[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70HBSX0HMQ6VQGNG4X478T1":3,"skill-same:01M70HBSX0HMQ6VQGNG4X478T1":154},{"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":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":90,"commitSha":91,"skillDirectory":92,"forksCount":93,"repositoryHtmlUrl":94,"repositoryHomepageUrl":6,"ownerHtmlUrl":95,"ownerBlogUrl":6,"ownerDescription":96,"updatedAt":97,"install":98,"resources":111},"01M70HBSX0HMQ6VQGNG4X478T1","a0-development",null,"Develop or operate Agent Zero: projects, chats, tasks, framework, tools and API\u002FWebUI.","mdnaimul22\u002Fhuman-skills","mdnaimul22","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64520358?v=4","01M70FH95MH2H796Q01TYSFZ03","Naimul","01M70FH96798CQR4YHA13F17GA",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"a0 development","development","activate","dox","extending","agent-zero","new","operate","prompt system","build agent","project","architecture","work","projects","loop","how","team","api","create","tasks","2026-11-10 10:12:30",false,"---\nname: a0-development\ndescription: \"Develop or operate Agent Zero: projects, chats, tasks, framework, tools and API\u002FWebUI.\"\nversion: 1.1.0\nauthor: Agent Zero Team\ntags: [\"development\", \"framework\", \"agent-zero\", \"extending\", \"tools\", \"extensions\", \"skills\", \"api\", \"agents\", \"prompts\", \"dox\"]\ntrigger_patterns:\n  - \"extend agent zero\"\n  - \"agent zero development\"\n  - \"build agent zero feature\"\n  - \"create agent zero tool\"\n  - \"add extension\"\n  - \"framework development\"\n  - \"agent zero architecture\"\n  - \"how does agent zero work\"\n  - \"create agent zero extension\"\n  - \"add api endpoint\"\n  - \"create agent profile\"\n  - \"agent zero internals\"\n  - \"how does the agent loop work\"\n  - \"extension hook points\"\n  - \"prompt system\"\n  - \"agent profile\"\n  - \"dox\"\n  - \"manage Agent Zero projects\"\n  - \"create Agent Zero chat\"\n  - \"Agent Zero API\"\n  - \"create project\"\n  - \"activate project\"\n  - \"project instructions\"\n  - \"create chat\"\n  - \"new chat\"\n---\n\n# Agent Zero Development\n\nUse this skill to develop Agent Zero or operate an existing instance on the user's behalf. For projects, chats, tasks, and other application features, read `references\u002Foperate-agent-zero.md` and use existing APIs. Load only the references needed for the task; verify current source before changing code.\n\n## Reality Rules\n\n1. Source and nearest DOX beat memory, examples, and this skill if they disagree.\n2. Before editing, read the applicable `AGENTS.md` chain from the repo root to every file you expect to touch.\n3. New capabilities should usually be plugins. For plugin-specific work, load `a0-create-plugin` for authoring\u002Freview\u002Fcontribution or `a0-manage-plugin` for discovery and lifecycle operations.\n4. Do not assume ports. Discover WebUI host\u002Fport from startup output, launcher or Docker mapping, or explicit `--host`, `--port`, `WEB_UI_HOST`, and `WEB_UI_PORT` configuration.\n5. In Docker, framework checks belong to `\u002Fopt\u002Fvenv-a0` and agent\u002Fuser code execution belongs to `\u002Fopt\u002Fvenv`. Do not use one runtime as proof for the other.\n6. Treat `\u002Fa0\u002F` as the runtime framework root inside Docker. In local development it means the repository root. If a live container matters, prove that `\u002Fa0` matches the checkout before trusting source-only conclusions.\n7. Do not document or change ignored `usr\u002F` or `tmp\u002F` runtime state unless the user explicitly asks.\n\n## Reference Map\n\nLoad references with:\n\n```json\n{\"tool_name\": \"skills_tool:read_file\", \"tool_args\": {\"skill_name\": \"a0-development\", \"file_path\": \"references\u002F\u003Cfile>.md\"}}\n```\n\n| Need | Read |\n|---|---|\n| Operate Agent Zero for the user: projects, chats, tasks, profiles, skills and settings | `references\u002Foperate-agent-zero.md` |\n| Runtime split, root layout, discovery order, path and port boundaries | `references\u002Farchitecture-runtime.md` |\n| DOX edit workflow, when to update docs, file-level DOX checks | `references\u002Fdox-workflow.md` |\n| Tool contracts, locations, prompts, and verification | `references\u002Ftools.md` |\n| Python\u002FWebUI extension discovery, hook points, ordering, implicit hooks | `references\u002Fextensions.md` |\n| HTTP API, WebSocket handlers, WebUI extension surfaces | `references\u002Fapi-webui.md` |\n| Agent profiles, prompts, skills, projects | `references\u002Fagents-prompts-skills-projects.md` |\n| Plugin-first workflow, where to put new work, handoffs to plugin skills | `references\u002Fplugins-workflow.md` |\n\n## Working Flow\n\n1. Distinguish operating existing features from developing new behavior. For application operations, follow `references\u002Foperate-agent-zero.md`; the remaining steps apply to source changes.\n2. Read the root `AGENTS.md`, then the nearest child `AGENTS.md` files for the target paths.\n3. Read the focused reference file from this skill.\n4. Inspect the current source files named by the reference before making a claim or patch.\n5. Keep changes narrow and in the repo-owned surface. Prefer `usr\u002F` for user-created runtime content, but do not document ignored user state unless requested.\n6. Update DOX when a durable contract, path, behavior, workflow, responsibility, or verification rule changes.\n7. Run targeted checks from the relevant DOX file. For skill-only changes, at minimum verify frontmatter parsing, reference paths, and markdown sanity.\n\n## Handoffs\n\n- Plugin creation: load `a0-create-plugin`.\n- Plugin management or installation: load `a0-manage-plugin`.\n- Plugin review, debugging or publishing: load `a0-create-plugin` and read its relevant reference.\n- Agent profile creation: load `a0-create-agent`.\n- Skill creation or skill format work: load `build-skill`.\n\n## Closeout\n\nReport the exact files changed, the grounding checks used, whether DOX was updated or intentionally left unchanged, and what verification ran. If a claim depends on a live Docker runtime, include the runtime proof, not only checkout evidence.\n","# Agent Zero Development\n\nUse this skill to develop Agent Zero or operate an existing instance on the user's behalf. For projects, chats, tasks, and other application features, read `references\u002Foperate-agent-zero.md` and use existing APIs. Load only the references needed for the task; verify current source before changing code.\n\n## Reality Rules\n\n1. Source and nearest DOX beat memory, examples, and this skill if they disagree.\n2. Before editing, read the applicable `AGENTS.md` chain from the repo root to every file you expect to touch.\n3. New capabilities should usually be plugins. For plugin-specific work, load `a0-create-plugin` for authoring\u002Freview\u002Fcontribution or `a0-manage-plugin` for discovery and lifecycle operations.\n4. Do not assume ports. Discover WebUI host\u002Fport from startup output, launcher or Docker mapping, or explicit `--host`, `--port`, `WEB_UI_HOST`, and `WEB_UI_PORT` configuration.\n5. In Docker, framework checks belong to `\u002Fopt\u002Fvenv-a0` and agent\u002Fuser code execution belongs to `\u002Fopt\u002Fvenv`. Do not use one runtime as proof for the other.\n6. Treat `\u002Fa0\u002F` as the runtime framework root inside Docker. In local development it means the repository root. If a live container matters, prove that `\u002Fa0` matches the checkout before trusting source-only conclusions.\n7. Do not document or change ignored `usr\u002F` or `tmp\u002F` runtime state unless the user explicitly asks.\n\n## Reference Map\n\nLoad references with:\n\n```json\n{\"tool_name\": \"skills_tool:read_file\", \"tool_args\": {\"skill_name\": \"a0-development\", \"file_path\": \"references\u002F\u003Cfile>.md\"}}\n```\n\n| Need | Read |\n|---|---|\n| Operate Agent Zero for the user: projects, chats, tasks, profiles, skills and settings | `references\u002Foperate-agent-zero.md` |\n| Runtime split, root layout, discovery order, path and port boundaries | `references\u002Farchitecture-runtime.md` |\n| DOX edit workflow, when to update docs, file-level DOX checks | `references\u002Fdox-workflow.md` |\n| Tool contracts, locations, prompts, and verification | `references\u002Ftools.md` |\n| Python\u002FWebUI extension discovery, hook points, ordering, implicit hooks | `references\u002Fextensions.md` |\n| HTTP API, WebSocket handlers, WebUI extension surfaces | `references\u002Fapi-webui.md` |\n| Agent profiles, prompts, skills, projects | `references\u002Fagents-prompts-skills-projects.md` |\n| Plugin-first workflow, where to put new work, handoffs to plugin skills | `references\u002Fplugins-workflow.md` |\n\n## Working Flow\n\n1. Distinguish operating existing features from developing new behavior. For application operations, follow `references\u002Foperate-agent-zero.md`; the remaining steps apply to source changes.\n2. Read the root `AGENTS.md`, then the nearest child `AGENTS.md` files for the target paths.\n3. Read the focused reference file from this skill.\n4. Inspect the current source files named by the reference before making a claim or patch.\n5. Keep changes narrow and in the repo-owned surface. Prefer `usr\u002F` for user-created runtime content, but do not document ignored user state unless requested.\n6. Update DOX when a durable contract, path, behavior, workflow, responsibility, or verification rule changes.\n7. Run targeted checks from the relevant DOX file. For skill-only changes, at minimum verify frontmatter parsing, reference paths, and markdown sanity.\n\n## Handoffs\n\n- Plugin creation: load `a0-create-plugin`.\n- Plugin management or installation: load `a0-manage-plugin`.\n- Plugin review, debugging or publishing: load `a0-create-plugin` and read its relevant reference.\n- Agent profile creation: load `a0-create-agent`.\n- Skill creation or skill format work: load `build-skill`.\n\n## Closeout\n\nReport the exact files changed, the grounding checks used, whether DOX was updated or intentionally left unchanged, and what verification ran. If a claim depends on a live Docker runtime, include the runtime proof, not only checkout evidence.\n",{"name":5,"tags":57,"author":64,"version":65,"description":7,"trigger_patterns":66},[33,58,37,36,59,60,61,49,62,63,35],"framework","tools","extensions","skills","agents","prompts","Agent Zero Team","1.1.0",[67,68,69,70,71,72,73,74,75,76,77,78,79,80,40,81,35,82,83,84,85,86,87,88,89],"extend agent zero","agent zero development","build agent zero feature","create agent zero tool","add extension","framework development","agent zero architecture","how does agent zero work","create agent zero extension","add api endpoint","create agent profile","agent zero internals","how does the agent loop work","extension hook points","agent profile","manage Agent Zero projects","create Agent Zero chat","Agent Zero API","create project","activate project","project instructions","create chat","new chat","main","74715deacdc69119d739f38916f8ee4f0f979ebf","skills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development",0,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills","https:\u002F\u002Fgithub.com\u002Fmdnaimul22","AI Agents Workflows Automation | Specializing in Python, FastAPI, MCP Agents & Custom ERP.","2026-11-11 21:16:57",{"source":8,"skillName":5,"commands":99,"prompt":109,"zipAvailable":110},[100,103,106],{"tool":101,"command":102},"npx","npx skills add mdnaimul22\u002Fhuman-skills --skill a0-development",{"tool":104,"command":105},"bunx","bunx skills add mdnaimul22\u002Fhuman-skills --skill a0-development",{"tool":107,"command":108},"pnpm","pnpm dlx skills add mdnaimul22\u002Fhuman-skills --skill a0-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002FSKILL.md",true,[112,118,122,126,130,134,138,142,146,150],{"path":113,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":116,"sourceHtmlUrl":117},"AGENTS.md","REFERENCE","参考文档",1785,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002FAGENTS.md",{"path":119,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Fagents-prompts-skills-projects.md",4671,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002Freferences\u002Fagents-prompts-skills-projects.md",{"path":123,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002FAGENTS.md",2080,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002Freferences\u002FAGENTS.md",{"path":127,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":128,"sourceHtmlUrl":129},"references\u002Fapi-webui.md",3562,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002Freferences\u002Fapi-webui.md",{"path":131,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":132,"sourceHtmlUrl":133},"references\u002Farchitecture-runtime.md",4110,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002Freferences\u002Farchitecture-runtime.md",{"path":135,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":136,"sourceHtmlUrl":137},"references\u002Fdox-workflow.md",2838,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002Freferences\u002Fdox-workflow.md",{"path":139,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":140,"sourceHtmlUrl":141},"references\u002Fextensions.md",4635,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002Freferences\u002Fextensions.md",{"path":143,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":144,"sourceHtmlUrl":145},"references\u002Foperate-agent-zero.md",15562,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002Freferences\u002Foperate-agent-zero.md",{"path":147,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":148,"sourceHtmlUrl":149},"references\u002Fplugins-workflow.md",3820,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002Freferences\u002Fplugins-workflow.md",{"path":151,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":152,"sourceHtmlUrl":153},"references\u002Ftools.md",3166,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fagent-zero_skills\u002Fa0-development\u002Freferences\u002Ftools.md",[155,163,171,178,185,192],{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":162},"01M767791C1KRP2ZRW2Z73VZ5Q","system-lifecycle-designer","Universal architectural methodology for designing granular, atomic, and sub-atomic lifecycles and end-to-end workflows for single functionality integrations across any domain (daemons, batch jobs, request transactions, resource pools). Provides patterns for deterministic identity, pre-commit validation, differential reconciliation, sticky leasing, state machines, transactional persistence, and closed-loop feedback.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fmy_skills\u002Fsystem-lifecycle-designer\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":170},"01M748ABPN5F1FANHH6HKZQMXT","style-sampling","Make a new episode in a proven video style - Collage Explainer, Finance Explainer, Animated Science Explainer, 3D Brand Explainer, 3D True Crime - on the person's topic. Use for \"an episode of\", \"in the style of\", \"sample this style\", 「用这个风格做一集」. One video to copy is reverse-any-video.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fheygen-com_hyperframes\u002Fstyle-sampling\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":170},"01M748A59V04PKW4HA0XQ81FGP","reverse-any-video","Rebuild any video file as an editable HyperFrames project - motion graphics, talking heads, live action or AI-generated footage - checked against the original frame by frame. Use to reverse, recreate, remake, replicate or copy a video, or 「复刻这个视频」「照着这个视频做一个」.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fheygen-com_hyperframes\u002Freverse-any-video\u002FSKILL.md",[],[],{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":170},"01M7487T50P55CSXMWXZ0G9KRG","typescript-patterns","TypeScript patterns for strict, type-safe, maintainable code in modern TypeScript and JavaScript applications. Covers strict compiler configuration, type design, narrowing, discriminated unions, generics, async and error handling, module boundaries, dependency hygiene, and type-level testing. Use when writing or reviewing TypeScript or JavaScript code.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ftypescript-patterns\u002FSKILL.md",[],[],{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":191,"publishedAt":170},"01M7487ERZRGPC5NJ75077Y238","test-collaboration","Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing test registry or TESTS.md. Use for test inventory, test gap analysis, unit\u002Fintegration\u002Fcontract\u002FE2E\u002Fsmoke classification, bug-to-test regression protection, consumer\u002Fprovider contract testing, test-necessity review, and pre-delivery evidence review.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ftest-collaboration\u002FSKILL.md",[],[],{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":198,"publishedAt":170},"01M748721J3GKR2WS6K0QWFC35","story-lifecycle","Manage a file-based epic → story → sprint development loop without requiring an external project management tool. Creates and tracks epics, breaks them into user stories, assigns them to sprints, and drives implementation story by story. Use when starting a new feature initiative or when the team has no Jira\u002FLinear\u002FTaiga but needs structured delivery tracking.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fstory-lifecycle\u002FSKILL.md",[],[]]