[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D7BC63BSWSQ7SQCM9Z2PN0":3,"skill-same:01M7D7BC63BSWSQ7SQCM9Z2PN0":83},{"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":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M7D7BC63BSWSQ7SQCM9Z2PN0","inference-sh-cli",null,"Run 150+ AI apps via inference.sh CLI (infsh) — image generation, video creation, LLMs, search, 3D, social automation. Uses the terminal tool. Triggers: inference.sh, infsh, ai apps, flux, veo, image generation, video generation, seedream, seedance, tavily","GrupoANDevelopment-m\u002Falberto-ai","GrupoANDevelopment-m","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F257455179?v=4","01M7D69X2N2KEVN0SJF6WGM6SH","Antônio  Ndombe","01M7D69X3P5JTT8H8S904N3888",0,"MIT","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Foptional\u002Fdevops\u002Fcli\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inference-sh-cli\ndescription: \"Run 150+ AI apps via inference.sh CLI (infsh) — image generation, video creation, LLMs, search, 3D, social automation. Uses the terminal tool. Triggers: inference.sh, infsh, ai apps, flux, veo, image generation, video generation, seedream, seedance, tavily\"\nversion: 1.0.0\nauthor: okaris\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [AI, image-generation, video, LLM, search, inference, FLUX, Veo, Claude]\n    related_skills: []\n---\n\n# inference.sh CLI\n\nRun 150+ AI apps in the cloud with a simple CLI. No GPU required.\n\nAll commands use the **terminal tool** to run `infsh` commands.\n\n## When to Use\n\n- User asks to generate images (FLUX, Reve, Seedream, Grok, Gemini image)\n- User asks to generate video (Veo, Wan, Seedance, OmniHuman)\n- User asks about inference.sh or infsh\n- User wants to run AI apps without managing individual provider APIs\n- User asks for AI-powered search (Tavily, Exa)\n- User needs avatar\u002Flipsync generation\n\n## Prerequisites\n\nThe `infsh` CLI must be installed and authenticated. Check with:\n\n```bash\ninfsh me\n```\n\nIf not installed:\n\n```bash\ncurl -fsSL https:\u002F\u002Fcli.inference.sh | sh\ninfsh login\n```\n\nSee `references\u002Fauthentication.md` for full setup details.\n\n## Workflow\n\n### 1. Always Search First\n\nNever guess app names — always search to find the correct app ID:\n\n```bash\ninfsh app list --search flux\ninfsh app list --search video\ninfsh app list --search image\n```\n\n### 2. Run an App\n\nUse the exact app ID from the search results. Always use `--json` for machine-readable output:\n\n```bash\ninfsh app run \u003Capp-id> --input '{\"prompt\": \"your prompt here\"}' --json\n```\n\n### 3. Parse the Output\n\nThe JSON output contains URLs to generated media. Present these to the user with `MEDIA:\u003Curl>` for inline display.\n\n## Common Commands\n\n### Image Generation\n\n```bash\n# Search for image apps\ninfsh app list --search image\n\n# FLUX Dev with LoRA\ninfsh app run falai\u002Fflux-dev-lora --input '{\"prompt\": \"sunset over mountains\", \"num_images\": 1}' --json\n\n# Gemini image generation\ninfsh app run google\u002Fgemini-2-5-flash-image --input '{\"prompt\": \"futuristic city\", \"num_images\": 1}' --json\n\n# Seedream (ByteDance)\ninfsh app run bytedance\u002Fseedream-5-lite --input '{\"prompt\": \"nature scene\"}' --json\n\n# Grok Imagine (xAI)\ninfsh app run xai\u002Fgrok-imagine-image --input '{\"prompt\": \"abstract art\"}' --json\n```\n\n### Video Generation\n\n```bash\n# Search for video apps\ninfsh app list --search video\n\n# Veo 3.1 (Google)\ninfsh app run google\u002Fveo-3-1-fast --input '{\"prompt\": \"drone shot of coastline\"}' --json\n\n# Seedance (ByteDance)\ninfsh app run bytedance\u002Fseedance-1-5-pro --input '{\"prompt\": \"dancing figure\", \"resolution\": \"1080p\"}' --json\n\n# Wan 2.5\ninfsh app run falai\u002Fwan-2-5 --input '{\"prompt\": \"person walking through city\"}' --json\n```\n\n### Local File Uploads\n\nThe CLI automatically uploads local files when you provide a path:\n\n```bash\n# Upscale a local image\ninfsh app run falai\u002Ftopaz-image-upscaler --input '{\"image\": \"\u002Fpath\u002Fto\u002Fphoto.jpg\", \"upscale_factor\": 2}' --json\n\n# Image-to-video from local file\ninfsh app run falai\u002Fwan-2-5-i2v --input '{\"image\": \"\u002Fpath\u002Fto\u002Fimage.png\", \"prompt\": \"make it move\"}' --json\n\n# Avatar with audio\ninfsh app run bytedance\u002Fomnihuman-1-5 --input '{\"audio\": \"\u002Fpath\u002Fto\u002Faudio.mp3\", \"image\": \"\u002Fpath\u002Fto\u002Fface.jpg\"}' --json\n```\n\n### Search & Research\n\n```bash\ninfsh app list --search search\ninfsh app run tavily\u002Ftavily-search --input '{\"query\": \"latest AI news\"}' --json\ninfsh app run exa\u002Fexa-search --input '{\"query\": \"machine learning papers\"}' --json\n```\n\n### Other Categories\n\n```bash\n# 3D generation\ninfsh app list --search 3d\n\n# Audio \u002F TTS\ninfsh app list --search tts\n\n# Twitter\u002FX automation\ninfsh app list --search twitter\n```\n\n## Pitfalls\n\n1. **Never guess app IDs** — always run `infsh app list --search \u003Cterm>` first. App IDs change and new apps are added frequently.\n2. **Always use `--json`** — raw output is hard to parse. The `--json` flag gives structured output with URLs.\n3. **Check authentication** — if commands fail with auth errors, run `infsh login` or verify `INFSH_API_KEY` is set.\n4. **Long-running apps** — video generation can take 30-120 seconds. The terminal tool timeout should be sufficient, but warn the user it may take a moment.\n5. **Input format** — the `--input` flag takes a JSON string. Make sure to properly escape quotes.\n\n## Reference Docs\n\n- `references\u002Fauthentication.md` — Setup, login, API keys\n- `references\u002Fapp-discovery.md` — Searching and browsing the app catalog\n- `references\u002Frunning-apps.md` — Running apps, input formats, output handling\n- `references\u002Fcli-reference.md` — Complete CLI command reference\n","# inference.sh CLI\n\nRun 150+ AI apps in the cloud with a simple CLI. No GPU required.\n\nAll commands use the **terminal tool** to run `infsh` commands.\n\n## When to Use\n\n- User asks to generate images (FLUX, Reve, Seedream, Grok, Gemini image)\n- User asks to generate video (Veo, Wan, Seedance, OmniHuman)\n- User asks about inference.sh or infsh\n- User wants to run AI apps without managing individual provider APIs\n- User asks for AI-powered search (Tavily, Exa)\n- User needs avatar\u002Flipsync generation\n\n## Prerequisites\n\nThe `infsh` CLI must be installed and authenticated. Check with:\n\n```bash\ninfsh me\n```\n\nIf not installed:\n\n```bash\ncurl -fsSL https:\u002F\u002Fcli.inference.sh | sh\ninfsh login\n```\n\nSee `references\u002Fauthentication.md` for full setup details.\n\n## Workflow\n\n### 1. Always Search First\n\nNever guess app names — always search to find the correct app ID:\n\n```bash\ninfsh app list --search flux\ninfsh app list --search video\ninfsh app list --search image\n```\n\n### 2. Run an App\n\nUse the exact app ID from the search results. Always use `--json` for machine-readable output:\n\n```bash\ninfsh app run \u003Capp-id> --input '{\"prompt\": \"your prompt here\"}' --json\n```\n\n### 3. Parse the Output\n\nThe JSON output contains URLs to generated media. Present these to the user with `MEDIA:\u003Curl>` for inline display.\n\n## Common Commands\n\n### Image Generation\n\n```bash\n# Search for image apps\ninfsh app list --search image\n\n# FLUX Dev with LoRA\ninfsh app run falai\u002Fflux-dev-lora --input '{\"prompt\": \"sunset over mountains\", \"num_images\": 1}' --json\n\n# Gemini image generation\ninfsh app run google\u002Fgemini-2-5-flash-image --input '{\"prompt\": \"futuristic city\", \"num_images\": 1}' --json\n\n# Seedream (ByteDance)\ninfsh app run bytedance\u002Fseedream-5-lite --input '{\"prompt\": \"nature scene\"}' --json\n\n# Grok Imagine (xAI)\ninfsh app run xai\u002Fgrok-imagine-image --input '{\"prompt\": \"abstract art\"}' --json\n```\n\n### Video Generation\n\n```bash\n# Search for video apps\ninfsh app list --search video\n\n# Veo 3.1 (Google)\ninfsh app run google\u002Fveo-3-1-fast --input '{\"prompt\": \"drone shot of coastline\"}' --json\n\n# Seedance (ByteDance)\ninfsh app run bytedance\u002Fseedance-1-5-pro --input '{\"prompt\": \"dancing figure\", \"resolution\": \"1080p\"}' --json\n\n# Wan 2.5\ninfsh app run falai\u002Fwan-2-5 --input '{\"prompt\": \"person walking through city\"}' --json\n```\n\n### Local File Uploads\n\nThe CLI automatically uploads local files when you provide a path:\n\n```bash\n# Upscale a local image\ninfsh app run falai\u002Ftopaz-image-upscaler --input '{\"image\": \"\u002Fpath\u002Fto\u002Fphoto.jpg\", \"upscale_factor\": 2}' --json\n\n# Image-to-video from local file\ninfsh app run falai\u002Fwan-2-5-i2v --input '{\"image\": \"\u002Fpath\u002Fto\u002Fimage.png\", \"prompt\": \"make it move\"}' --json\n\n# Avatar with audio\ninfsh app run bytedance\u002Fomnihuman-1-5 --input '{\"audio\": \"\u002Fpath\u002Fto\u002Faudio.mp3\", \"image\": \"\u002Fpath\u002Fto\u002Fface.jpg\"}' --json\n```\n\n### Search & Research\n\n```bash\ninfsh app list --search search\ninfsh app run tavily\u002Ftavily-search --input '{\"query\": \"latest AI news\"}' --json\ninfsh app run exa\u002Fexa-search --input '{\"query\": \"machine learning papers\"}' --json\n```\n\n### Other Categories\n\n```bash\n# 3D generation\ninfsh app list --search 3d\n\n# Audio \u002F TTS\ninfsh app list --search tts\n\n# Twitter\u002FX automation\ninfsh app list --search twitter\n```\n\n## Pitfalls\n\n1. **Never guess app IDs** — always run `infsh app list --search \u003Cterm>` first. App IDs change and new apps are added frequently.\n2. **Always use `--json`** — raw output is hard to parse. The `--json` flag gives structured output with URLs.\n3. **Check authentication** — if commands fail with auth errors, run `infsh login` or verify `INFSH_API_KEY` is set.\n4. **Long-running apps** — video generation can take 30-120 seconds. The terminal tool timeout should be sufficient, but warn the user it may take a moment.\n5. **Input format** — the `--input` flag takes a JSON string. Make sure to properly escape quotes.\n\n## Reference Docs\n\n- `references\u002Fauthentication.md` — Setup, login, API keys\n- `references\u002Fapp-discovery.md` — Searching and browsing the app catalog\n- `references\u002Frunning-apps.md` — Running apps, input formats, output handling\n- `references\u002Fcli-reference.md` — Complete CLI command reference\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":39,"description":7},"okaris","1.0.0",{"hermes":27},{"tags":28,"related_skills":38},[29,30,31,32,33,34,35,36,37],"AI","image-generation","video","LLM","search","inference","FLUX","Veo","Claude",[],[40,41,42],"linux","macos","windows","main","eac438ea9216a7cb8a570cab803eb01eeafc6793","skills\u002Foptional\u002Fdevops\u002Fcli","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m","https:\u002F\u002Fid-preview--d5bef06d-6c9e-4563-a3d4-a855b9d61610.lovable.app\u002F","Eu sou Antonio B. B. Ndombe \r\nEu sou um Pesquisador e desenvolvedor de sistema autonomia cognitivos, fundador de sistemas ODCs ( organismos digital conscientes)","2026-11-04 06:53:39",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add GrupoANDevelopment-m\u002Falberto-ai --skill inference-sh-cli",{"tool":57,"command":58},"bunx","bunx skills add GrupoANDevelopment-m\u002Falberto-ai --skill inference-sh-cli",{"tool":60,"command":61},"pnpm","pnpm dlx skills add GrupoANDevelopment-m\u002Falberto-ai --skill inference-sh-cli","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Foptional\u002Fdevops\u002Fcli\u002FSKILL.md",true,[65,71,75,79],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fapp-discovery.md","REFERENCE","参考文档",2120,"https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Foptional\u002Fdevops\u002Fcli\u002Freferences\u002Fapp-discovery.md",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fauthentication.md",1084,"https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Foptional\u002Fdevops\u002Fcli\u002Freferences\u002Fauthentication.md",{"path":76,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fcli-reference.md",3181,"https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Foptional\u002Fdevops\u002Fcli\u002Freferences\u002Fcli-reference.md",{"path":80,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Frunning-apps.md",3705,"https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Foptional\u002Fdevops\u002Fcli\u002Freferences\u002Frunning-apps.md",[84,92,99,106,113,120],{"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":88,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7DASC6FSCJP49JZBSK0NY1Z","nemoclaw-user-reference","Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture, agent integration, plugin structure, or blueprint design. Trigger keywords - nemoclaw architecture, nemoclaw agent architecture, nemoclaw plugin blueprint structure, nemoclaw vs openshell, which cli, nemoclaw cli, openshell cli, sandbox commands, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-reference\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7DAS5S79VK33XFGVAM2TFWF","nemoclaw-user-overview","Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-overview\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7DAS0PQEMET5MNGZ1ABSZVS","nemoclaw-user-monitor-sandbox","Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-monitor-sandbox\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7DARQYGF7E9A69VH6S3CGN9","nemoclaw-user-manage-sandboxes","Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw sandboxes, nemoclaw status, nemoclaw list, nemoclaw dashboard port, nemoclaw rebuild, nemoclaw upgrade sandboxes, nemoclaw uninstall, sandbox mutability, sandbox runtime configuration, sandbox rebuild, nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw messaging channels, nemoclaw telegram, nemoclaw discord, nemoclaw slack, nemoclaw wechat, nemoclaw whatsapp, openshell channel messaging, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M7DARH8BRTG51TRCAB7YWDJ4","nemoclaw-user-manage-policy","Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access. Trigger keywords - customize nemoclaw network policy, sandbox egress policy configuration, nemoclaw integration policy examples, post-install policy setup, openshell approval workflow, policy preset, nemoclaw approve network requests, sandbox egress approval tui.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-policy\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":19},"01M7DARAT62M2VR37590VCZ5NS","nemoclaw-user-get-started","Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-get-started\u002FSKILL.md",[],[]]