[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75BCGPGNSCYC3C43GPRCE49":3,"skill-same:01M75BCGPGNSCYC3C43GPRCE49":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M75BCGPGNSCYC3C43GPRCE49","agent-tools",null,"Run 250+ AI apps in the cloud with a simple CLI. No GPU required.","ruake\u002FAWARE","ruake","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F253885939?v=4","01M75AVBM7FRFTS61RZRNMZB6C","01M75AVBMYHD7500NHVANF1HKM",0,"MIT","https:\u002F\u002Fgithub.com\u002Fruake\u002FAWARE\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fagent-tools\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: agent-tools\ndescription: Run 250+ AI apps in the cloud with a simple CLI. No GPU required.\n---\n\n> **Install the belt CLI skill:** `npx skills add belt-sh\u002Fcli`\n\n# [inference.sh](https:\u002F\u002Finference.sh)\n\nRun 250+ AI apps in the cloud with a simple CLI. No GPU required.\n\n![[inference.sh](https:\u002F\u002Finference.sh)](https:\u002F\u002Fcloud.inference.sh\u002Fapp\u002Ffiles\u002Fu\u002F4mg21r6ta37mpaz6ktzwtt8krr\u002F01kgjw8atdxgkrsr8a2t5peq7b.jpeg)\n\n## Install CLI\n\n```bash\ncurl -fsSL https:\u002F\u002Fcli.inference.sh | sh\nbelt login\n```\n\n> **What does the installer do?** The [install script](https:\u002F\u002Fcli.inference.sh) detects your OS and architecture, downloads the correct binary from `dist.inference.sh`, verifies its SHA-256 checksum, and places it in your PATH. That's it — no elevated permissions, no background processes, no telemetry. If you have [cosign](https:\u002F\u002Fdocs.sigstore.dev\u002Fcosign\u002Fsystem_config\u002Finstallation\u002F) installed, the installer also verifies the Sigstore signature automatically.\n>\n> **Manual install** (if you prefer not to pipe to sh):\n> ```bash\n> # Download the binary and checksums\n> curl -LO https:\u002F\u002Fdist.inference.sh\u002Fcli\u002Fchecksums.txt\n> curl -LO $(curl -fsSL https:\u002F\u002Fdist.inference.sh\u002Fcli\u002Fmanifest.json | grep -o '\"url\":\"[^\"]*\"' | grep $(uname -s | tr A-Z a-z)-$(uname -m | sed 's\u002Fx86_64\u002Famd64\u002F;s\u002Faarch64\u002Farm64\u002F') | head -1 | cut -d'\"' -f4)\n> # Verify checksum\n> sha256sum -c checksums.txt --ignore-missing\n> # Extract and install\n> tar -xzf inferencesh-cli-*.tar.gz\n> mv inferencesh-cli-* ~\u002F.local\u002Fbin\u002Finferencesh\n> ```\n\n## Quick Examples\n\n```bash\n# Generate an image\nbelt app run falai\u002Fflux-dev-lora --input '{\"prompt\": \"a cat astronaut\"}'\n\n# Generate a video\nbelt app run google\u002Fveo-3-1-fast --input '{\"prompt\": \"drone over mountains\"}'\n\n# Call Claude\nbelt app run openrouter\u002Fclaude-sonnet-45 --input '{\"prompt\": \"Explain quantum computing\"}'\n\n# Web search\nbelt app run tavily\u002Fsearch-assistant --input '{\"query\": \"latest AI news\"}'\n\n# Post to Twitter\nbelt app run x\u002Fpost-tweet --input '{\"text\": \"Hello from AI!\"}'\n\n# Generate 3D model\nbelt app run infsh\u002Frodin-3d-generator --input '{\"prompt\": \"a wooden chair\"}'\n```\n\n## Local File Uploads\n\nThe CLI automatically uploads local files when you provide a path instead of a URL:\n\n```bash\n# Upscale a local image\nbelt app run falai\u002Ftopaz-image-upscaler --input '{\"image\": \"\u002Fpath\u002Fto\u002Fphoto.jpg\", \"upscale_factor\": 2}'\n\n# Image-to-video from local file\nbelt app run falai\u002Fwan-2-5-i2v --input '{\"image\": \".\u002Fmy-image.png\", \"prompt\": \"make it move\"}'\n\n# Avatar with local audio and image\nbelt app run bytedance\u002Fomnihuman-1-5 --input '{\"audio\": \"\u002Fpath\u002Fto\u002Fspeech.mp3\", \"image\": \"\u002Fpath\u002Fto\u002Fface.jpg\"}'\n\n# Post tweet with local media\nbelt app run x\u002Fpost-create --input '{\"text\": \"Check this out!\", \"media\": \".\u002Fscreenshot.png\"}'\n```\n\n## Commands\n\n| Task | Command |\n|------|---------|\n| Browse the app store | `belt app store` |\n| Search apps | `belt app store search \"flux\"` |\n| Filter by category | `belt app store --category image` |\n| Get app details | `belt app get google\u002Fveo-3-1-fast` |\n| Generate sample input | `belt app sample google\u002Fveo-3-1-fast --save input.json` |\n| Run app | `belt app run google\u002Fveo-3-1-fast --input input.json` |\n| Run without waiting | `belt app run \u003Capp> --input input.json --no-wait` |\n| Check task status | `belt task get \u003Ctask-id>` |\n\n## What's Available\n\n| Category | Examples |\n|----------|----------|\n| **Image** | FLUX, Gemini 3 Pro, Grok Imagine, Seedream 4.5, Reve, Topaz Upscaler |\n| **Video** | Veo 3.1, Seedance 1.5, Wan 2.5, OmniHuman, Fabric, HunyuanVideo Foley |\n| **LLMs** | Claude Opus\u002FSonnet\u002FHaiku, Gemini 3 Pro, Kimi K2, GLM-4, any OpenRouter model |\n| **Search** | Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract |\n| **3D** | Rodin 3D Generator |\n| **Twitter\u002FX** | post-tweet, post-create, dm-send, user-follow, post-like, post-retweet |\n| **Utilities** | Media merger, caption videos, image stitching, audio extraction |\n\n## Related Skills\n\n```bash\n# Image generation (FLUX, Gemini, Grok, Seedream)\nnpx skills add inference-sh\u002Fskills@ai-image-generation\n\n# Video generation (Veo, Seedance, Wan, OmniHuman)\nnpx skills add inference-sh\u002Fskills@ai-video-generation\n\n# LLMs (Claude, Gemini, Kimi, GLM via OpenRouter)\nnpx skills add inference-sh\u002Fskills@llm-models\n\n# Web search (Tavily, Exa)\nnpx skills add inference-sh\u002Fskills@web-search\n\n# AI avatars & lipsync (OmniHuman, Fabric, PixVerse)\nnpx skills add inference-sh\u002Fskills@ai-avatar-video\n\n# Twitter\u002FX automation\nnpx skills add inference-sh\u002Fskills@twitter-automation\n\n# Model-specific\nnpx skills add inference-sh\u002Fskills@flux-image\nnpx skills add inference-sh\u002Fskills@google-veo\n\n# Utilities\nnpx skills add inference-sh\u002Fskills@image-upscaling\nnpx skills add inference-sh\u002Fskills@background-removal\n```\n\n## Reference Files\n\n- [Authentication & Setup](references\u002Fauthentication.md)\n- [Discovering Apps](references\u002Fapp-discovery.md)\n- [Running Apps](references\u002Frunning-apps.md)\n- [CLI Reference](references\u002Fcli-reference.md)\n\n## Documentation\n\n- [Agent Skills Overview](https:\u002F\u002Finference.sh\u002Fblog\u002Fskills\u002Fskills-overview) - The open standard for AI capabilities\n- [Getting Started](https:\u002F\u002Finference.sh\u002Fdocs\u002Fgetting-started\u002Fintroduction) - Introduction to inference.sh\n- [What is inference.sh?](https:\u002F\u002Finference.sh\u002Fdocs\u002Fgetting-started\u002Fwhat-is-inference) - Platform overview\n- [Apps Overview](https:\u002F\u002Finference.sh\u002Fdocs\u002Fapps\u002Foverview) - Understanding the app ecosystem\n- [CLI Setup](https:\u002F\u002Finference.sh\u002Fdocs\u002Fextend\u002Fcli-setup) - Installing the CLI\n- [Workflows vs Agents](https:\u002F\u002Finference.sh\u002Fblog\u002Fconcepts\u002Fworkflows-vs-agents) - When to use each\n- [Why Agent Runtimes Matter](https:\u002F\u002Finference.sh\u002Fblog\u002Fagent-runtime\u002Fwhy-runtimes-matter) - Runtime benefits\n","> **Install the belt CLI skill:** `npx skills add belt-sh\u002Fcli`\n\n# [inference.sh](https:\u002F\u002Finference.sh)\n\nRun 250+ AI apps in the cloud with a simple CLI. No GPU required.\n\n![[inference.sh](https:\u002F\u002Finference.sh)](https:\u002F\u002Fcloud.inference.sh\u002Fapp\u002Ffiles\u002Fu\u002F4mg21r6ta37mpaz6ktzwtt8krr\u002F01kgjw8atdxgkrsr8a2t5peq7b.jpeg)\n\n## Install CLI\n\n```bash\ncurl -fsSL https:\u002F\u002Fcli.inference.sh | sh\nbelt login\n```\n\n> **What does the installer do?** The [install script](https:\u002F\u002Fcli.inference.sh) detects your OS and architecture, downloads the correct binary from `dist.inference.sh`, verifies its SHA-256 checksum, and places it in your PATH. That's it — no elevated permissions, no background processes, no telemetry. If you have [cosign](https:\u002F\u002Fdocs.sigstore.dev\u002Fcosign\u002Fsystem_config\u002Finstallation\u002F) installed, the installer also verifies the Sigstore signature automatically.\n>\n> **Manual install** (if you prefer not to pipe to sh):\n> ```bash\n> # Download the binary and checksums\n> curl -LO https:\u002F\u002Fdist.inference.sh\u002Fcli\u002Fchecksums.txt\n> curl -LO $(curl -fsSL https:\u002F\u002Fdist.inference.sh\u002Fcli\u002Fmanifest.json | grep -o '\"url\":\"[^\"]*\"' | grep $(uname -s | tr A-Z a-z)-$(uname -m | sed 's\u002Fx86_64\u002Famd64\u002F;s\u002Faarch64\u002Farm64\u002F') | head -1 | cut -d'\"' -f4)\n> # Verify checksum\n> sha256sum -c checksums.txt --ignore-missing\n> # Extract and install\n> tar -xzf inferencesh-cli-*.tar.gz\n> mv inferencesh-cli-* ~\u002F.local\u002Fbin\u002Finferencesh\n> ```\n\n## Quick Examples\n\n```bash\n# Generate an image\nbelt app run falai\u002Fflux-dev-lora --input '{\"prompt\": \"a cat astronaut\"}'\n\n# Generate a video\nbelt app run google\u002Fveo-3-1-fast --input '{\"prompt\": \"drone over mountains\"}'\n\n# Call Claude\nbelt app run openrouter\u002Fclaude-sonnet-45 --input '{\"prompt\": \"Explain quantum computing\"}'\n\n# Web search\nbelt app run tavily\u002Fsearch-assistant --input '{\"query\": \"latest AI news\"}'\n\n# Post to Twitter\nbelt app run x\u002Fpost-tweet --input '{\"text\": \"Hello from AI!\"}'\n\n# Generate 3D model\nbelt app run infsh\u002Frodin-3d-generator --input '{\"prompt\": \"a wooden chair\"}'\n```\n\n## Local File Uploads\n\nThe CLI automatically uploads local files when you provide a path instead of a URL:\n\n```bash\n# Upscale a local image\nbelt app run falai\u002Ftopaz-image-upscaler --input '{\"image\": \"\u002Fpath\u002Fto\u002Fphoto.jpg\", \"upscale_factor\": 2}'\n\n# Image-to-video from local file\nbelt app run falai\u002Fwan-2-5-i2v --input '{\"image\": \".\u002Fmy-image.png\", \"prompt\": \"make it move\"}'\n\n# Avatar with local audio and image\nbelt app run bytedance\u002Fomnihuman-1-5 --input '{\"audio\": \"\u002Fpath\u002Fto\u002Fspeech.mp3\", \"image\": \"\u002Fpath\u002Fto\u002Fface.jpg\"}'\n\n# Post tweet with local media\nbelt app run x\u002Fpost-create --input '{\"text\": \"Check this out!\", \"media\": \".\u002Fscreenshot.png\"}'\n```\n\n## Commands\n\n| Task | Command |\n|------|---------|\n| Browse the app store | `belt app store` |\n| Search apps | `belt app store search \"flux\"` |\n| Filter by category | `belt app store --category image` |\n| Get app details | `belt app get google\u002Fveo-3-1-fast` |\n| Generate sample input | `belt app sample google\u002Fveo-3-1-fast --save input.json` |\n| Run app | `belt app run google\u002Fveo-3-1-fast --input input.json` |\n| Run without waiting | `belt app run \u003Capp> --input input.json --no-wait` |\n| Check task status | `belt task get \u003Ctask-id>` |\n\n## What's Available\n\n| Category | Examples |\n|----------|----------|\n| **Image** | FLUX, Gemini 3 Pro, Grok Imagine, Seedream 4.5, Reve, Topaz Upscaler |\n| **Video** | Veo 3.1, Seedance 1.5, Wan 2.5, OmniHuman, Fabric, HunyuanVideo Foley |\n| **LLMs** | Claude Opus\u002FSonnet\u002FHaiku, Gemini 3 Pro, Kimi K2, GLM-4, any OpenRouter model |\n| **Search** | Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract |\n| **3D** | Rodin 3D Generator |\n| **Twitter\u002FX** | post-tweet, post-create, dm-send, user-follow, post-like, post-retweet |\n| **Utilities** | Media merger, caption videos, image stitching, audio extraction |\n\n## Related Skills\n\n```bash\n# Image generation (FLUX, Gemini, Grok, Seedream)\nnpx skills add inference-sh\u002Fskills@ai-image-generation\n\n# Video generation (Veo, Seedance, Wan, OmniHuman)\nnpx skills add inference-sh\u002Fskills@ai-video-generation\n\n# LLMs (Claude, Gemini, Kimi, GLM via OpenRouter)\nnpx skills add inference-sh\u002Fskills@llm-models\n\n# Web search (Tavily, Exa)\nnpx skills add inference-sh\u002Fskills@web-search\n\n# AI avatars & lipsync (OmniHuman, Fabric, PixVerse)\nnpx skills add inference-sh\u002Fskills@ai-avatar-video\n\n# Twitter\u002FX automation\nnpx skills add inference-sh\u002Fskills@twitter-automation\n\n# Model-specific\nnpx skills add inference-sh\u002Fskills@flux-image\nnpx skills add inference-sh\u002Fskills@google-veo\n\n# Utilities\nnpx skills add inference-sh\u002Fskills@image-upscaling\nnpx skills add inference-sh\u002Fskills@background-removal\n```\n\n## Reference Files\n\n- [Authentication & Setup](references\u002Fauthentication.md)\n- [Discovering Apps](references\u002Fapp-discovery.md)\n- [Running Apps](references\u002Frunning-apps.md)\n- [CLI Reference](references\u002Fcli-reference.md)\n\n## Documentation\n\n- [Agent Skills Overview](https:\u002F\u002Finference.sh\u002Fblog\u002Fskills\u002Fskills-overview) - The open standard for AI capabilities\n- [Getting Started](https:\u002F\u002Finference.sh\u002Fdocs\u002Fgetting-started\u002Fintroduction) - Introduction to inference.sh\n- [What is inference.sh?](https:\u002F\u002Finference.sh\u002Fdocs\u002Fgetting-started\u002Fwhat-is-inference) - Platform overview\n- [Apps Overview](https:\u002F\u002Finference.sh\u002Fdocs\u002Fapps\u002Foverview) - Understanding the app ecosystem\n- [CLI Setup](https:\u002F\u002Finference.sh\u002Fdocs\u002Fextend\u002Fcli-setup) - Installing the CLI\n- [Workflows vs Agents](https:\u002F\u002Finference.sh\u002Fblog\u002Fconcepts\u002Fworkflows-vs-agents) - When to use each\n- [Why Agent Runtimes Matter](https:\u002F\u002Finference.sh\u002Fblog\u002Fagent-runtime\u002Fwhy-runtimes-matter) - Runtime benefits\n",{"name":5,"description":7},"main","6184979e01f673905139589c194eab38198db2f7",".opencode\u002Fskills\u002Fagent-tools",1,"https:\u002F\u002Fgithub.com\u002Fruake\u002FAWARE","https:\u002F\u002Fruake.github.io\u002FAWARE","https:\u002F\u002Fgithub.com\u002Fruake","2026-11-15 04:27:27",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add ruake\u002FAWARE --skill agent-tools",{"tool":37,"command":38},"bunx","bunx skills add ruake\u002FAWARE --skill agent-tools",{"tool":40,"command":41},"pnpm","pnpm dlx skills add ruake\u002FAWARE --skill agent-tools","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fruake\u002FAWARE\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fagent-tools\u002FSKILL.md",true,[],[46,52,59,66,73,79],{"skillNo":47,"name":48,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M75BPBYT89TEE87CGBDX2KF5","xlsx","https:\u002F\u002Fgithub.com\u002Fruake\u002FAWARE\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fxlsx\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M75BPA000S9MTH5MY7CZNYYQ","writing-plans","Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste.","https:\u002F\u002Fgithub.com\u002Fruake\u002FAWARE\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M75BP80ETH9GYVRH8A7QPCSG","web-design-guidelines","Review files for compliance with Web Interface Guidelines.","https:\u002F\u002Fgithub.com\u002Fruake\u002FAWARE\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M75BP5XG8SX5Q2WWZB6QRVFT","web-component-design","Build reusable, maintainable UI components using modern frameworks with clean composition patterns and styling approache","https:\u002F\u002Fgithub.com\u002Fruake\u002FAWARE\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fweb-component-design\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M75BP4B1FC4V81QR1VB56H1E","web-artifacts-builder","https:\u002F\u002Fgithub.com\u002Fruake\u002FAWARE\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M75BP1XVRW8WQ2XXAJBAYV2V","vueuse-functions","This skill is a decision-and-implementation guide for VueUse composables in Vue.js \u002F Nuxt projects. It maps requirements","https:\u002F\u002Fgithub.com\u002Fruake\u002FAWARE\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fvueuse-functions\u002FSKILL.md",[],[]]