[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A5AFPXYS3QTYRFJNTF6ETX":3,"skill-same:01M7A5AFPXYS3QTYRFJNTF6ETX":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7A5AFPXYS3QTYRFJNTF6ETX","Replicate Automation",null,"Automate Replicate AI model operations -- run predictions, upload files, inspect model schemas, list versions, and manage prediction history via the Composio MCP integration.","siuserxiaowei\u002Fxiaowei-ai-tools","siuserxiaowei","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F226641659?v=4","01M7A3SYZKS0MVRZZJQC10XSYM","siuser小伟","01M7A3SZ0735VJJQ0479SNF44J",1,"MIT","https:\u002F\u002Fgithub.com\u002Fsiuserxiaowei\u002Fxiaowei-ai-tools\u002Fblob\u002Fmain\u002Fprojects\u002F技能集合与工具目录\u002Fawesome-codex-skills\u002Fcomposio-skills\u002Freplicate-automation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: Replicate Automation\ndescription: \"Automate Replicate AI model operations -- run predictions, upload files, inspect model schemas, list versions, and manage prediction history via the Composio MCP integration.\"\nrequires:\n  mcp:\n    - rube\n---\n\n# Replicate Automation\n\nAutomate your Replicate AI model workflows -- run predictions on any public model (image generation, LLMs, audio, video), upload input files, inspect model schemas and documentation, list model versions, and track prediction history.\n\n**Toolkit docs:** [composio.dev\u002Ftoolkits\u002Freplicate](https:\u002F\u002Fcomposio.dev\u002Ftoolkits\u002Freplicate)\n\n---\n\n## Setup\n\n1. Add the Composio MCP server to your client: `https:\u002F\u002Frube.app\u002Fmcp`\n2. Connect your Replicate account when prompted (API token authentication)\n3. Start using the workflows below\n\n---\n\n## Core Workflows\n\n### 1. Get Model Details and Schema\n\nUse `REPLICATE_MODELS_GET` to inspect a model's input\u002Foutput schema before running predictions.\n\n```\nTool: REPLICATE_MODELS_GET\nInputs:\n  - model_owner: string (required) -- e.g., \"meta\", \"black-forest-labs\", \"stability-ai\"\n  - model_name: string (required) -- e.g., \"meta-llama-3-8b-instruct\", \"flux-1.1-pro\"\n```\n\n**Important:** Each model has unique input keys and types. Always check the `openapi_schema` from this response before constructing prediction inputs.\n\n### 2. Run a Prediction\n\nUse `REPLICATE_MODELS_PREDICTIONS_CREATE` to run inference on any model with optional synchronous waiting and webhooks.\n\n```\nTool: REPLICATE_MODELS_PREDICTIONS_CREATE\nInputs:\n  - model_owner: string (required) -- e.g., \"meta\", \"black-forest-labs\"\n  - model_name: string (required) -- e.g., \"flux-1.1-pro\", \"sdxl\"\n  - input: object (required) -- model-specific inputs, e.g., { \"prompt\": \"A sunset over mountains\" }\n  - wait_for: integer (1-60 seconds, optional) -- synchronous wait for completion\n  - cancel_after: string (optional) -- max execution time, e.g., \"300s\", \"5m\"\n  - webhook: string (optional) -- HTTPS URL for async completion notifications\n  - webhook_events_filter: array (optional) -- [\"start\", \"output\", \"logs\", \"completed\"]\n```\n\n**Sync vs Async:** Use `wait_for` (1-60s) for fast models. For long-running jobs, omit it and use webhooks or poll via `REPLICATE_PREDICTIONS_LIST`.\n\n### 3. Upload Files for Model Input\n\nUse `REPLICATE_CREATE_FILE` to upload images, documents, or other binary inputs that models need.\n\n```\nTool: REPLICATE_CREATE_FILE\nInputs:\n  - content: string (required) -- base64-encoded file content\n  - filename: string (required) -- e.g., \"input.png\", \"audio.wav\" (max 255 bytes UTF-8)\n  - content_type: string (default \"application\u002Foctet-stream\") -- MIME type\n  - metadata: object (optional) -- custom JSON metadata\n```\n\n### 4. Read Model Documentation\n\nUse `REPLICATE_MODELS_README_GET` to access a model's README in Markdown format for detailed usage instructions.\n\n```\nTool: REPLICATE_MODELS_README_GET\nInputs:\n  - model_owner: string (required)\n  - model_name: string (required)\n```\n\n### 5. List Model Versions\n\nUse `REPLICATE_MODELS_VERSIONS_LIST` to see all available versions of a model, sorted newest first.\n\n```\nTool: REPLICATE_MODELS_VERSIONS_LIST\nInputs:\n  - model_owner: string (required)\n  - model_name: string (required)\n```\n\n### 6. Track Prediction History and Files\n\nUse `REPLICATE_PREDICTIONS_LIST` to retrieve prediction history, and `REPLICATE_FILES_GET`\u002F`REPLICATE_FILES_LIST` to manage uploaded files.\n\n```\nTool: REPLICATE_PREDICTIONS_LIST\n  - Lists all predictions for the authenticated user with pagination\n\nTool: REPLICATE_FILES_LIST\n  - Lists uploaded files, most recent first\n\nTool: REPLICATE_FILES_GET\n  - Get details of a specific file by ID\n```\n\n---\n\n## Known Pitfalls\n\n| Pitfall | Detail |\n|---------|--------|\n| Model-specific input keys | Each model has unique input keys and types. Using the wrong key causes validation errors. Always call `REPLICATE_MODELS_GET` first to check the `openapi_schema`. |\n| File upload encoding | `REPLICATE_CREATE_FILE` requires base64-encoded content. Binary files treated as text (UTF-8) will fail with decode errors. |\n| Public vs deployment paths | Public models must be run via `REPLICATE_MODELS_PREDICTIONS_CREATE`. Using deployment-oriented paths causes HTTP 404 failures. |\n| Sync wait limits | `wait_for` supports 1-60 seconds only. Long-running jobs need async handling via webhooks or polling `REPLICATE_PREDICTIONS_LIST`. |\n| Image model constraints | Image models like flux-1.1-pro have specific constraints (e.g., max width\u002Fheight 1440px, valid aspect ratios). Check the model schema first. |\n| Stale file references | Heavy usage creates many uploads. Routinely check `REPLICATE_FILES_LIST` to avoid using stale `file_id` references. |\n\n---\n\n## Quick Reference\n\n| Tool Slug | Description |\n|-----------|-------------|\n| `REPLICATE_MODELS_GET` | Get model details, schema, and metadata |\n| `REPLICATE_MODELS_PREDICTIONS_CREATE` | Run a prediction on a model |\n| `REPLICATE_CREATE_FILE` | Upload a file for model input |\n| `REPLICATE_MODELS_README_GET` | Get model README documentation |\n| `REPLICATE_MODELS_VERSIONS_LIST` | List all versions of a model |\n| `REPLICATE_PREDICTIONS_LIST` | List prediction history with pagination |\n| `REPLICATE_FILES_LIST` | List uploaded files |\n| `REPLICATE_FILES_GET` | Get file details by ID |\n\n---\n\n*Powered by [Composio](https:\u002F\u002Fcomposio.dev)*\n","# Replicate Automation\n\nAutomate your Replicate AI model workflows -- run predictions on any public model (image generation, LLMs, audio, video), upload input files, inspect model schemas and documentation, list model versions, and track prediction history.\n\n**Toolkit docs:** [composio.dev\u002Ftoolkits\u002Freplicate](https:\u002F\u002Fcomposio.dev\u002Ftoolkits\u002Freplicate)\n\n---\n\n## Setup\n\n1. Add the Composio MCP server to your client: `https:\u002F\u002Frube.app\u002Fmcp`\n2. Connect your Replicate account when prompted (API token authentication)\n3. Start using the workflows below\n\n---\n\n## Core Workflows\n\n### 1. Get Model Details and Schema\n\nUse `REPLICATE_MODELS_GET` to inspect a model's input\u002Foutput schema before running predictions.\n\n```\nTool: REPLICATE_MODELS_GET\nInputs:\n  - model_owner: string (required) -- e.g., \"meta\", \"black-forest-labs\", \"stability-ai\"\n  - model_name: string (required) -- e.g., \"meta-llama-3-8b-instruct\", \"flux-1.1-pro\"\n```\n\n**Important:** Each model has unique input keys and types. Always check the `openapi_schema` from this response before constructing prediction inputs.\n\n### 2. Run a Prediction\n\nUse `REPLICATE_MODELS_PREDICTIONS_CREATE` to run inference on any model with optional synchronous waiting and webhooks.\n\n```\nTool: REPLICATE_MODELS_PREDICTIONS_CREATE\nInputs:\n  - model_owner: string (required) -- e.g., \"meta\", \"black-forest-labs\"\n  - model_name: string (required) -- e.g., \"flux-1.1-pro\", \"sdxl\"\n  - input: object (required) -- model-specific inputs, e.g., { \"prompt\": \"A sunset over mountains\" }\n  - wait_for: integer (1-60 seconds, optional) -- synchronous wait for completion\n  - cancel_after: string (optional) -- max execution time, e.g., \"300s\", \"5m\"\n  - webhook: string (optional) -- HTTPS URL for async completion notifications\n  - webhook_events_filter: array (optional) -- [\"start\", \"output\", \"logs\", \"completed\"]\n```\n\n**Sync vs Async:** Use `wait_for` (1-60s) for fast models. For long-running jobs, omit it and use webhooks or poll via `REPLICATE_PREDICTIONS_LIST`.\n\n### 3. Upload Files for Model Input\n\nUse `REPLICATE_CREATE_FILE` to upload images, documents, or other binary inputs that models need.\n\n```\nTool: REPLICATE_CREATE_FILE\nInputs:\n  - content: string (required) -- base64-encoded file content\n  - filename: string (required) -- e.g., \"input.png\", \"audio.wav\" (max 255 bytes UTF-8)\n  - content_type: string (default \"application\u002Foctet-stream\") -- MIME type\n  - metadata: object (optional) -- custom JSON metadata\n```\n\n### 4. Read Model Documentation\n\nUse `REPLICATE_MODELS_README_GET` to access a model's README in Markdown format for detailed usage instructions.\n\n```\nTool: REPLICATE_MODELS_README_GET\nInputs:\n  - model_owner: string (required)\n  - model_name: string (required)\n```\n\n### 5. List Model Versions\n\nUse `REPLICATE_MODELS_VERSIONS_LIST` to see all available versions of a model, sorted newest first.\n\n```\nTool: REPLICATE_MODELS_VERSIONS_LIST\nInputs:\n  - model_owner: string (required)\n  - model_name: string (required)\n```\n\n### 6. Track Prediction History and Files\n\nUse `REPLICATE_PREDICTIONS_LIST` to retrieve prediction history, and `REPLICATE_FILES_GET`\u002F`REPLICATE_FILES_LIST` to manage uploaded files.\n\n```\nTool: REPLICATE_PREDICTIONS_LIST\n  - Lists all predictions for the authenticated user with pagination\n\nTool: REPLICATE_FILES_LIST\n  - Lists uploaded files, most recent first\n\nTool: REPLICATE_FILES_GET\n  - Get details of a specific file by ID\n```\n\n---\n\n## Known Pitfalls\n\n| Pitfall | Detail |\n|---------|--------|\n| Model-specific input keys | Each model has unique input keys and types. Using the wrong key causes validation errors. Always call `REPLICATE_MODELS_GET` first to check the `openapi_schema`. |\n| File upload encoding | `REPLICATE_CREATE_FILE` requires base64-encoded content. Binary files treated as text (UTF-8) will fail with decode errors. |\n| Public vs deployment paths | Public models must be run via `REPLICATE_MODELS_PREDICTIONS_CREATE`. Using deployment-oriented paths causes HTTP 404 failures. |\n| Sync wait limits | `wait_for` supports 1-60 seconds only. Long-running jobs need async handling via webhooks or polling `REPLICATE_PREDICTIONS_LIST`. |\n| Image model constraints | Image models like flux-1.1-pro have specific constraints (e.g., max width\u002Fheight 1440px, valid aspect ratios). Check the model schema first. |\n| Stale file references | Heavy usage creates many uploads. Routinely check `REPLICATE_FILES_LIST` to avoid using stale `file_id` references. |\n\n---\n\n## Quick Reference\n\n| Tool Slug | Description |\n|-----------|-------------|\n| `REPLICATE_MODELS_GET` | Get model details, schema, and metadata |\n| `REPLICATE_MODELS_PREDICTIONS_CREATE` | Run a prediction on a model |\n| `REPLICATE_CREATE_FILE` | Upload a file for model input |\n| `REPLICATE_MODELS_README_GET` | Get model README documentation |\n| `REPLICATE_MODELS_VERSIONS_LIST` | List all versions of a model |\n| `REPLICATE_PREDICTIONS_LIST` | List prediction history with pagination |\n| `REPLICATE_FILES_LIST` | List uploaded files |\n| `REPLICATE_FILES_GET` | Get file details by ID |\n\n---\n\n*Powered by [Composio](https:\u002F\u002Fcomposio.dev)*\n",{"name":5,"requires":24,"description":7},{"mcp":25},[26],"rube","main","ebb257363024c428d3c797cb705194b35d00cb0f","projects\u002F技能集合与工具目录\u002Fawesome-codex-skills\u002Fcomposio-skills\u002Freplicate-automation",0,"https:\u002F\u002Fgithub.com\u002Fsiuserxiaowei\u002Fxiaowei-ai-tools","https:\u002F\u002Fgithub.com\u002Fsiuserxiaowei","2026-11-03 21:39:44",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add siuserxiaowei\u002Fxiaowei-ai-tools --skill \"Replicate Automation\"",{"tool":40,"command":41},"bunx","bunx skills add siuserxiaowei\u002Fxiaowei-ai-tools --skill \"Replicate Automation\"",{"tool":43,"command":44},"pnpm","pnpm dlx skills add siuserxiaowei\u002Fxiaowei-ai-tools --skill \"Replicate Automation\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsiuserxiaowei\u002Fxiaowei-ai-tools\u002Fblob\u002Fmain\u002Fprojects\u002F技能集合与工具目录\u002Fawesome-codex-skills\u002Fcomposio-skills\u002Freplicate-automation\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7A66TQCYTAPVGB01H6593P0","x-article-draft-uploader","把本地 Markdown 转为经核验的 X Articles 新草稿。适用于需要保留首图封面、正文图片相对位置，并在独立 Playwright 会话中复用用户已授权 Chrome 登录态的任务；不负责公开发布。","https:\u002F\u002Fgithub.com\u002Fsiuserxiaowei\u002Fxiaowei-ai-tools\u002Fblob\u002Fmain\u002Fskills\u002Fx-article-draft-uploader\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7A66R643K97EQHY5AFBBVQ6","wecom-operations","通过用户已配置的官方 wecom-cli 管理企业微信文档、智能文档、待办、会议和日程。适合创建或查询这些云端对象、把本地 Markdown 转为智能文档，以及在明确确认后更新或取消对象；不发送消息、不控制桌面客户端。","https:\u002F\u002Fgithub.com\u002Fsiuserxiaowei\u002Fxiaowei-ai-tools\u002Fblob\u002Fmain\u002Fskills\u002Fwecom-operations\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7A66M3AXR54FQB7B4TX5VN9","wecom-local-vault","Inspect authorized local WeCom databases on macOS, create private plaintext snapshots, and query or export contacts, conversations, and messages without modifying the source account store. Use when the user asks to parse 企业微信\u002FWeCom local data, recover a private database snapshot, inspect local contacts or sessions, search chat history, or export a bounded conversation.","https:\u002F\u002Fgithub.com\u002Fsiuserxiaowei\u002Fxiaowei-ai-tools\u002Fblob\u002Fmain\u002Fskills\u002Fwecom-local-vault\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7A6649YFS2SQ8SKFSTBRN2Z","wechat-reading","Read and analyze WeRead\u002F微信读书 search results, book metadata, bookshelf entries, progress, notes, highlights, public reviews, recommendations, and reading statistics through the official read-only Agent Gateway. Use for WeRead account questions or exports; do not imply that the current Gateway can add, remove, upload, rate, like, or edit content.","https:\u002F\u002Fgithub.com\u002Fsiuserxiaowei\u002Fxiaowei-ai-tools\u002Fblob\u002Fmain\u002Fskills\u002Fwechat-reading\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7A65QZNA4FBYV32WH9S97QG","wechat-mp-batch-exporter","Build a bounded, private archive from known WeChat Official Account article URLs or an owner-authorized account-history export, with explicit reconciliation of article, publish-group, and platform-marked-original counts. Use for batch body capture, history normalization, or enhanced metrics\u002Fcomments workflows. Do not use for a one-page summary or to automate the WeChat client.","https:\u002F\u002Fgithub.com\u002Fsiuserxiaowei\u002Fxiaowei-ai-tools\u002Fblob\u002Fmain\u002Fskills\u002Fwechat-mp-batch-exporter\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7A65NP84R1JFFZEPVZT065P","wechat-local-vault","在 macOS 本机建立并查询私有微信数据快照。适用于盘点数据库、离线校验已有密钥候选、创建全量或增量明文快照、查会话与联系人、按时间检索消息、导出指定聊天、查看朋友圈或收藏，以及准备群聊摘要素材。所有查询只读，默认隐藏内部账号标识，不操控微信界面，也不发送任何内容。","https:\u002F\u002Fgithub.com\u002Fsiuserxiaowei\u002Fxiaowei-ai-tools\u002Fblob\u002Fmain\u002Fskills\u002Fwechat-local-vault\u002FSKILL.md",[],[]]