{"id":"8ac90d6b-7f24-4f13-aa22-18e904026762","entityType":"agent","slug":"clawhub-jeekchen-picnow","name":"Picnow — Image Generation","canonicalUrl":"https://www.xpersona.co/agent/clawhub-jeekchen-picnow","canonicalPath":"/agent/clawhub-jeekchen-picnow","generatedAt":"2026-10-13T03:11:06.046Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-12T00:51:22.891Z","emptyReason":null},"description":"Generate high-quality images via Picnow (api.letmego.top). Activate when the user wants to create, generate, draw, or design images — including product photo... Skill: Picnow — Image Generation Owner: jeekchen Summary: Generate high-quality images via Picnow (api.letmego.top). Activate when the user wants to create, generate, draw, or design images — including product photo... Tags: async:1.1.0, claude-code:1.1.0, claude-skill:1.0.1, gpt-image-2:1.1.0, hermess-agent:1.1.0, image-generation:1.1.0, image-to-image:1.1.0, latest:1.1.0, openclaw:1.1.0, picnow:1.1.0, text-to-image","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 965 downloads reported by the source. Last updated 10/12/2026.","installCommand":"clawhub skill install s173f300j681dxrv9x50arfmp9868yzn:picnow","sourceUrl":"https://clawhub.ai/jeekchen/picnow","homepage":"https://clawhub.ai/jeekchen/skills/picnow","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/jeekchen/picnow","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/jeekchen/skills/picnow","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Generate high-quality images via Picnow (api.letmego.top). Activate when the user wants to create, generate, draw, or design images — including product photo..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:51:22.891Z","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":"2026-10-12T00:51:22.891Z","emptyReason":null},"stars":null,"forks":null,"downloads":965,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.1.0","tractionLabel":"965 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:51:22.880Z","emptyReason":null},"lastUpdatedAt":"2026-10-12T00:51:22.891Z","lastCrawledAt":"2026-10-12T00:51:22.880Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-13T00:51:22.880Z","lastVerifiedAt":null,"highlights":[{"version":"1.1.0","createdAt":"2026-05-28T15:04:00.606Z","changelog":"v1.1.0 — Switch to async image API; fixes \"image fails to generate\" on 2K/4K renders 【Root cause】The previous version called the synchronous endpoints /v1/images/{generations,edits}. 2K/4K renders and complex image-to-image edits often exceeded 100s and were killed by Cloudflare's edge timeout (524), which users experienced as silent failures. 【Changes】 - Switched to the async API /v1/async/images/{generations,edits}: submission returns a task_id immediately, the client polls until completion - Polling: 1.5s initial delay, 3s interval, 10 min cap - Return value is still an upstream public CDN URL — no auth required, ready to render or share inline - CLI flags and stdout JSON format are unchanged; no migration needed 【Verified】 - 1K square text-to-image: ~10s - 2K landscape text-to-image: 62s - 1K image-to-image edit: 117s ✅ (would have hit Cloudflare 524 on the old sync path) - Error paths (missing token, invalid token, task failure, submission error) all surface clean messages and exit 1 【Deprecated】1.0.0 and 1.0.1 are marked deprecated on npm. All users should upgrade to 1.1.0+.","fileCount":5,"zipByteSize":8449},{"version":"1.0.1","createdAt":"2026-05-07T16:08:45.243Z","changelog":"- Initial release of Picnow image generation skill. - Supports high-quality text-to-image and image-to-image generation, including editing, style transfer, and background change. - Offers 1K, 2K, and 4K resolution options; supports square, landscape, and portrait aspect ratios. - Handles both English and Chinese trigger phrases for flexible activation. - Provides clear error handling and user guidance for missing or invalid API keys, quota issues, and network errors. - Outputs image URLs with options to preview, download, or generate variations.","fileCount":4,"zipByteSize":6046}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s173f300j681dxrv9x50arfmp9868yzn:picnow","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"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-jeekchen-picnow/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jeekchen-picnow/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jeekchen-picnow/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-jeekchen-picnow/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-jeekchen-picnow/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-jeekchen-picnow/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-13T03:11:06.046Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jeekchen-picnow/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jeekchen-picnow/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jeekchen-picnow/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-jeekchen-picnow/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":"high","updatedAt":"2026-10-12T00:51:22.891Z","emptyReason":null},"readme":"Skill: Picnow — Image Generation\n\nOwner: jeekchen\n\nSummary: Generate high-quality images via Picnow (api.letmego.top). Activate when the user wants to create, generate, draw, or design images — including product photo...\n\nTags: async:1.1.0, claude-code:1.1.0, claude-skill:1.0.1, gpt-image-2:1.1.0, hermess-agent:1.1.0, image-generation:1.1.0, image-to-image:1.1.0, latest:1.1.0, openclaw:1.1.0, picnow:1.1.0, text-to-image:1.1.0\n\nVersion history:\n\nv1.1.0 | 2026-05-28T15:04:00.606Z | user\n\nv1.1.0 — Switch to async image API; fixes \"image fails to generate\" on 2K/4K renders\n\n  【Root cause】The previous version called the synchronous endpoints /v1/images/{generations,edits}. 2K/4K renders and complex image-to-image edits often exceeded 100s and were killed by\n   Cloudflare's edge timeout (524), which users experienced as silent failures.\n\n  【Changes】\n  - Switched to the async API /v1/async/images/{generations,edits}: submission returns a task_id immediately, the client polls until completion\n  - Polling: 1.5s initial delay, 3s interval, 10 min cap\n  - Return value is still an upstream public CDN URL — no auth required, ready to render or share inline\n  - CLI flags and stdout JSON format are unchanged; no migration needed\n\n  【Verified】\n  - 1K square text-to-image: ~10s\n  - 2K landscape text-to-image: 62s\n  - 1K image-to-image edit: 117s ✅ (would have hit Cloudflare 524 on the old sync path)\n  - Error paths (missing token, invalid token, task failure, submission error) all surface clean messages and exit 1\n\n  【Deprecated】1.0.0 and 1.0.1 are marked deprecated on npm. All users should upgrade to 1.1.0+.\n\nv1.0.1 | 2026-05-07T16:08:45.243Z | user\n\n- Initial release of Picnow image generation skill.\n- Supports high-quality text-to-image and image-to-image generation, including editing, style transfer, and background change.\n- Offers 1K, 2K, and 4K resolution options; supports square, landscape, and portrait aspect ratios.\n- Handles both English and Chinese trigger phrases for flexible activation.\n- Provides clear error handling and user guidance for missing or invalid API keys, quota issues, and network errors.\n- Outputs image URLs with options to preview, download, or generate variations.\n\nArchive index:\n\nArchive v1.1.0: 5 files, 8449 bytes\n\nFiles: README.md (2665b), scripts/generate.js (7712b), skill-card.md (2019b), SKILL.md (5112b), _meta.json (125b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: picnow\ndescription: >\n  Generate high-quality images via Picnow (api.letmego.top). Activate when\n  the user wants to create, generate, draw, or design images — including\n  product photos, posters, banners, illustrations, social media visuals,\n  hero shots, covers, and thumbnails. Also handles image editing: style\n  transfer, background change, image-to-image (改图/配图/修图/图改图).\n  Supports 1K / 2K / 4K resolution, square / landscape / portrait aspect ratios.\n  Requires LETMEGO_API_KEY environment variable (your letmego 令牌/token).\nwhen_to_use:\n  # English triggers\n  - User asks to generate, draw, create, or make an image / picture / photo / visual / graphic / artwork / illustration\n  - User says \"image for\", \"picture for\", \"visual for\", \"banner for\", \"poster for\"\n  - User wants a product photo, hero shot, thumbnail, cover, poster, banner, or social media image\n  - User wants to edit, retouch, restyle, stylize, or transform an existing image\n  - User wants image-to-image, style transfer, background change, or outpainting\n  - User asks to \"add an image\", \"pair with image\", \"create a graphic\", or \"design a visual\"\n  - User wants to render, visualize, or illustrate something\n  # 中文触发词\n  - 用户说 生图 / 出图 / 做图 / 画图 / 画张 / 画一张 / 帮我画 / 帮我出图\n  - 用户说 配图 / 加图 / 插图 / 来张图 / 给我图 / 图片素材\n  - 用户说 改图 / 修图 / 图改图 / 换风格 / 风格化 / 重绘\n  - 用户说 生成图片 / 生成图像 / 创作图 / 设计图\n  - 用户说 产品图 / 主图 / 效果图 / 宣传图 / 海报 / 封面 / 头图 / 背景图\n  - 用户说 换背景 / 去背景 / 修改图片 / 图片编辑\nallowed-tools:\n  - Bash\n---\n\n# Picnow Image Generation Skill\n\nPicnow wraps the `api.letmego.top` GPT-Image-2 API. This skill handles\ntext-to-image and image-to-image (edit) generation.\n\nThe script uses the **async API** (`/v1/async/images/...`) — it submits the\njob, polls until completion, and prints the final URL. This avoids the 100s\nCloudflare edge timeout that 2K/4K renders used to hit. A single call may\ntake up to ~5 minutes for heavy renders; no extra flags needed.\n\n## 1. Environment check\n\nBefore generating, verify the token is set:\n\n```bash\nif [ -z \"$LETMEGO_API_KEY\" ]; then\n  echo \"❌ LETMEGO_API_KEY is not set.\"\n  echo \"Visit https://api.letmego.top to get your 令牌, then:\"\n  echo \"  export LETMEGO_API_KEY=your_token\"\n  exit 1\nfi\n```\n\n## 2. Gather parameters\n\nAsk the user if not already provided:\n\n| Parameter | Options | Default |\n|-----------|---------|---------|\n| `prompt` | any text description | *(required)* |\n| `quality` | `1k` · `2k` · `4k` | `1k` |\n| `aspect` | `square` · `landscape` · `portrait` | `square` |\n| `n` | 1 – 10 | `1` |\n| `ref` | local file path (optional) | *(none → text-to-image)* |\n\n**Quality guide:**\n- `1k` — up to 1536×1536, fast and cheap, great for previews and social media\n- `2k` — up to 2048×2048, suitable for e-commerce and print\n- `4k` — up to 3840×2160, landscape or portrait only (no 4k square)\n\n## 3. Locate and run the generation script\n\n```bash\n# Resolve skill directory (user-global → project-local)\nSKILL_DIR=\"$HOME/.claude/skills/picnow\"\n[ -d \"$SKILL_DIR\" ] || SKILL_DIR=\".claude/skills/picnow\"\n\nnode \"$SKILL_DIR/scripts/generate.js\" \\\n  --prompt \"PROMPT_HERE\" \\\n  --quality QUALITY \\\n  --aspect ASPECT \\\n  --n N\n  # add: --ref /path/to/image.jpg   for image-to-image\n```\n\nThe script outputs a single JSON line:\n```json\n{ \"urls\": [\"https://...cdn.../image.png\"] }\n```\n\n## 4. Present results\n\n- Display each URL as a clickable link or inline image.\n- For multiple images, list them with index labels (1/3, 2/3, …).\n- Offer to download, save to a project, or run another variation.\n\n## Error handling\n\n| Exit condition | Meaning | Action |\n|---|---|---|\n| `LETMEGO_API_KEY` missing | Token not set | Guide user to picnow settings |\n| HTTP 401 | Token invalid | Ask user to check or refresh token |\n| HTTP 402 / quota | Insufficient balance | Direct to letmego.top recharge |\n| HTTP 4xx other | Bad request | Show upstream error message |\n| Network error | Connection issue | Suggest retry |\n\n## Examples\n\n**Text-to-image:**\n```\nUser: 帮我画一张珠宝产品主图，白色背景，高清\n→ quality=2k, aspect=square\n→ node \"$SKILL_DIR/scripts/generate.js\" \\\n    --prompt \"jewelry product hero shot, white background, studio lighting, photorealistic\" \\\n    --quality 2k --aspect square --n 1\n```\n\n**Image-to-image:**\n```\nUser: 把这张图改成动漫风格 [uploads reference.jpg]\n→ quality=1k, ref=reference.jpg\n→ node \"$SKILL_DIR/scripts/generate.js\" \\\n    --prompt \"anime style illustration, vibrant colors, clean linework\" \\\n    --quality 1k --aspect square --n 1 --ref reference.jpg\n```\n\n**Landscape banner:**\n```\nUser: Generate a landscape banner for a coffee brand\n→ quality=1k, aspect=landscape, n=2\n→ node \"$SKILL_DIR/scripts/generate.js\" \\\n    --prompt \"coffee brand lifestyle banner, warm tones, morning light, artisan aesthetic\" \\\n    --quality 1k --aspect landscape --n 2\n```\n\nFile v1.1.0:README.md\n\n# picnow — Image Generation Skill\n\n> Generate images from any SKILL.md-compatible AI agent — text-to-image, image-to-image, 1K / 2K / 4K, powered by GPT-Image-2.\n\n**Install & docs:** https://picnow.letmego.top/skills\n\n---\n\n## Quick start\n\n### 1. Install\n\n```bash\n# skillpm — installs from npm\nnpx skillpm install @jxai/picnow\n\n# skills — installs from GitHub\nnpx skills install jeekchen/picnow-skill\n\n# SkillHub\nskillhub install @jxai/picnow\n\n# ClawHub\nclawdhub install @jxai/picnow\n\n# Manual\ngit clone https://github.com/jeekchen/picnow-skill\ncp -r picnow-skill/skills/picnow ~/.claude/skills/picnow\n```\n\n### 2. Get a token (令牌)\n\nSign up at **https://api.letmego.top** and copy your token, then:\n\n```bash\n# macOS / Linux — add to ~/.zshrc or ~/.bashrc to persist\nexport LETMEGO_API_KEY=your_token\n\n# Windows PowerShell (permanent)\n[System.Environment]::SetEnvironmentVariable(\"LETMEGO_API_KEY\",\"your_token\",\"User\")\n```\n\n### 3. Use it\n\nJust talk to your agent — the skill activates automatically:\n\n```\n> 帮我画一张珠宝产品主图，白色背景，高清\n> Generate a landscape banner for a coffee brand\n> 把这张图改成动漫风格  [attach reference.jpg]\n> Create a portrait poster for a music festival\n```\n\n---\n\n## Parameters\n\n| Parameter | Options | Default |\n|-----------|---------|---------|\n| `--prompt` | Any text | *(required)* |\n| `--quality` | `1k` · `2k` · `4k` | `1k` |\n| `--aspect` | `square` · `landscape` · `portrait` | `square` |\n| `--n` | 1 – 10 | `1` |\n| `--ref` | Local image path | *(none → text-to-image)* |\n\n**Quality guide**\n\n| Quality | Max resolution | Best for |\n|---------|---------------|----------|\n| `1k` | 1536 × 1536 | Previews, social media |\n| `2k` | 2048 × 2048 | E-commerce, print |\n| `4k` | 3840 × 2160 | Landscape / portrait only |\n\n---\n\n## Direct script usage\n\n```bash\n# Text-to-image\nLETMEGO_API_KEY=your_token node skills/picnow/scripts/generate.js \\\n  --prompt \"product photo, white background, studio lighting\" \\\n  --quality 2k --aspect square --n 1\n\n# Image-to-image (style transfer / edit)\nLETMEGO_API_KEY=your_token node skills/picnow/scripts/generate.js \\\n  --prompt \"anime style, vibrant colors\" \\\n  --quality 1k --aspect square --ref ./reference.jpg\n```\n\nOutput: a single JSON line — `{ \"urls\": [\"https://...\"] }`\n\n---\n\n## Supported clients\n\n- **Claude Code** (via `npx skillpm` or manual install)\n- **OpenAI Codex CLI**\n- **OpenClaw**\n- Any agent that supports the SKILL.md standard\n\n---\n\n## Published on\n\n- [SkillsMP](https://skillsmp.com)\n- [ClawHub](https://clawhub.ai)\n- [SkillHub](https://skillhub.club)\n\n---\n\n## License\n\nMIT © [jeekchen](https://github.com/jeekchen)\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn7e4fh6hp3br1krxnv0vy1w8982dpjb\",\n  \"slug\": \"picnow\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1779980640606\n}\n\nFile v1.1.0:skill-card.md\n\n## Description:\n\nGenerates and edits images through Picnow's api.letmego.top service with 1K, 2K, and 4K quality options and square, landscape, or portrait aspect ratios.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[jeekchen](https://clawhub.ai/user/jeekchen)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to ask an agent to create product images, banners, posters, social visuals, thumbnails, and image-to-image edits through the Picnow API.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Reference-image generation can upload any readable local file passed through --ref to a third-party API.\n\nMitigation: Use only prompts and reference images that are appropriate to send to api.letmego.top, avoid arbitrary local paths, and confirm reference files before execution.\n\nRisk: The skill requires an API token for the third-party Picnow service.\n\nMitigation: Store LETMEGO_API_KEY in a secret manager or temporary environment variable and avoid exposing it in command history, logs, or shared files.\n\n## Reference(s):\n\n- [Picnow install and usage documentation](https://picnow.letmego.top/skills)\n- [Picnow API service](https://api.letmego.top)\n- [ClawHub release page](https://clawhub.ai/jeekchen/skills/picnow)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with shell commands and JSON URL output from the generation script]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [The generation script prints a single JSON object containing generated image URLs.]\n\n## Skill Version(s):\n\n1.1.0 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.1: 4 files, 6046 bytes\n\nFiles: scripts/generate.js (5712b), skill-card.md (1761b), SKILL.md (4819b), _meta.json (125b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: picnow\ndescription: >\n  Generate high-quality images via Picnow (api.letmego.top). Activate when\n  the user wants to create, generate, draw, or design images — including\n  product photos, posters, banners, illustrations, social media visuals,\n  hero shots, covers, and thumbnails. Also handles image editing: style\n  transfer, background change, image-to-image (改图/配图/修图/图改图).\n  Supports 1K / 2K / 4K resolution, square / landscape / portrait aspect ratios.\n  Requires LETMEGO_API_KEY environment variable (your letmego 令牌/token).\nwhen_to_use:\n  # English triggers\n  - User asks to generate, draw, create, or make an image / picture / photo / visual / graphic / artwork / illustration\n  - User says \"image for\", \"picture for\", \"visual for\", \"banner for\", \"poster for\"\n  - User wants a product photo, hero shot, thumbnail, cover, poster, banner, or social media image\n  - User wants to edit, retouch, restyle, stylize, or transform an existing image\n  - User wants image-to-image, style transfer, background change, or outpainting\n  - User asks to \"add an image\", \"pair with image\", \"create a graphic\", or \"design a visual\"\n  - User wants to render, visualize, or illustrate something\n  # 中文触发词\n  - 用户说 生图 / 出图 / 做图 / 画图 / 画张 / 画一张 / 帮我画 / 帮我出图\n  - 用户说 配图 / 加图 / 插图 / 来张图 / 给我图 / 图片素材\n  - 用户说 改图 / 修图 / 图改图 / 换风格 / 风格化 / 重绘\n  - 用户说 生成图片 / 生成图像 / 创作图 / 设计图\n  - 用户说 产品图 / 主图 / 效果图 / 宣传图 / 海报 / 封面 / 头图 / 背景图\n  - 用户说 换背景 / 去背景 / 修改图片 / 图片编辑\nallowed-tools:\n  - Bash\n---\n\n# Picnow Image Generation Skill\n\nPicnow wraps the `api.letmego.top` GPT-Image-2 API. This skill handles\ntext-to-image and image-to-image (edit) generation.\n\n## 1. Environment check\n\nBefore generating, verify the token is set:\n\n```bash\nif [ -z \"$LETMEGO_API_KEY\" ]; then\n  echo \"❌ LETMEGO_API_KEY is not set.\"\n  echo \"Visit https://api.letmego.top to get your 令牌, then:\"\n  echo \"  export LETMEGO_API_KEY=your_token\"\n  exit 1\nfi\n```\n\n## 2. Gather parameters\n\nAsk the user if not already provided:\n\n| Parameter | Options | Default |\n|-----------|---------|---------|\n| `prompt` | any text description | *(required)* |\n| `quality` | `1k` · `2k` · `4k` | `1k` |\n| `aspect` | `square` · `landscape` · `portrait` | `square` |\n| `n` | 1 – 10 | `1` |\n| `ref` | local file path (optional) | *(none → text-to-image)* |\n\n**Quality guide:**\n- `1k` — up to 1536×1536, fast and cheap, great for previews and social media\n- `2k` — up to 2048×2048, suitable for e-commerce and print\n- `4k` — up to 3840×2160, landscape or portrait only (no 4k square)\n\n## 3. Locate and run the generation script\n\n```bash\n# Resolve skill directory (user-global → project-local)\nSKILL_DIR=\"$HOME/.claude/skills/picnow\"\n[ -d \"$SKILL_DIR\" ] || SKILL_DIR=\".claude/skills/picnow\"\n\nnode \"$SKILL_DIR/scripts/generate.js\" \\\n  --prompt \"PROMPT_HERE\" \\\n  --quality QUALITY \\\n  --aspect ASPECT \\\n  --n N\n  # add: --ref /path/to/image.jpg   for image-to-image\n```\n\nThe script outputs a single JSON line:\n```json\n{ \"urls\": [\"https://...cdn.../image.png\"] }\n```\n\n## 4. Present results\n\n- Display each URL as a clickable link or inline image.\n- For multiple images, list them with index labels (1/3, 2/3, …).\n- Offer to download, save to a project, or run another variation.\n\n## Error handling\n\n| Exit condition | Meaning | Action |\n|---|---|---|\n| `LETMEGO_API_KEY` missing | Token not set | Guide user to picnow settings |\n| HTTP 401 | Token invalid | Ask user to check or refresh token |\n| HTTP 402 / quota | Insufficient balance | Direct to letmego.top recharge |\n| HTTP 4xx other | Bad request | Show upstream error message |\n| Network error | Connection issue | Suggest retry |\n\n## Examples\n\n**Text-to-image:**\n```\nUser: 帮我画一张珠宝产品主图，白色背景，高清\n→ quality=2k, aspect=square\n→ node \"$SKILL_DIR/scripts/generate.js\" \\\n    --prompt \"jewelry product hero shot, white background, studio lighting, photorealistic\" \\\n    --quality 2k --aspect square --n 1\n```\n\n**Image-to-image:**\n```\nUser: 把这张图改成动漫风格 [uploads reference.jpg]\n→ quality=1k, ref=reference.jpg\n→ node \"$SKILL_DIR/scripts/generate.js\" \\\n    --prompt \"anime style illustration, vibrant colors, clean linework\" \\\n    --quality 1k --aspect square --n 1 --ref reference.jpg\n```\n\n**Landscape banner:**\n```\nUser: Generate a landscape banner for a coffee brand\n→ quality=1k, aspect=landscape, n=2\n→ node \"$SKILL_DIR/scripts/generate.js\" \\\n    --prompt \"coffee brand lifestyle banner, warm tones, morning light, artisan aesthetic\" \\\n    --quality 1k --aspect landscape --n 2\n```\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7e4fh6hp3br1krxnv0vy1w8982dpjb\",\n  \"slug\": \"picnow\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1778170125243\n}\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nGenerates high-quality text-to-image and image-to-image outputs through Picnow's api.letmego.top image API. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[jeekchen](https://clawhub.ai/user/jeekchen) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and end users use this skill to generate product photos, posters, banners, illustrations, thumbnails, and edited image variants from text prompts or reference images. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Prompts and referenced local image files are sent to api.letmego.top using the user's LETMEGO_API_KEY. <br>\nMitigation: Avoid sensitive photos, confidential designs, or regulated data unless the user explicitly intends to upload them, and confirm ambiguous image requests before generation. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/jeekchen/picnow) <br>\n- [Picnow API](https://api.letmego.top) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown guidance with shell commands and JSON image URL output] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires LETMEGO_API_KEY and Node 18 or newer; generated image URLs are returned by the Picnow API.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\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. <br>","readmeExcerpt":"Skill: Picnow — Image Generation Owner: jeekchen Summary: Generate high-quality images via Picnow (api.letmego.top). Activate when the user wants to create, generate, draw, or design images — including product photo... Tags: async:1.1.0, claude-code:1.1.0, claude-skill:1.0.1, gpt-image-2:1.1.0, hermess-agent:1.1.0, image-generation:1.1.0, image-to-image:1.1.0, latest:1.1.0, openclaw:1.1.0, picnow:1.1.0, text-to-image","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"if [ -z \"$LETMEGO_API_KEY\" ]; then\n  echo \"❌ LETMEGO_API_KEY is not set.\"\n  echo \"Visit https://api.letmego.top to get your 令牌, then:\"\n  echo \"  export LETMEGO_API_KEY=your_token\"\n  exit 1\nfi"},{"language":"bash","snippet":"# Resolve skill directory (user-global → project-local)\nSKILL_DIR=\"$HOME/.claude/skills/picnow\"\n[ -d \"$SKILL_DIR\" ] || SKILL_DIR=\".claude/skills/picnow\"\n\nnode \"$SKILL_DIR/scripts/generate.js\" \\\n  --prompt \"PROMPT_HERE\" \\\n  --quality QUALITY \\\n  --aspect ASPECT \\\n  --n N\n  # add: --ref /path/to/image.jpg   for image-to-image"},{"language":"json","snippet":"{ \"urls\": [\"https://...cdn.../image.png\"] }"},{"language":"text","snippet":"User: 帮我画一张珠宝产品主图，白色背景，高清\n→ quality=2k, aspect=square\n→ node \"$SKILL_DIR/scripts/generate.js\" \\\n    --prompt \"jewelry product hero shot, white background, studio lighting, photorealistic\" \\\n    --quality 2k --aspect square --n 1"},{"language":"text","snippet":"User: 把这张图改成动漫风格 [uploads reference.jpg]\n→ quality=1k, ref=reference.jpg\n→ node \"$SKILL_DIR/scripts/generate.js\" \\\n    --prompt \"anime style illustration, vibrant colors, clean linework\" \\\n    --quality 1k --aspect square --n 1 --ref reference.jpg"},{"language":"text","snippet":"User: Generate a landscape banner for a coffee brand\n→ quality=1k, aspect=landscape, n=2\n→ node \"$SKILL_DIR/scripts/generate.js\" \\\n    --prompt \"coffee brand lifestyle banner, warm tones, morning light, artisan aesthetic\" \\\n    --quality 1k --aspect landscape --n 2"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: picnow\ndescription: >\n  Generate high-quality images via Picnow (api.letmego.top). Activate when\n  the user wants to create, generate, draw, or design images — including\n  product photos, posters, banners, illustrations, social media visuals,\n  hero shots, covers, and thumbnails. Also handles image editing: style\n  transfer, background change, image-to-image (改图/配图/修图/图改图).\n  Supports 1K / 2K / 4K resolution, square / landscape / portrait aspect ratios.\n  Requires LETMEGO_API_KEY environment variable (your letmego 令牌/token).\nwhen_to_use:\n  # English triggers\n  - User asks to generate, draw, create, or make an image / picture / photo / visual / graphic / artwork / illustration\n  - User says \"image for\", \"picture for\", \"visual for\", \"banner for\", \"poster for\"\n  - User wants a product photo, hero shot, thumbnail, cover, poster, banner, or social media image\n  - User wants to edit, retouch, restyle, stylize, or transform an existing image\n  - User wants image-to-image, style transfer, background change, or outpainting\n  - User asks to \"add an image\", \"pair with image\", \"create a graphic\", or \"design a visual\"\n  - User wants to render, visualize, or illustrate something\n  # 中文触发词\n  - 用户说 生图 / 出图 / 做图 / 画图 / 画张 / 画一张 / 帮我画 / 帮我出图\n  - 用户说 配图 / 加图 / 插图 / 来张图 / 给我图 / 图片素材\n  - 用户说 改图 / 修图 / 图改图 / 换风格 / 风格化 / 重绘\n  - 用户说 生成图片 / 生成图像 / 创作图 / 设计图\n  - 用户说 产品图 / 主图 / 效果图 / 宣传图 / 海报 / 封面 / 头图 / 背景图\n  - 用户说 换背景 / 去背景 / 修改图片 / 图片编辑\nallowed-tools:\n  - Bash\n---\n\n# Picnow Image Generation Skill\n\nPicnow wraps the `api.letmego.top` GPT-Image-2 API. This skill handles\ntext-to-image and image-to-image (edit) generation.\n\nThe script uses the **async API** (`/v1/async/images/...`) — it submits the\njob, polls until completion, and prints the final URL. This avoids the 100s\nCloudflare edge timeout that 2K/4K renders used to hit. A single call may\ntake up to ~5 minutes for heavy renders; no extra flags needed.\n\n## 1. Environment check\n\nBefore generating, verify the token is set:\n\n```bash\nif [ -z \"$LETMEGO_API_KEY\" ]; then\n  echo \"❌ LETMEGO_API_KEY is not set.\"\n  echo \"Visit https://api.letmego.top to get your 令牌, then:\"\n  echo \"  export LETMEGO_API_KEY=your_token\"\n  exit 1\nfi\n```\n\n## 2. Gather parameters\n\nAsk the user if not already provided:\n\n| Parameter | Options | Default |\n|-----------|---------|---------|\n| `prompt` | any text description | *(required)* |\n| `quality` | `1k` · `2k` · `4k` | `1k` |\n| `aspect` | `square` · `landscape` · `portrait` | `square` |\n| `n` | 1 – 10 | `1` |\n| `ref` | local file path (optional) | *(none → text-to-image)* |\n\n**Quality guide:**\n- `1k` — up to 1536×1536, fast and cheap, great for previews and social media\n- `2k` — up to 2048×2048, suitable for e-commerce and print\n- `4k` — up to 3840×2160, landscape or portrait only (no 4k square)\n\n## 3. Locate and run the generation script\n\n```bash\n# Resolve skill directory (user-global → project-local)\nSKILL_DIR=\"$HOME/.claude/skills/picnow\"\n[ -d \"$SKILL_DIR\" ] || SKILL_DIR=\".claude/skills/p"},{"path":"README.md","content":"# picnow — Image Generation Skill\n\n> Generate images from any SKILL.md-compatible AI agent — text-to-image, image-to-image, 1K / 2K / 4K, powered by GPT-Image-2.\n\n**Install & docs:** https://picnow.letmego.top/skills\n\n---\n\n## Quick start\n\n### 1. Install\n\n```bash\n# skillpm — installs from npm\nnpx skillpm install @jxai/picnow\n\n# skills — installs from GitHub\nnpx skills install jeekchen/picnow-skill\n\n# SkillHub\nskillhub install @jxai/picnow\n\n# ClawHub\nclawdhub install @jxai/picnow\n\n# Manual\ngit clone https://github.com/jeekchen/picnow-skill\ncp -r picnow-skill/skills/picnow ~/.claude/skills/picnow\n```\n\n### 2. Get a token (令牌)\n\nSign up at **https://api.letmego.top** and copy your token, then:\n\n```bash\n# macOS / Linux — add to ~/.zshrc or ~/.bashrc to persist\nexport LETMEGO_API_KEY=your_token\n\n# Windows PowerShell (permanent)\n[System.Environment]::SetEnvironmentVariable(\"LETMEGO_API_KEY\",\"your_token\",\"User\")\n```\n\n### 3. Use it\n\nJust talk to your agent — the skill activates automatically:\n\n```\n> 帮我画一张珠宝产品主图，白色背景，高清\n> Generate a landscape banner for a coffee brand\n> 把这张图改成动漫风格  [attach reference.jpg]\n> Create a portrait poster for a music festival\n```\n\n---\n\n## Parameters\n\n| Parameter | Options | Default |\n|-----------|---------|---------|\n| `--prompt` | Any text | *(required)* |\n| `--quality` | `1k` · `2k` · `4k` | `1k` |\n| `--aspect` | `square` · `landscape` · `portrait` | `square` |\n| `--n` | 1 – 10 | `1` |\n| `--ref` | Local image path | *(none → text-to-image)* |\n\n**Quality guide**\n\n| Quality | Max resolution | Best for |\n|---------|---------------|----------|\n| `1k` | 1536 × 1536 | Previews, social media |\n| `2k` | 2048 × 2048 | E-commerce, print |\n| `4k` | 3840 × 2160 | Landscape / portrait only |\n\n---\n\n## Direct script usage\n\n```bash\n# Text-to-image\nLETMEGO_API_KEY=your_token node skills/picnow/scripts/generate.js \\\n  --prompt \"product photo, white background, studio lighting\" \\\n  --quality 2k --aspect square --n 1\n\n# Image-to-image (style transfer / edit)\nLETMEGO_API_KEY=your_token node skills/picnow/scripts/generate.js \\\n  --prompt \"anime style, vibrant colors\" \\\n  --quality 1k --aspect square --ref ./reference.jpg\n```\n\nOutput: a single JSON line — `{ \"urls\": [\"https://...\"] }`\n\n---\n\n## Supported clients\n\n- **Claude Code** (via `npx skillpm` or manual install)\n- **OpenAI Codex CLI**\n- **OpenClaw**\n- Any agent that supports the SKILL.md standard\n\n---\n\n## Published on\n\n- [SkillsMP](https://skillsmp.com)\n- [ClawHub](https://clawhub.ai)\n- [SkillHub](https://skillhub.club)\n\n---\n\n## License\n\nMIT © [jeekchen](https://github.com/jeekchen)"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7e4fh6hp3br1krxnv0vy1w8982dpjb\",\n  \"slug\": \"picnow\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1779980640606\n}"},{"path":"skill-card.md","content":"## Description:\n\nGenerates and edits images through Picnow's api.letmego.top service with 1K, 2K, and 4K quality options and square, landscape, or portrait aspect ratios.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[jeekchen](https://clawhub.ai/user/jeekchen)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to ask an agent to create product images, banners, posters, social visuals, thumbnails, and image-to-image edits through the Picnow API.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Reference-image generation can upload any readable local file passed through --ref to a third-party API.\n\nMitigation: Use only prompts and reference images that are appropriate to send to api.letmego.top, avoid arbitrary local paths, and confirm reference files before execution.\n\nRisk: The skill requires an API token for the third-party Picnow service.\n\nMitigation: Store LETMEGO_API_KEY in a secret manager or temporary environment variable and avoid exposing it in command history, logs, or shared files.\n\n## Reference(s):\n\n- [Picnow install and usage documentation](https://picnow.letmego.top/skills)\n- [Picnow API service](https://api.letmego.top)\n- [ClawHub release page](https://clawhub.ai/jeekchen/skills/picnow)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with shell commands and JSON URL output from the generation script]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [The generation script prints a single JSON object containing generated image URLs.]\n\n## Skill Version(s):\n\n1.1.0 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Generate high-quality images via Picnow (api.letmego.top). Activate when the user wants to create, generate, draw, or design images — including product photo... Skill: Picnow — Image Generation Owner: jeekchen Summary: Generate high-quality images via Picnow (api.letmego.top). Activate when the user wants to create, generate, draw, or design images — including product photo... Tags: async:1.1.0, claude-code:1.1.0, claude-skill:1.0.1, gpt-image-2:1.1.0, hermess-agent:1.1.0, image-generation:1.1.0, image-to-image:1.1.0, latest:1.1.0, openclaw:1.1.0, picnow:1.1.0, text-to-image","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1411,"uniquenessScore":47,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-12T00:51:22.891Z","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":"2026-10-12T00:51:22.891Z","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":"2026-10-13T03:11:06.046Z","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"}]}}}