[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6D8G2AG07608KVGBTDS0A9G":3,"skill-same:01M6D8G2AG07608KVGBTDS0A9G":78},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":57,"updatedAt":58,"install":59,"resources":71},"01M6D8G2AG07608KVGBTDS0A9G","agents-md-authoring",null,"Create or revise repository `AGENTS.md` files using a progressive-disclosure, dispatcher-style structure. Use when an agent needs to author or edit a top-level or directory-local `AGENTS.md`, convert a long instruction file into task-oriented \"Start Here for ...\" sections, add a concise \"Must Follow\" section with Always\u002FNever rules, improve skill-discovery cues, or decide whether guidance belongs in root `AGENTS.md`, deeper docs, local `AGENTS.md`, or a repository-local skill.","jesse-black\u002Fdocgarden","jesse-black","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5840911?v=4","01M6D8G07TP5PJH5NHT9YJ8E1Y","Jesse Black","01M6D8G0C92CS19125JXMPEVSQ",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjesse-black\u002Fdocgarden\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagents-md-authoring\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"agents md authoring","authoring","agents md","decide","local","deeper","structure","task","files","never","use","directory","Rules","convert","improve","discovery","improve skill","file","dispatcher","create","2026-11-10 10:12:30",false,"---\nname: agents-md-authoring\ndescription: Create or revise repository `AGENTS.md` files using a progressive-disclosure, dispatcher-style structure. Use when an agent needs to author or edit a top-level or directory-local `AGENTS.md`, convert a long instruction file into task-oriented \"Start Here for ...\" sections, add a concise \"Must Follow\" section with Always\u002FNever rules, improve skill-discovery cues, or decide whether guidance belongs in root `AGENTS.md`, deeper docs, local `AGENTS.md`, or a repository-local skill.\nmetadata:\n  internal: true\n---\n\n# AGENTS.md Authoring\n\nUse `AGENTS.md` as a routing layer, not as the full knowledge base.\n\nPrefer short, stable guidance that helps an agent decide what to read next. Move long procedures, rationale, and subsystem-specific detail into `docs\u002F`, directory-local `AGENTS.md` files, or repository-local skills.\n\n## Workflow\n\n### 1. Establish scope\n\nDetermine whether the file being edited is:\n\n- a root `AGENTS.md` that should act as the repository dispatcher,\n- a directory-local `AGENTS.md` that should govern one subsystem,\n- or both as part of a broader restructuring.\n\nRead the existing `AGENTS.md` plus the nearby knowledge sources it points to before rewriting structure. For a root file, also inspect the repository map and existing docs layout so the file points to real sources of truth.\n\n### 2. Preserve progressive disclosure\n\nKeep the always-loaded layer small.\n\nFor a root `AGENTS.md`:\n\n- Prefer a short `Must Follow` section containing only repo-wide invariants.\n- Prefer grouped `Repository Map` sections such as `Start Here for Architecture and Implementation`, `Start Here for Testing`, or `Start Here for Skills and Specialist Workflows`.\n- Prefer routing language that tells the agent where to go next.\n\nDo not turn the root file into a long playbook. If guidance needs detailed explanation, examples, rationale, or maintenance-heavy instructions, move it into `docs\u002F` and leave a short pointer in `AGENTS.md`.\n\n### 3. Use strict placement rules\n\nPlace guidance according to scope:\n\n- Put it in root `AGENTS.md` if nearly every task benefits from seeing it early and it can stay short and stable.\n- Put it in a directory-local `AGENTS.md` if it applies mainly inside one subsystem such as `api\u002F`, `web\u002F`, or `terraform\u002F`.\n- Put it in `docs\u002F` if it needs long-form explanation, reference material, rationale, or examples.\n- Put it in a repository-local skill if it describes a reusable specialist workflow with clear triggers and validation steps.\n\nWhen in doubt, keep maps near the top and playbooks deeper down.\n\n### 4. Make retrieval cues explicit\n\nDo not assume an agent will infer when a deeper document or skill applies.\n\nAdd short trigger cues such as:\n\n- what kind of task should send the agent to `docs\u002FTESTING.md`,\n- when a directory-local `AGENTS.md` must be loaded,\n- when repository-local skills should be inspected,\n- and how likely user phrases map to internal skill names.\n\nPrefer one-line retrieval cues over embedding the whole workflow.\n\n### 5. Write enforceable invariants\n\nIf a `Must Follow` section exists, keep it short and make every line an `ALWAYS` or `NEVER`.\n\nOnly include instructions that are:\n\n- repo-wide,\n- stable,\n- high-cost to miss,\n- and actionable without extra interpretation.\n\nDo not put local conventions or fragile implementation details in `Must Follow`.\n\n### 6. Keep the file easy to scan\n\nPrefer compact sections, direct file references, and task-shaped grouping.\n\nGood root-file pattern:\n\n- `## Must Follow`\n- `## Repository Map`\n- `### Start Here for ...`\n\nAvoid large prose blocks, mixed abstraction levels, and long bullet lists with weak prioritization.\n\n## Editing Patterns\n\n### Converting a long root file\n\nIf the existing root `AGENTS.md` mixes routing, detailed workflow instructions, and subsystem rules:\n\n1. Extract the true repo-wide invariants into `Must Follow`.\n2. Group the remaining routing pointers under `Start Here for ...` headings.\n3. Remove or relocate long procedures into `docs\u002F`, local `AGENTS.md`, or skills.\n4. Leave short pointers behind so the deeper guidance remains discoverable.\n\n### Adding skill discoverability\n\nWhen a repository uses local skills, ensure the root file makes them findable without expanding into skill procedure.\n\nGood pattern:\n\n- point to the skill,\n- mention the categories of specialist workflows covered,\n- and include short alias mapping when a likely user phrase differs from the skill folder name.\n\n### Editing directory-local `AGENTS.md`\n\nFor directory-local files, bias toward:\n\n- working-directory expectations,\n- local commands,\n- subsystem file maps,\n- testing commands,\n- and implementation patterns specific to that directory.\n\nDo not duplicate broad repository guidance unless it is truly required in local context.\n\n## Quality Bar\n\nA good `AGENTS.md` should let an agent answer these questions quickly:\n\n- What kind of task is this?\n- Which source should I read next?\n- Which instructions are mandatory?\n- What guidance belongs here versus somewhere deeper?\n\nIf the file feels like an encyclopedia, it is probably too large. If it fails to tell the agent where to go next, it is probably too small or too vague.\n","# AGENTS.md Authoring\n\nUse `AGENTS.md` as a routing layer, not as the full knowledge base.\n\nPrefer short, stable guidance that helps an agent decide what to read next. Move long procedures, rationale, and subsystem-specific detail into `docs\u002F`, directory-local `AGENTS.md` files, or repository-local skills.\n\n## Workflow\n\n### 1. Establish scope\n\nDetermine whether the file being edited is:\n\n- a root `AGENTS.md` that should act as the repository dispatcher,\n- a directory-local `AGENTS.md` that should govern one subsystem,\n- or both as part of a broader restructuring.\n\nRead the existing `AGENTS.md` plus the nearby knowledge sources it points to before rewriting structure. For a root file, also inspect the repository map and existing docs layout so the file points to real sources of truth.\n\n### 2. Preserve progressive disclosure\n\nKeep the always-loaded layer small.\n\nFor a root `AGENTS.md`:\n\n- Prefer a short `Must Follow` section containing only repo-wide invariants.\n- Prefer grouped `Repository Map` sections such as `Start Here for Architecture and Implementation`, `Start Here for Testing`, or `Start Here for Skills and Specialist Workflows`.\n- Prefer routing language that tells the agent where to go next.\n\nDo not turn the root file into a long playbook. If guidance needs detailed explanation, examples, rationale, or maintenance-heavy instructions, move it into `docs\u002F` and leave a short pointer in `AGENTS.md`.\n\n### 3. Use strict placement rules\n\nPlace guidance according to scope:\n\n- Put it in root `AGENTS.md` if nearly every task benefits from seeing it early and it can stay short and stable.\n- Put it in a directory-local `AGENTS.md` if it applies mainly inside one subsystem such as `api\u002F`, `web\u002F`, or `terraform\u002F`.\n- Put it in `docs\u002F` if it needs long-form explanation, reference material, rationale, or examples.\n- Put it in a repository-local skill if it describes a reusable specialist workflow with clear triggers and validation steps.\n\nWhen in doubt, keep maps near the top and playbooks deeper down.\n\n### 4. Make retrieval cues explicit\n\nDo not assume an agent will infer when a deeper document or skill applies.\n\nAdd short trigger cues such as:\n\n- what kind of task should send the agent to `docs\u002FTESTING.md`,\n- when a directory-local `AGENTS.md` must be loaded,\n- when repository-local skills should be inspected,\n- and how likely user phrases map to internal skill names.\n\nPrefer one-line retrieval cues over embedding the whole workflow.\n\n### 5. Write enforceable invariants\n\nIf a `Must Follow` section exists, keep it short and make every line an `ALWAYS` or `NEVER`.\n\nOnly include instructions that are:\n\n- repo-wide,\n- stable,\n- high-cost to miss,\n- and actionable without extra interpretation.\n\nDo not put local conventions or fragile implementation details in `Must Follow`.\n\n### 6. Keep the file easy to scan\n\nPrefer compact sections, direct file references, and task-shaped grouping.\n\nGood root-file pattern:\n\n- `## Must Follow`\n- `## Repository Map`\n- `### Start Here for ...`\n\nAvoid large prose blocks, mixed abstraction levels, and long bullet lists with weak prioritization.\n\n## Editing Patterns\n\n### Converting a long root file\n\nIf the existing root `AGENTS.md` mixes routing, detailed workflow instructions, and subsystem rules:\n\n1. Extract the true repo-wide invariants into `Must Follow`.\n2. Group the remaining routing pointers under `Start Here for ...` headings.\n3. Remove or relocate long procedures into `docs\u002F`, local `AGENTS.md`, or skills.\n4. Leave short pointers behind so the deeper guidance remains discoverable.\n\n### Adding skill discoverability\n\nWhen a repository uses local skills, ensure the root file makes them findable without expanding into skill procedure.\n\nGood pattern:\n\n- point to the skill,\n- mention the categories of specialist workflows covered,\n- and include short alias mapping when a likely user phrase differs from the skill folder name.\n\n### Editing directory-local `AGENTS.md`\n\nFor directory-local files, bias toward:\n\n- working-directory expectations,\n- local commands,\n- subsystem file maps,\n- testing commands,\n- and implementation patterns specific to that directory.\n\nDo not duplicate broad repository guidance unless it is truly required in local context.\n\n## Quality Bar\n\nA good `AGENTS.md` should let an agent answer these questions quickly:\n\n- What kind of task is this?\n- Which source should I read next?\n- Which instructions are mandatory?\n- What guidance belongs here versus somewhere deeper?\n\nIf the file feels like an encyclopedia, it is probably too large. If it fails to tell the agent where to go next, it is probably too small or too vague.\n",{"name":5,"metadata":49,"description":7},{"internal":50},true,"main","a3937e6e80074000b5213e737409f99f6a8443e2",".agents\u002Fskills\u002Fagents-md-authoring",0,"https:\u002F\u002Fgithub.com\u002Fjesse-black\u002Fdocgarden","https:\u002F\u002Fgithub.com\u002Fjesse-black","Building the accessible communication tool I wish I'd had sooner.","2026-07-22 22:14:44",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":50},[61,64,67],{"tool":62,"command":63},"npx","npx skills add jesse-black\u002Fdocgarden --skill agents-md-authoring",{"tool":65,"command":66},"bunx","bunx skills add jesse-black\u002Fdocgarden --skill agents-md-authoring",{"tool":68,"command":69},"pnpm","pnpm dlx skills add jesse-black\u002Fdocgarden --skill agents-md-authoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjesse-black\u002Fdocgarden\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagents-md-authoring\u002FSKILL.md",[72],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"agents\u002Fopenai.yaml","REFERENCE","参考文档",291,"https:\u002F\u002Fgithub.com\u002Fjesse-black\u002Fdocgarden\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagents-md-authoring\u002Fagents\u002Fopenai.yaml",[79,90,98,118,133,146],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":86,"publishedAt":44},"01M6D8H0WMA0PYJXE10H076KB3","Skill Beacon","skillbeacon metadata for scoped skill discovery.","https:\u002F\u002Fgithub.com\u002Fjesse-black\u002Fdocgarden\u002Fblob\u002Fmain\u002Ftests\u002Fdiscovery-repo\u002F.agents\u002Fskills\u002Fskillbeacon\u002FSKILL.md",[85],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[81,87,39,88,89],"beacon","skill discovery","metadata",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":44},"01M6D8GXTTDAG9V9M5W1QCWSCK","Build Beacon","buildbeacon metadata for scoped skill discovery.","https:\u002F\u002Fgithub.com\u002Fjesse-black\u002Fdocgarden\u002Fblob\u002Fmain\u002Ftests\u002Fdiscovery-repo\u002F.agents\u002Fskills\u002Fimplement\u002FSKILL.md",[],[87,97,92,88,89,39],"build",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":107,"publishedAt":44},"01M6D8GSWPXC04681NY3XA9BKB","description-frontmatter-authoring","Create or revise Markdown `description` frontmatter so `docgarden match` routes agents to the right repository documents. Use when adding a new routed Markdown document, updating existing frontmatter, fixing noisy or missing match results, tuning skills or docs discovery, or making descriptions more query-aligned without loading document bodies.","https:\u002F\u002Fgithub.com\u002Fjesse-black\u002Fdocgarden\u002Fblob\u002Fmain\u002Fskills\u002Fdescription-frontmatter-authoring\u002FSKILL.md",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",[25,108,109,110,43,111,112,39,113,114,34,115,116,117],"description frontmatter authoring","docs","documents","repository","tuning","markdown","results","document","query","revise",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":44},"01M6D8GPRP006YE31GRYKDRYCP","planner-execplan","Create, update, revise, reopen, or rescope a plan or ExecPlan using `PLANS.md`. Use when an agent needs to create a plan, plan a change, update the plan with new requirements, or rewrite an active ExecPlan.","https:\u002F\u002Fgithub.com\u002Fjesse-black\u002Fdocgarden\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fplanner-execplan\u002FSKILL.md",[],[125,126,117,127,128,43,129,130,34,131,132],"planner execplan","planner","plans","change","update","plan","active","requirements",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":44},"01M6D8GKJJ1867WVATETQF36AR","generator-execplan","Implement from an active plan or ExecPlan while keeping it up to date. Use when an agent needs to implement the active plan, continue plan-driven work, resume the current plan, or carry out an existing ExecPlan.","https:\u002F\u002Fgithub.com\u002Fjesse-black\u002Fdocgarden\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgenerator-execplan\u002FSKILL.md",[],[140,141,142,130,143,34,144,145,131],"generator execplan","work","implement","continue","up","resume",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":155,"publishedAt":44},"01M6D8GG5PKA3X8VAS35CRWHKH","evaluator-execplan","Review the current branch, PR, or worktree against the plan or ExecPlan and record findings. Use when an agent needs a code review with findings for changes associated with an active plan.","https:\u002F\u002Fgithub.com\u002Fjesse-black\u002Fdocgarden\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fevaluator-execplan\u002FSKILL.md",[152],{"categoryNo":153,"categoryName":154,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",[156,157,158,159,160,130,161,34,162,131,163],"evaluator execplan","review","pr","code","worktree","branch","record","code review"]