[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MPB18AG6VFE37Z1130HGCA":3,"skill-same:01M6MPB18AG6VFE37Z1130HGCA":84},{"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":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6MPB18AG6VFE37Z1130HGCA","agents-md-improver",null,"Maintain AGENTS.md-based project instructions for tools that support AGENTS.md. Use for instruction audits, session learnings, AGENTS.md updates, or migrating useful CLAUDE.md rules into a shared instruction source. Not for general docs, code review, runtime debugging, or global memory unless asked.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyyykf\u002Fspellbook-skills\u002Fskills\u002Fagents-md-improver\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"agents md improver","agents md","general","useful","source","for","updates","runtime","project","shared","maintain","learnings","code review","use","session","Tools","code","debugging","support","memory","review","2026-11-10 10:12:30",false,"---\nname: agents-md-improver\ndescription: \"Maintain AGENTS.md-based project instructions for tools that support AGENTS.md. Use for instruction audits, session learnings, AGENTS.md updates, or migrating useful CLAUDE.md rules into a shared instruction source. Not for general docs, code review, runtime debugging, or global memory unless asked.\"\n---\n\n# AGENTS.md Improver\n\n## Overview\n\nMaintain concise project instructions for AGENTS.md-compatible tools such as Codex, Copilot, Cursor, and similar coding agents.\n\n**Core principle:** Find the effective instruction source -> extract durable learnings -> propose compact diffs -> apply approved changes only.\n\n**Announce at start:** \"I'm using the agents-md-improver skill to maintain concise AGENTS.md project instructions.\"\n\n## Prerequisites\n\n- A repository or workspace with `AGENTS.md`, nested `AGENTS.md`, or compatible instruction files.\n- A user request to audit, improve, revise, migrate, or capture learnings into project instructions.\n\n## Workflow\n\n### Phase 1: Identify Instruction Targets\n\nFind instruction files from the repository root:\n\n```bash\nfind . \\( -name \"AGENTS.md\" -o -name \"CLAUDE.md\" -o -name \".claude.local.md\" \\) 2>\u002Fdev\u002Fnull | head -50\n```\n\nUse these targeting rules:\n\n- `.\u002FAGENTS.md`: primary shared project instructions for AGENTS.md-compatible tools.\n- Nested `AGENTS.md`: module-specific instructions; update only when the learning applies to that subtree.\n- Include-only `AGENTS.md`: if it contains only an include such as `@.\u002FCLAUDE.md`, read the target and treat that target as the effective source. Update the target only when the repository intentionally shares one instruction file across tools.\n- `CLAUDE.md`: Claude Code-specific instructions, or a shared source when `AGENTS.md` intentionally points to it. Do not update it just because it exists.\n- `.claude.local.md`: personal Claude Code local notes. Do not create or edit it for shared AGENTS.md project memory.\n- User\u002Fglobal instruction files, such as `~\u002F.codex\u002FAGENTS.md`: update only when the user explicitly asks for global behavior.\n- `.project_context\u002F`: historical exploration, plans, and execution summaries. Use it for trace records, not agent steering instructions.\n\nIf no `AGENTS.md` exists, propose creating the narrowest useful one, usually `.\u002FAGENTS.md`.\n\n### Phase 2: Choose The Mode\n\nChoose exactly one primary mode before scanning or proposing edits:\n\n- **Repository Audit Mode:** use when the user asks whether instructions are stale, incomplete, inaccurate, outdated, or should be refreshed against the current repository. Then read [references\u002Frepository-audit.md](references\u002Frepository-audit.md).\n- **Session Learning Mode:** use when the user asks to capture this session's learnings, revise instructions from the current conversation, or preserve newly discovered repo-specific behavior. Then read [references\u002Fsession-learning.md](references\u002Fsession-learning.md).\n- **Migration Mode:** use when moving useful guidance from `CLAUDE.md` or another tool-specific instruction file into an AGENTS.md-compatible source. Reuse Session Learning Mode for extraction rules, but keep tool-only slash commands, hooks, or UI shortcuts in tool-specific files unless the user asks to make them shared.\n\n### Phase 3: Draft Compact Updates\n\n`AGENTS.md` is prompt context. Prefer dense, operational bullets.\n\nGood format:\n\n```markdown\n- Use `rg` for repo-wide search; fall back only if unavailable.\n- Run `pnpm test -- --runInBand` for flaky integration tests in this repo.\n- Keep API compatibility normalization in the service layer unless a spec explicitly changes request validation.\n```\n\nAvoid adding:\n\n- generic engineering advice;\n- one-off debugging details unlikely to recur;\n- unverified assumptions or stale guesses;\n- long explanations, logs, secrets, tokens, private URLs, or machine-specific credentials;\n- duplicates of existing instructions.\n\n### Phase 4: Propose Before Editing\n\nAlways show proposed changes before modifying files. Group proposals by target file.\n\nUse this format:\n\n````markdown\n### Update: .\u002FAGENTS.md\n\nWhy: \u003Cone-line reason this helps future agent sessions>\n\n```diff\n+ \u003Cconcise addition>\n```\n````\n\nIf multiple files could be updated, explain the placement tradeoff:\n\n- root `AGENTS.md` for project-wide behavior;\n- nested `AGENTS.md` for module-local behavior;\n- `.project_context\u002F` for historical records;\n- `CLAUDE.md` only for Claude Code-specific behavior or an intentional shared source.\n\nAsk for approval before editing. If the user already explicitly said to apply changes, proceed with the smallest safe patch.\n\n### Phase 5: Apply Carefully\n\nWhen approved:\n\n- use minimal patches and preserve the file's existing organization;\n- insert under an existing relevant heading when possible;\n- create a short new heading only if no suitable section exists;\n- do not reorder unrelated content;\n- do not remove or rewrite existing instructions unless the user asked for cleanup or the instruction is clearly obsolete;\n- after editing, re-read the changed section and report exactly what changed.\n\n## Common Mistakes\n\n- Treating `.project_context\u002F` as agent steering context. It is for traceability, not instructions that should load every session.\n- Updating `CLAUDE.md` for a shared AGENTS.md request when the repo does not intentionally share one source file.\n- Missing an include-only `AGENTS.md` and patching the wrapper instead of the effective source.\n- Capturing logs, secrets, private URLs, or one-off debugging notes as durable instructions.\n- Adding broad best practices that any competent agent already knows.\n\n## Output\n\nFor Repository Audit Mode, provide the quality report format from [references\u002Frepository-audit.md](references\u002Frepository-audit.md).\n\nFor Session Learning Mode or Migration Mode, provide:\n\n- files changed;\n- concise summary of additions;\n- any skipped proposals and why.\n\n## References\n\n- [repository-audit.md](references\u002Frepository-audit.md) - Repository scan scope, quality criteria, and report template for stale or incomplete instructions.\n- [session-learning.md](references\u002Fsession-learning.md) - Session learning extraction rules and concise update proposal template.\n","# AGENTS.md Improver\n\n## Overview\n\nMaintain concise project instructions for AGENTS.md-compatible tools such as Codex, Copilot, Cursor, and similar coding agents.\n\n**Core principle:** Find the effective instruction source -> extract durable learnings -> propose compact diffs -> apply approved changes only.\n\n**Announce at start:** \"I'm using the agents-md-improver skill to maintain concise AGENTS.md project instructions.\"\n\n## Prerequisites\n\n- A repository or workspace with `AGENTS.md`, nested `AGENTS.md`, or compatible instruction files.\n- A user request to audit, improve, revise, migrate, or capture learnings into project instructions.\n\n## Workflow\n\n### Phase 1: Identify Instruction Targets\n\nFind instruction files from the repository root:\n\n```bash\nfind . \\( -name \"AGENTS.md\" -o -name \"CLAUDE.md\" -o -name \".claude.local.md\" \\) 2>\u002Fdev\u002Fnull | head -50\n```\n\nUse these targeting rules:\n\n- `.\u002FAGENTS.md`: primary shared project instructions for AGENTS.md-compatible tools.\n- Nested `AGENTS.md`: module-specific instructions; update only when the learning applies to that subtree.\n- Include-only `AGENTS.md`: if it contains only an include such as `@.\u002FCLAUDE.md`, read the target and treat that target as the effective source. Update the target only when the repository intentionally shares one instruction file across tools.\n- `CLAUDE.md`: Claude Code-specific instructions, or a shared source when `AGENTS.md` intentionally points to it. Do not update it just because it exists.\n- `.claude.local.md`: personal Claude Code local notes. Do not create or edit it for shared AGENTS.md project memory.\n- User\u002Fglobal instruction files, such as `~\u002F.codex\u002FAGENTS.md`: update only when the user explicitly asks for global behavior.\n- `.project_context\u002F`: historical exploration, plans, and execution summaries. Use it for trace records, not agent steering instructions.\n\nIf no `AGENTS.md` exists, propose creating the narrowest useful one, usually `.\u002FAGENTS.md`.\n\n### Phase 2: Choose The Mode\n\nChoose exactly one primary mode before scanning or proposing edits:\n\n- **Repository Audit Mode:** use when the user asks whether instructions are stale, incomplete, inaccurate, outdated, or should be refreshed against the current repository. Then read [references\u002Frepository-audit.md](references\u002Frepository-audit.md).\n- **Session Learning Mode:** use when the user asks to capture this session's learnings, revise instructions from the current conversation, or preserve newly discovered repo-specific behavior. Then read [references\u002Fsession-learning.md](references\u002Fsession-learning.md).\n- **Migration Mode:** use when moving useful guidance from `CLAUDE.md` or another tool-specific instruction file into an AGENTS.md-compatible source. Reuse Session Learning Mode for extraction rules, but keep tool-only slash commands, hooks, or UI shortcuts in tool-specific files unless the user asks to make them shared.\n\n### Phase 3: Draft Compact Updates\n\n`AGENTS.md` is prompt context. Prefer dense, operational bullets.\n\nGood format:\n\n```markdown\n- Use `rg` for repo-wide search; fall back only if unavailable.\n- Run `pnpm test -- --runInBand` for flaky integration tests in this repo.\n- Keep API compatibility normalization in the service layer unless a spec explicitly changes request validation.\n```\n\nAvoid adding:\n\n- generic engineering advice;\n- one-off debugging details unlikely to recur;\n- unverified assumptions or stale guesses;\n- long explanations, logs, secrets, tokens, private URLs, or machine-specific credentials;\n- duplicates of existing instructions.\n\n### Phase 4: Propose Before Editing\n\nAlways show proposed changes before modifying files. Group proposals by target file.\n\nUse this format:\n\n````markdown\n### Update: .\u002FAGENTS.md\n\nWhy: \u003Cone-line reason this helps future agent sessions>\n\n```diff\n+ \u003Cconcise addition>\n```\n````\n\nIf multiple files could be updated, explain the placement tradeoff:\n\n- root `AGENTS.md` for project-wide behavior;\n- nested `AGENTS.md` for module-local behavior;\n- `.project_context\u002F` for historical records;\n- `CLAUDE.md` only for Claude Code-specific behavior or an intentional shared source.\n\nAsk for approval before editing. If the user already explicitly said to apply changes, proceed with the smallest safe patch.\n\n### Phase 5: Apply Carefully\n\nWhen approved:\n\n- use minimal patches and preserve the file's existing organization;\n- insert under an existing relevant heading when possible;\n- create a short new heading only if no suitable section exists;\n- do not reorder unrelated content;\n- do not remove or rewrite existing instructions unless the user asked for cleanup or the instruction is clearly obsolete;\n- after editing, re-read the changed section and report exactly what changed.\n\n## Common Mistakes\n\n- Treating `.project_context\u002F` as agent steering context. It is for traceability, not instructions that should load every session.\n- Updating `CLAUDE.md` for a shared AGENTS.md request when the repo does not intentionally share one source file.\n- Missing an include-only `AGENTS.md` and patching the wrapper instead of the effective source.\n- Capturing logs, secrets, private URLs, or one-off debugging notes as durable instructions.\n- Adding broad best practices that any competent agent already knows.\n\n## Output\n\nFor Repository Audit Mode, provide the quality report format from [references\u002Frepository-audit.md](references\u002Frepository-audit.md).\n\nFor Session Learning Mode or Migration Mode, provide:\n\n- files changed;\n- concise summary of additions;\n- any skipped proposals and why.\n\n## References\n\n- [repository-audit.md](references\u002Frepository-audit.md) - Repository scan scope, quality criteria, and report template for stale or incomplete instructions.\n- [session-learning.md](references\u002Fsession-learning.md) - Session learning extraction rules and concise update proposal template.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fyyykf\u002Fspellbook-skills\u002Fskills\u002Fagents-md-improver",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill agents-md-improver",{"tool":66,"command":67},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill agents-md-improver",{"tool":69,"command":70},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill agents-md-improver","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyyykf\u002Fspellbook-skills\u002Fskills\u002Fagents-md-improver\u002FSKILL.md",true,[74,80],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Frepository-audit.md","REFERENCE","参考文档",3949,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyyykf\u002Fspellbook-skills\u002Fskills\u002Fagents-md-improver\u002Freferences\u002Frepository-audit.md",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fsession-learning.md",1276,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyyykf\u002Fspellbook-skills\u002Fskills\u002Fagents-md-improver\u002Freferences\u002Fsession-learning.md",[85,95,103,111,119,127],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":94},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":99,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":94},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":94},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":94},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":123,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":94},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":131,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":94},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]