n例行版本更新 2026-09-08\n\nv1.3.14 | 2026-09-07T01:15:46.256Z | user\n\n例行版本更新 2026-09-07\n\nv1.3.13 | 2026-09-04T01:17:41.296Z | user\n\n例行版本更新 2026-09-04\n\nv1.3.12 | 2026-09-02T01:12:10.253Z | user\n\n例行版本更新 2026-09-02\n\nv1.3.11 | 2026-08-31T02:52:48.068Z | user\n\n源码仓库迁移至 github.com/dlazy-ai/cli\n\nv1.3.10 | 2026-08-24T09:23:44.897Z | user\n\nRestore Chinese display name\n\nv1.3.9 | 2026-08-17T09:06:19.079Z | user\n\nRestore Chinese display name\n\nv1.3.8 | 2026-08-10T05:47:32.782Z | user\n\nRestore Chinese display name\n\nv1.3.7 | 2026-08-10T04:02:05.013Z | user\n\nRestore Chinese display name\n\nv1.3.6 | 2026-07-21T02:18:50.534Z | auto\n\n- Updated CLI dependency to @dlazy/cli version 1.2.3 in install instructions and metadata.\n- Removed the skill-card.md file.\n- No changes to core workflow or usage instructions.\n\nv1.3.5 | 2026-07-20T05:53:25.586Z | user\n\n规范 dlazy- 前缀命名，补充中文显示名\n\nv1.3.4 | 2026-07-17T10:38:47.226Z | auto\n\n- Updated version to 1.2.2.\n- Documentation updates in SKILL.md and SKILL-cn.md.\n- Removed redundant file: skill-card.md.\n\nv1.2.2 | 2026-07-17T08:44:53.307Z | auto\n\n- Removed the file: skill-card.md.\n- Made minor updates to SKILL.md and SKILL-cn.md, but no user-facing functionality change is apparent.\n- Version in SKILL.md downgraded from 1.2.2 to 1.2.1, possibly correcting a previous version discrepancy.\n- No changes to usage instructions or workflow visible in the changelog context.\n\nv1.3.3 | 2026-07-09T01:48:27.601Z | user\n\nset Chinese display name for CN search\n\nv1.3.2 | 2026-07-09T01:48:14.739Z | user\n\nset Chinese display name for CN search\n\nv1.3.1 | 2026-07-09T01:30:43.456Z | user\n\nset Chinese display name for CN search\n\nv1.3.0 | 2026-07-07T19:44:31.228Z | auto\n\n- Updated to version 1.3.0.\n- Documentation improvements in both English (SKILL.md) and Chinese (SKILL-cn.md) files.\n- No changes to core logic or technical instructions; update is documentation-only for clarity and completeness.\n\nv1.2.1 | 2026-07-07T18:32:35.473Z | auto\n\n- Skill renamed from \"image-storyboard\" to \"dlazy-image-storyboard\".\n- Added concise Chinese description in the main description field.\n- Updated SKILL.md and SKILL-cn.md documentation.\n- Removed redundant skill-card.md file.\n- No changes to command syntax or API endpoints.\n\nv1.2.0 | 2026-06-02T10:04:38.055Z | auto\n\n- Updated CLI dependency to use @dlazy/cli version 1.2.0 (was 1.0.9).\n- Changed install instructions and metadata to point to the latest CLI version.\n- Removed the unused skill-card.md file.\n- No other workflow or logic changes; all feature sets and instructions remain consistent.\n\nv1.1.2 | 2026-06-02T01:40:47.766Z | user\n\nUpdate model skills (names/params refreshed); add search-audio/image/video\n\nv1.1.1 | 2026-05-06T14:14:03.649Z | auto\n\nimage-storyboard 1.1.1\n\n- Documentation updated in both SKILL.md and SKILL-cn.md files.\n- No changes to core logic or workflow; all updates are related to documentation clarity and instructions.\n\nv1.1.0 | 2026-05-01T07:57:04.781Z | auto\n\n- Adds recommendation to use `dlazy login` for simplified authentication via device code flow\n- Updates authentication section to clarify login options and emphasize reduced need for manual API key handling\n- No changes to core storyboard workflow, planning, or technical execution\n- Documentation improvements for ease of setup and clarity\n\nv1.0.9 | 2026-04-30T10:22:56.358Z | user\n\nSync to CLI 1.0.9 with cliWarning support\n\nv1.0.5 | 2026-04-29T02:35:57.946Z | user\n\nbump @dlazy/cli to 1.0.8\n\nv1.0.4 | 2026-04-27T08:04:00.066Z | 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 | 2026-04-27T07:42:42.964Z | 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 | 2026-04-24T04:09:57.743Z | auto\n\nimage-storyboard v1.0.2\n\n- Updated documentation files SKILL.md, SKILL-en.md, and SKILL-cn.md with minor text improvements and clarifications.\n- No changes to core functionality or workflow logic.\n- Improved instructions and formatting for clearer user guidance.\n\nv1.0.1 | 2026-04-24T03:36:21.848Z | auto\n\nimage-storyboard 1.0.1\n\n- 新增身份验证说明，要求配置 dLazy API key，并提供获取与设置的详细指引。\n- 更新依赖：dlazy CLI 升级至 1.0.6 版本。\n- 技能主流程、规范与执行说明保持与上一版本一致，仅在文档文件（SKILL.md 及多语言文档）做补充和修订。\n\nv1.0.0 | 2026-04-23T08:01:43.895Z | auto\n\nInitial release of image-storyboard skill — a professional storyboard tool for film, advertising, short video, and educational storytelling.\n\n- Provides a strict \"plan first, then render\" workflow for generating industry-standard storyboards.\n- Covers both cinematic (movies, commercials, shorts) and narrative (education, comics) storyboard workflows.\n- Enforces rigorous step-by-step user interaction with required confirmations at key stages (requirements, character design, script, image generation).\n- Requires precise technical specifications and metadata for each storyboard type.\n- Includes role design standards, script formatting, and professional delivery options (including A4/PDF export and layout variations).\n- Prohibits batch image generation and mandates terminal command usage for rendering images.\n\nArchive index:\n\nArchive v1.3.27: 4 files, 11315 bytes\n\nFiles: skill-card.md (2295b), SKILL-cn.md (9177b), SKILL.md (9177b), _meta.json (142b)\n\nFile v1.3.27:SKILL.md\n\n---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.27:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-storyboard\",\n  \"version\": \"1.3.27\",\n  \"publishedAt\": 1791422133845\n}\n\nFile v1.3.27:skill-card.md\n\n## Description:\n\nGuides film, advertising, short-video, and educational storyboard creation through a plan-first workflow with approval gates before image generation.\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 production teams use this skill to plan character designs, write shot-by-shot scripts, generate storyboard images after approval, and prepare cinematic or narrative layouts for delivery.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected media files are sent to dLazy's hosted services.\n\nMitigation: Review content before submission and avoid sharing sensitive prompts or media without authorization.\n\nRisk: Using the CLI requires a dLazy API key stored locally or provided by environment variable.\n\nMitigation: Protect the key, use only a trusted installation, and rotate or revoke it if exposed.\n\nRisk: One documentation line names a different CLI version than the pinned install commands.\n\nMitigation: Confirm the intended CLI version before installing; use the on-demand npx command if a global install is unnecessary.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-image-storyboard)\n- [dLazy CLI repository (listed by skill metadata; not verified release provenance)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Shell commands, Images, PDF]\n\n**Output Format:** [Bulleted storyboard plans and scripts, image links, and a print-ready A4 storyboard layout]\n\n**Output Parameters:** [1D text with linked image outputs; A4 landscape for final layout]\n\n**Other Properties Related to Output:** [The workflow requests approval at requirements, character, script, and image-delivery gates.]\n\n## Skill Version(s):\n\n1.3.27 (source: ClawHub release metadata; supplied skill frontmatter says 1.3.6)\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 v1.3.27:SKILL-cn.md\n\n---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.26: 4 files, 11216 bytes\n\nFiles: skill-card.md (2052b), SKILL-cn.md (9177b), SKILL.md (9177b), _meta.json (142b)\n\nFile v1.3.26:SKILL.md\n\n---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.26:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-storyboard\",\n  \"version\": \"1.3.26\",\n  \"publishedAt\": 1791076464850\n}\n\nFile v1.3.26:skill-card.md\n\n## Description:\n\nHelps creators plan, script, and generate cinematic or narrative storyboards with approval checkpoints before rendering 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\nFilmmakers, advertisers, educators, and other creators use this skill to turn a brief into character references, shot-by-shot scripts, and storyboard images, confirming each stage before proceeding.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The networked dLazy CLI sends prompts and parameters to its cloud API and uploads referenced media files.\n\nMitigation: Use only media intended for upload and review prompts and file paths before generating images.\n\nRisk: Installing the third-party CLI or retaining an API key adds supply-chain and credential exposure.\n\nMitigation: Review the CLI before installation; consider the on-demand npx option and a per-session DLAZY_API_KEY instead of persistent setup.\n\n## Reference(s):\n\n- [dLazy CLI source (linked in skill metadata; not verified release provenance)](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):** [Markdown, Image URLs, Shell commands, Guidance]\n\n**Output Format:** [Markdown shot lists and visual prompts, with generated image links]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires confirmation at planning, character, script, and image-delivery stages; specifies an A4 landscape storyboard layout for print or PDF export.]\n\n## Skill Version(s):\n\n1.3.26 (source: server-resolved release; skill frontmatter says 1.3.6)\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---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.25: 4 files, 11178 bytes\n\nFiles: skill-card.md (1983b), SKILL-cn.md (9177b), SKILL.md (9177b), _meta.json (142b)\n\nFile v1.3.25:SKILL.md\n\n---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.25:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-storyboard\",\n  \"version\": \"1.3.25\",\n  \"publishedAt\": 1790917012042\n}\n\nFile v1.3.25:skill-card.md\n\n## Description:\n\nGuides cinematic and narrative storyboard creation through approved specifications, character design, scripts, and image generation.\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 production teams use this skill to plan film, advertising, short-video, educational, and comic-style storyboards, approving each stage before generating 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 cloud service, with generated images hosted remotely.\n\nMitigation: Avoid sensitive material and approve prompts and local media before submission; review hosted output links before sharing.\n\nRisk: The dLazy API key may be saved in the user's local CLI profile.\n\nMitigation: Use the DLAZY_API_KEY environment variable when persistent storage is unwanted, and rotate or revoke exposed keys.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-image-storyboard)\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\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Image URLs, Storyboard guidance]\n\n**Output Format:** [Markdown bullet lists with per-panel prompts, generation commands, and image links]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Includes shot and scene specifications, approval checkpoints, and A4 landscape print/PDF layout guidance.]\n\n## Skill Version(s):\n\n1.3.25 (source: ClawHub release)\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---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.24: 4 files, 11210 bytes\n\nFiles: skill-card.md (2073b), SKILL-cn.md (9177b), SKILL.md (9177b), _meta.json (142b)\n\nFile v1.3.24:SKILL.md\n\n---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.24:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-storyboard\",\n  \"version\": \"1.3.24\",\n  \"publishedAt\": 1790730793777\n}\n\nFile v1.3.24:skill-card.md\n\n## Description:\n\nGuides film, advertising, short-video, and educational storyboard creation through a plan-first, render-later workflow.\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 production teams use this skill to plan characters, script and approve storyboard panels, generate images, and prepare cinematic or narrative storyboard layouts.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and referenced media may be sent to dLazy, and generated image URLs are hosted there.\n\nMitigation: Avoid sending sensitive briefs or media unless dLazy's cloud handling is acceptable.\n\nRisk: Login stores an API key in local CLI configuration.\n\nMitigation: Protect the local configuration or use the DLAZY_API_KEY environment-variable option.\n\nRisk: Installing the CLI globally runs third-party package code.\n\nMitigation: Review the npm package and linked CLI source before installing, or use the documented on-demand invocation.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-image-storyboard)\n- [dLazy CLI source (listed in skill metadata; 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):** [Markdown, Shell commands, Image URLs]\n\n**Output Format:** [Bulleted storyboard plans and scripts, image links, and print/PDF layout guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires confirmation at key stages before generating successive images.]\n\n## Skill Version(s):\n\n1.3.24 (source: ClawHub release metadata; embedded skill frontmatter: 1.3.6)\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---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.23: 4 files, 11160 bytes\n\nFiles: skill-card.md (1965b), SKILL-cn.md (9177b), SKILL.md (9177b), _meta.json (142b)\n\nFile v1.3.23:SKILL.md\n\n---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.23:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-storyboard\",\n  \"version\": \"1.3.23\",\n  \"publishedAt\": 1790561539246\n}\n\nFile v1.3.23:skill-card.md\n\n## Description:\n\nGuides creators through planning, character approval, scripted shots, and image generation for cinematic and narrative storyboards.\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\nFilm, advertising, short-video, and education creators use this skill to plan and approve characters and shot scripts before generating storyboard visuals and preparing a printable layout.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Creative prompts and selected media files are sent to dLazy's cloud service.\n\nMitigation: Review prompts and media before submission; use only content approved for external processing.\n\nRisk: Installing the CLI and storing API credentials locally may expose an unverified package or persistent key.\n\nMitigation: Verify the @dlazy/cli package and pinned version before use; prefer DLAZY_API_KEY for non-persistent credentials.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-image-storyboard)\n- [dLazy CLI repository](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, Guidance, Shell commands]\n\n**Output Format:** [Markdown with shot lists, prompts, and image links]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Includes approval checkpoints, shot metadata, character references, and links to generated images; final layout targets A4 landscape print or PDF.]\n\n## Skill Version(s):\n\n1.3.23 (source: ClawHub release metadata; artifact frontmatter: 1.3.6)\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---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.22: 4 files, 11180 bytes\n\nFiles: skill-card.md (2011b), SKILL-cn.md (9177b), SKILL.md (9177b), _meta.json (142b)\n\nFile v1.3.22:SKILL.md\n\n---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.22:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-storyboard\",\n  \"version\": \"1.3.22\",\n  \"publishedAt\": 1790558074460\n}\n\nFile v1.3.22:skill-card.md\n\n## Description:\n\nGuides film, advertising, short-video, and educational storyboard creation through an approval-gated plan-first, render-later workflow.\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 production teams use this skill to turn creative briefs into cinematic or narrative storyboards, confirming specifications, character designs, and scripts before generating images one at a time.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Creative prompts and referenced media are sent to dLazy cloud services.\n\nMitigation: Avoid supplying sensitive creative assets unless their upload and processing by dLazy are acceptable.\n\nRisk: The workflow uses an external CLI and a dLazy API key.\n\nMitigation: Review the CLI package before use, protect the API key, and prefer npx when a lasting global installation is unnecessary.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-image-storyboard)\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- [dLazy website](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands]\n\n**Output Format:** [Bulleted Markdown with storyboard specifications, image prompts, and generated image URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Approval-gated character reference and per-image generation; A4 landscape print/PDF delivery specification.]\n\n## Skill Version(s):\n\n1.3.22 (source: ClawHub release metadata; artifact frontmatter lists 1.3.6)\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---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.21: 4 files, 11306 bytes\n\nFiles: skill-card.md (2348b), SKILL-cn.md (9177b), SKILL.md (9177b), _meta.json (142b)\n\nFile v1.3.21:SKILL.md\n\n---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.21:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-storyboard\",\n  \"version\": \"1.3.21\",\n  \"publishedAt\": 1790214662497\n}\n\nFile v1.3.21:skill-card.md\n\n## Description:\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\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 creative teams use this skill to turn creative briefs into cinematic or narrative storyboard workflows with requirements gates, character reference planning, script structure, image generation steps, and final storyboard layout guidance.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected local media paths or files may be sent to dLazy cloud endpoints for generation.\n\nMitigation: Use this skill only with content approved for dLazy cloud processing and avoid submitting sensitive media unless that use is authorized.\n\nRisk: API keys may be stored in the local dLazy CLI configuration.\n\nMitigation: Prefer environment-variable credentials for short-lived use or rotate and revoke stored API keys when local credential persistence is a concern.\n\nRisk: Generated outputs are hosted on files.dlazy.com.\n\nMitigation: Review generated result URLs and sharing expectations before distributing storyboard outputs.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dlazyai/skills/dlazy-image-storyboard)\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):** [Guidance, Markdown, Shell commands]\n\n**Output Format:** [Markdown text with bulleted plans, image-generation prompts, synchronous CLI commands, and generated image URLs.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires user confirmation gates before image generation and sends prompts or selected media to dLazy cloud endpoints.]\n\n## Skill Version(s):\n\n1.3.21 (source: server release evidence; artifact frontmatter lists 1.3.6)\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---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.20: 4 files, 11325 bytes\n\nFiles: skill-card.md (2408b), SKILL-cn.md (9177b), SKILL.md (9177b), _meta.json (142b)\n\nFile v1.3.20:SKILL.md\n\n---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.20:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-storyboard\",\n  \"version\": \"1.3.20\",\n  \"publishedAt\": 1790039518587\n}\n\nFile v1.3.20:skill-card.md\n\n## Description:\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict plan-first, render-later flow.\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\nCreative teams, developers, and agents use this skill to turn film, advertising, short-video, educational, or comic-style briefs into gated storyboard plans, character references, panel prompts, and generated storyboard imagery.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected media files may be sent to dLazy cloud endpoints for image generation.\n\nMitigation: Use the skill only when sending that content to dLazy is acceptable, and avoid sensitive media unless the deployment has approved that data flow.\n\nRisk: Using the dLazy CLI requires an API key and may store credentials in local CLI configuration.\n\nMitigation: Prefer the DLAZY_API_KEY environment variable when persistent local configuration is not desired, and rotate or revoke keys from the dLazy dashboard when needed.\n\nRisk: The workflow depends on installing or running the third-party npm CLI.\n\nMitigation: Review the CLI source or npm package before global installation, or use the pinned npx command for on-demand execution.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dlazyai/skills/dlazy-image-storyboard)\n- [dLazy CLI homepage](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy website](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Markdown with storyboard planning bullets, prompt drafts, confirmation gates, generated image URLs, and inline shell commands.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [The workflow uses user confirmation gates before image generation and runs one synchronous dLazy CLI generation command at a time.]\n\n## Skill Version(s):\n\n1.3.20 (source: release evidence)\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---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to proceed to the character design phase?</suggestion>`\n\n### State 2: Character Design (Visual Bible)\n\nGoal: lock in character appearance to prevent later drift.\n\nExecution requirements:\n\n1. Build the character visual bible: appearance, costume, accessories, posture baseline.\n2. Generate and present a single character master reference image.\n3. Output as a bulleted list.\n4. Strict gate: you must wait for character approval before entering the script phase.\n\nSuggested prompt:\n\n- `<suggestion>Character look is locked — start the storyboard script?</suggestion>`\n\n### State 3: Storyboard Production (Script and Visuals)\n\n#### Phase 1: Script Writing (think)\n\n- Convert the narrative into a structured script.\n- Output as a bulleted list.\n- Strict gate: do not generate images until the script is approved.\n\n## Output Requirements\n\n- Use bulleted lists, not tables (except for the delivery layout spec).\n- Clearly mark current state, completed items, and items awaiting confirmation.\n- All critical gate nodes must wait for user confirmation before continuing.\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.19: 4 files, 11253 bytes\n\nFiles: skill-card.md (2205b), SKILL-cn.md (9177b), SKILL.md (9177b), _meta.json (142b)\n\nFile v1.3.19:SKILL.md\n\n---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes at least:\n\n- Requirements exploration and tech-spec lock-in\n- Character design and character master sheet confirmation\n- Script structuring and script-gate confirmation\n- Image generation and batched delivery\n- Final storyboard assembly and export\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update the task plan as soon as each state finishes.\n- When the user asks to roll back or rework, add or re-order tasks and return to the corresponding state.\n\n## Technical Specification System\n\n### 1) Cinematic Storyboards (Film / Ad / Short)\n\n- Aspect ratios: 16:9, 2.35:1, 9:16, etc.\n- Required metadata:\n  - Shot size (close-up, medium, wide, etc.)\n  - Camera movement (push, pull, pan, dolly, tracking)\n  - Lighting and color temperature\n\n### 2) Narrative Storyboards (Education / Comic)\n\n- Aspect ratios: comic or vertical-narrative standards\n- Required metadata:\n  - Sequence markers (e.g., S01-P03)\n  - Mood tags (tense, warm, relieved, etc.)\n\n### 3) Character Master Sheet\n\n- Visual standard: clean full-body reference, no text, frames, or UI elements\n- Style fit:\n  - Cinematic projects prefer photoreal style\n  - Narrative projects prefer 2D or sketch styles\n- Core elements:\n  - Identity, age, vibe\n  - Appearance, costume details, key accessories\n- Generation formula:\n  - `[subject] + [character traits] + [tech specs] + [style] --no text`\n\n### 4) Script Structure Format\n\nEvery storyboard panel must output in this structure:\n\n- Visual prompt: [subject/character] + [action/interaction] + [environment/scene]\n- Tech params: [shot size, camera, lighting, etc.]\n- Text/logic: [narrative or logic elements]\n- Status: [pending / generated]\n\n### 5) Delivery Spec (final storyboard)\n\n- Paper size: A4 landscape (297mm × 210mm)\n- Output: print and PDF export\n- L1 layout (vertical film strip, cinematic): black background, single column\n- L2 layout (comic grid, narrative): white background, thick borders, caption boxes, step markers\n\n## Standard Workflow (4 states)\n\nEvery reply must start with:\n\n- `**Current Step:** [state] | **Next:** [goal]`\n\n### State 1: Requirements Exploration and Validation\n\nGoal: lock in tech specs and the style guide.\n\nExecution requirements:\n\n1. Analyze the user's input and fill in missing info.\n2. Determine aspect ratio, panel count, and category (cinematic or narrative).\n3. Output as a bulleted list, not a table.\n4. Wait for the user's explicit \"continue\" or \"confirm.\"\n\nSuggested prompt:\n\n- `<suggestion>The specs are organized — confirm to pr\n\nArchive v1.3.18: 4 files, 11352 bytes\n\nFiles: skill-card.md (2424b), SKILL-cn.md (9177b), SKILL.md (9177b), _meta.json (142b)","readmeExcerpt":"Skill: 分镜图工作流 Image Storyboard Owner: dlazyai Summary: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow. Tags: latest:1.3.27 Version history: v1.3.27 | 2026-10-08T01:15:33.845Z | user 例行版本更新 2026-10-08 v1.3.26 | 2026-10-04T01:14:24.850Z | user 例行版本更新 2026-10-04 v1.3.25 | 2026-10-02T04:56:52.042Z | user 例行版本更新","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"dlazy login"},{"language":"bash","snippet":"dlazy auth set YOUR_API_KEY"},{"language":"bash","snippet":"npx @dlazy/cli@1.2.3 <command>"},{"language":"bash","snippet":"dlazy login"},{"language":"bash","snippet":"dlazy auth set YOUR_API_KEY"},{"language":"bash","snippet":"npx @dlazy/cli@1.2.3 <command>"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes a"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-storyboard\",\n  \"version\": \"1.3.27\",\n  \"publishedAt\": 1791422133845\n}"},{"path":"skill-card.md","content":"## Description:\n\nGuides film, advertising, short-video, and educational storyboard creation through a plan-first workflow with approval gates before image generation.\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 production teams use this skill to plan character designs, write shot-by-shot scripts, generate storyboard images after approval, and prepare cinematic or narrative layouts for delivery.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected media files are sent to dLazy's hosted services.\n\nMitigation: Review content before submission and avoid sharing sensitive prompts or media without authorization.\n\nRisk: Using the CLI requires a dLazy API key stored locally or provided by environment variable.\n\nMitigation: Protect the key, use only a trusted installation, and rotate or revoke it if exposed.\n\nRisk: One documentation line names a different CLI version than the pinned install commands.\n\nMitigation: Confirm the intended CLI version before installing; use the on-demand npx command if a global install is unnecessary.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-image-storyboard)\n- [dLazy CLI repository (listed by skill metadata; not verified release provenance)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Shell commands, Images, PDF]\n\n**Output Format:** [Bulleted storyboard plans and scripts, image links, and a print-ready A4 storyboard layout]\n\n**Output Parameters:** [1D text with linked image outputs; A4 landscape for final layout]\n\n**Other Properties Related to Output:** [The workflow requests approval at requirements, character, script, and image-delivery gates.]\n\n## Skill Version(s):\n\n1.3.27 (source: ClawHub release metadata; supplied skill frontmatter says 1.3.6)\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":"---\nname: dlazy-image-storyboard\nversion: 1.3.6\ndescription: A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.\ntriggers:\n  - Storyboard Workflow Director\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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\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。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\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。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\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**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\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：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\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。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\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。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\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。\n\n---\nname: 'image-storyboard'\ndescription: 'A professional storyboard skill that turns user creative briefs into industry-standard storyboards, covering film, advertising, short video, and educational narrative scenarios.'\n---\n\n# 分镜图工作流 Image Storyboard\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict \"plan first, render later\" flow.\n\n## Core Positioning\n\nTurn user creative briefs into industry-grade storyboards across two main pipelines:\n\n- Cinematic storyboards: film, advertising, shorts\n- Narrative storyboards: educational content, comic-style narrative\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any execution, set up a task plan that includes a"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1255,"uniquenessScore":41,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T04:38:24.507Z","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":"2026-10-09T04:38:24.507Z","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":"2026-10-10T05:44:40.370Z","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"}]}}}