[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71FKWDG64SCRRHNBK14QVHZ":3,"skill-same:01M71FKWDG64SCRRHNBK14QVHZ":98},{"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":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":60,"commitSha":61,"skillDirectory":62,"forksCount":13,"repositoryHtmlUrl":63,"repositoryHomepageUrl":6,"ownerHtmlUrl":64,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":65,"install":66,"resources":79},"01M71FKWDG64SCRRHNBK14QVHZ","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","gjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6","gjbvsjjvgm-sketch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F278511911?v=4","01M71F3JXKZQ70H2KCHHTXKZDA","01M71F3JY8A79Z3NZBW08TF4JD",0,"MIT","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes-agent\u002Foptional-skills\u002Fdevops\u002Fcli\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"cli","inference sh","inference","inference sh cli","seedance","image","apps","triggers","creation","social","image-generation","video generation","tool","3D","Video","Image Generation","search","automation","llms","tavily","2026-11-10 10:12:30",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\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":48,"license":14,"version":49,"metadata":50,"description":7},"okaris","1.0.0",{"hermes":51},{"tags":52,"related_skills":59},[53,33,54,55,39,25,56,57,58],"AI","video","LLM","FLUX","Veo","Claude",[],"main","93bbc269671fbb340afa15b36a8766f15dc30df2","hermes-agent\u002Foptional-skills\u002Fdevops\u002Fcli","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch","2026-04-27 02:51:28",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add gjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6 --skill inference-sh-cli",{"tool":72,"command":73},"bunx","bunx skills add gjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6 --skill inference-sh-cli",{"tool":75,"command":76},"pnpm","pnpm dlx skills add gjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6 --skill inference-sh-cli","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes-agent\u002Foptional-skills\u002Fdevops\u002Fcli\u002FSKILL.md",true,[80,86,90,94],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fapp-discovery.md","REFERENCE","参考文档",2120,"https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes-agent\u002Foptional-skills\u002Fdevops\u002Fcli\u002Freferences\u002Fapp-discovery.md",{"path":87,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fauthentication.md",1084,"https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes-agent\u002Foptional-skills\u002Fdevops\u002Fcli\u002Freferences\u002Fauthentication.md",{"path":91,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fcli-reference.md",3181,"https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes-agent\u002Foptional-skills\u002Fdevops\u002Fcli\u002Freferences\u002Fcli-reference.md",{"path":95,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Frunning-apps.md",3705,"https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes-agent\u002Foptional-skills\u002Fdevops\u002Fcli\u002Freferences\u002Frunning-apps.md",[99,140,168,184,203,224],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":119,"publishedAt":43},"01M71G6TJ2RAQ1J0PV3K6D9GQA","writing-plans","Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Fwriting-plans\u002FSKILL.md",[105,108,111,116],{"categoryNo":106,"categoryName":107,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":109,"categoryName":110,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":112,"categoryName":113,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":117,"categoryName":118,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000036","内容创作者",[120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","superpowers","paths","test-driven-development","you","for","test-driven","when",{"skillNo":141,"name":135,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":153,"publishedAt":43},"01M71G6R81013R3T7W5VP56GCB","Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Ftest-driven-development\u002FSKILL.md",[145,148,151,152],{"categoryNo":146,"categoryName":147,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":149,"categoryName":150,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":109,"categoryName":110,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":117,"categoryName":118,"taxonomyType":114,"taxonomyTypeDesc":115},[154,155,128,156,157,120,158,129,159,132,133,160,161,162,163,164,165,166,167,139],"test","test driven development","driven","testing","debugging","refactor","red-green-refactor","cycle","green","systematic","bugfix","implementing","systematic-debugging","test-first",{"skillNo":169,"name":166,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":174,"publishedAt":43},"01M71G6N0Y546JZEDF25E2PMCE","Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Fsystematic-debugging\u002FSKILL.md",[173],{"categoryNo":149,"categoryName":150,"taxonomyType":20,"taxonomyTypeDesc":21},[175,158,163,120,154,128,132,176,133,177,178,179,122,180,135,181,138,182,183,139],"systematic debugging","use","bug","root-cause","problem-solving","problem","fixes","phase","root cause",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":196,"publishedAt":43},"01M71G6J0DXEGY48GH4KVW2SJH","subagent-driven-development","Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Fsubagent-driven-development\u002FSKILL.md",[190,191,192,193],{"categoryNo":109,"categoryName":110,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":112,"categoryName":113,"taxonomyType":114,"taxonomyTypeDesc":115},{"categoryNo":117,"categoryName":118,"taxonomyType":114,"taxonomyTypeDesc":115},{"categoryNo":194,"categoryName":195,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000037","律师与法务",[128,197,132,156,120,124,125,198,127,129,199,131,200,201,133,122,202,135,138,139],"subagent driven development","code quality","delegation","parallel","delegate","fresh",{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":211,"publishedAt":43},"01M71G6EFFBQX6634E6XHB09Y1","requesting-code-review","Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Frequesting-code-review\u002FSKILL.md",[209,210],{"categoryNo":146,"categoryName":147,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":112,"categoryName":113,"taxonomyType":114,"taxonomyTypeDesc":115},[212,124,129,213,120,214,131,215,216,217,218,132,219,220,221,133,135,222,223,138],"code review","requesting code review","commit","verification","security scan","pipeline","loop","reviewer","fix","auto","static","auto-fix",{"skillNo":225,"name":226,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":230,"publishedAt":43},"01M71G6CM8ANSWVFXCN9AAD58Y","plan","Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes\u002Fplans\u002F` directory, and do not execute the work.","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Fplan\u002FSKILL.md",[],[226,120,231,125,128,130,232,132,233,234,235,236,237,238,122,239,240,241,137,242],"directory","markdown","workspace","work","write","implementation","do","active","plan mode","inspect","mode","plan-mode"]