[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MGNK83PH4HD93DKFQRQBFR":3,"skill-same:01M6MGNK83PH4HD93DKFQRQBFR":79},{"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":28,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M6MGNK83PH4HD93DKFQRQBFR","create-agent-onboarding",null,"Use when a repo has no AGENTS.md and an AI coding agent needs onboarding context, or the user asks to generate onboarding files. Produces AGENTS.md (cross-agent), a CLAUDE.md wrapper, and the .aiboarding lifecycle (state, config, hooks). Fallback target when the session-start hook reports missing onboarding files.","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\u002Fgustavo-meilus\u002Faiboarding\u002Fskills\u002Fcreate-agent-onboarding\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"create agent","create","create agent onboarding","onboarding","when","coding agent","hook","missing","fallback","files","reports","Wrapper","hooks","session","context","repo","coding","lifecycle","start","generate","config","2026-11-10 10:12:30",false,"---\nname: create-agent-onboarding\ndescription: Use when a repo has no AGENTS.md and an AI coding agent needs onboarding context, or the user asks to generate onboarding files. Produces AGENTS.md (cross-agent), a CLAUDE.md wrapper, and the .aiboarding lifecycle (state, config, hooks). Fallback target when the session-start hook reports missing onboarding files.\n---\n\n# Creating agent onboarding files\n\nTreat the AI as a fresh engineer. Generate a compressed, high-signal `AGENTS.md`\nat the repo root - the canonical, tool-agnostic onboarding document read natively\nby Codex, Copilot, Cursor and imported by Claude Code via a thin `CLAUDE.md`\nwrapper - then bootstrap the lifecycle that keeps it current.\n\n**Announce at start:** \"Using create-agent-onboarding to generate this repo's onboarding files.\"\n\n## Runtime awareness\nThe generation phases below are tool-agnostic and work under Claude Code, Codex,\nCopilot CLI, or any SKILL.md-compatible agent. Phase 6 installs repo-local hooks\nonly for Claude Code. The Codex plugin supplies optional native hooks after `\u002Fhooks`\ntrust review; copied standalone skills never install Codex settings. When hooks are\ndisabled, unavailable, or untrusted, run `update-agent-onboarding` manually after\nmeaningful commits.\n\n## Phase 0: Pre-flight routing\nInspect the repo root before generating anything:\n- **`AIBOARDING.md` exists (legacy v1 layout):** stop and run `migrate-aiboarding`\n  instead - never regenerate from scratch over an existing onboarding investment.\n- **`AGENTS.md` already exists:** treat it as primary input. Skip greenfield\n  grilling; interrogate only the gaps against the section schema below, then\n  propose a restructure as an approval-gated diff. Never overwrite silently.\n- **`CLAUDE.md` already exists:** preserve it. The only changes allowed are adding\n  the `@AGENTS.md` import line and managing an aiboarding-owned block via\n  `.aiboarding\u002Ftools\u002Finject-fenced` (marker-fenced, idempotent, removable).\n\n## Shared contracts\n**`AGENTS.md` schema** - tool-agnostic, no frontmatter, no Claude-specific syntax.\nH2 sections in this exact order:\n1. `## Project Purpose`\n2. `## Stack and Runtime`\n3. `## Build, Test, Run` - exact commands; fast checks and full checks\n4. `## Architecture Map` - directories, boundaries, data flow, dependency direction\n5. `## Domain Model` - entities, workflows, invariants, vocabulary\n6. `## Agent Guardrails` - what agents must NOT assume\u002Frefactor\u002Fdelete\u002Frename\u002F\"simplify\"\n7. `## Known Failure Modes` - mistakes previous agents made or will likely make\n8. `## Verification Before Completion` - commands agents must run before claiming done\n9. `## Escalation - Ask the User When` - stop-and-ask cases\n\nBacktick-quote every command, identifier, file path, and error string - the\ncompression byte-preservation checker treats backtick spans as protected.\n\n**`CLAUDE.md` wrapper** - first line `@AGENTS.md`, then an aiboarding-fenced block\nof Claude-only workflow notes. Never duplicate `AGENTS.md` content: imports expand\ninto context at launch, so duplication doubles token cost for zero benefit.\n\n**`.aiboarding\u002Fstate.json`** - operational state, one top-level key per line\n(hooks read it with a line scanner, not a JSON parser):\n```json\n{\n  \"aiboarding_version\": 2,\n  \"canonical_file\": \"AGENTS.md\",\n  \"claude_wrapper\": \"CLAUDE.md\",\n  \"generated\": \"YYYY-MM-DD\",\n  \"last_synced_commit\": \"\u003Cgit rev-parse HEAD>\",\n  \"last_drift_classification\": {},\n  \"receipts\": [\n  ]\n}\n```\nState is committed. Advancing `last_synced_commit` must never modify `AGENTS.md`\nor `CLAUDE.md` - that separation is what prevents self-referential drift loops.\n\n## Phase 1: Background crawl + initial grilling\nRun two tracks. A single agent cannot truly act in parallel: perform Track A's file\nreads first and hold the findings, then immediately open Track B and keep grilling.\n\n**Track A - automated discovery (no user input):** read dependency manifests\n(`package.json`, `pyproject.toml`, `go.mod`, `Cargo.toml`, etc.), the directory\nstructure, CI configs, and any README\u002Fdocs. Extract tech stack, build\u002Ftest\u002Frun\ncommands, and standard engineering basics. Hold these findings for Phase 3.\n\n**Track B - grilling interrogation:** open with:\n> \"I'm scanning your codebase structure in the background for the tech stack. While I\n> do that: what is the core business problem this project solves?\"\nThen walk the conceptual tree **one question at a time**, challenging vague answers and\nincentivizing a targeted brain-dump per micro-topic. Do not batch questions.\n\n## Phase 2: Architectural & AI context\nSteer the grilling toward architecture and AI-specific guardrails. Extract constraints\nand known AI failure modes, e.g.:\n> \"You mentioned a custom Auth provider. What are the architectural gotchas or AI\n> failure modes around it that a future sub-agent must not trip over?\"\nAlso cover the two sections agents skip most: what must be verified before claiming\nwork done (`Verification Before Completion`) and which situations demand stopping to\nask the user (`Escalation`). Continue until you have at least one architectural\nconstraint, one AI-specific failure mode or guardrail, one verification command, and\none escalation case.\n\n## Phase 3: Reconciliation & gap analysis\n**HARD GATE - do not start until BOTH Track A (crawl) and Track B (grilling) are\ncomplete.** Cross-examine Track A findings against Track B answers. Run a short, final\ngrilling pass focused only on discrepancies, e.g.:\n> \"The crawl found a Postgres connection string, but you didn't mention a database. How\n> does Postgres fit the core domain, and are there AI constraints here?\"\n\n## Phase 4: Synthesis & generation\nWhen the reconciliation pass is complete and no open discrepancies remain, combine\nverified Track A findings with reconciled Track B domain knowledge. Draft `AGENTS.md`\nagainst the schema above. Nothing Claude-specific goes in it; Claude-only workflow\nnotes belong in the `CLAUDE.md` wrapper block.\n\n## Phase 5: Token compression\nCompress the draft by following the `compress-onboarding` skill: level from\n`config.json` (`compression_level`, default `full`), high-consequence preservation\nand any per-region opt-in handled only by that skill, byte-preservation verified with\n`.aiboarding\u002Ftools\u002Fcheck-preservation`, receipt appended to `state.json`. Present the\ncompressed document to the user for approval before writing it to the repo root.\n\n## Phase 6: Install & bootstrap\nAfter the document is approved and written, install the lifecycle with your own file\ntools (no shell installer), for cross-platform safety. Every step is idempotent  - \nrunning create twice must not duplicate hooks, settings entries, or fenced blocks.\n\n1. **Locate the templates** at `\u003Cplugin-root>\u002Ftemplates\u002F`, where `\u003Cplugin-root>` is\n   two levels up from this skill. Use `${CLAUDE_PLUGIN_ROOT}\u002Ftemplates` if set;\n   otherwise resolve relative to this skill's own directory.\n2. **Write `CLAUDE.md`**: line one `@AGENTS.md`, then the Claude-notes block via\n   `inject-fenced \u003Crepo>\u002FCLAUDE.md claude-notes \u003Cnotes-file>`. If `CLAUDE.md` exists,\n   only add the import line (if absent) and the fenced block.\n3. **Write config**: copy `templates\u002Fstate\u002Fconfig.json` to\n   `\u003Crepo>\u002F.aiboarding\u002Fconfig.json` (keep an existing config) and\n   `templates\u002Fstate\u002Fdot-gitignore` to `\u003Crepo>\u002F.aiboarding\u002F.gitignore`. Defer the\n   initial `state.json` pointer until the Phase 7 validation record is persisted.\n4. **Copy hook scripts** *(Claude Code runtimes only)*: create\n   `\u003Crepo>\u002F.aiboarding\u002Fhooks\u002F` and copy these six files from\n   `\u003Cplugin-root>\u002Ftemplates\u002Fhooks\u002F` verbatim: `run-hook.cmd`, `_lib`, `session-start`,\n   `subagent-start`, `drift-check`, `instructions-loaded`.\n5. **Copy tools**: create `\u003Crepo>\u002F.aiboarding\u002Ftools\u002F` and copy `inject-fenced`,\n   `check-size-budget`, `check-preservation`, `classify-drift`, and\n   `lifecycle-decision`, `audit-onboarding-evidence`, `verify-onboarding-mutations`, and `write-evidence`. Installed tools must\n   byte-match their `templates\u002Ftools\u002F` sources.\n   Evidence is created lazily; inspect it directly at\n   `.aiboarding\u002Fevidence\u002Fv1\u002F` by matching a record's `repository.head`, `type`, and\n   `outcome`—never add it to `state.json` or onboarding files.\n6. **Merge settings** *(Claude Code runtimes only)*: merge the `hooks` block of\n   `\u003Cplugin-root>\u002Ftemplates\u002Fsettings\u002Fhooks.json` into `\u003Crepo>\u002F.claude\u002Fsettings.json`,\n   per top-level event. Before adding an entry, check for an existing aiboarding entry\n   for that event (a `command` containing `.aiboarding\u002Fhooks\u002Frun-hook.cmd`) and replace\n   it in place. **Remove** stale entries pointing at the retired `pre-task` and\n   `post-commit` hooks, and delete those files from `\u003Crepo>\u002F.aiboarding\u002Fhooks\u002F` if\n   present.\n\n## Phase 7: Validation gate (blocking)\nDo not report success until every check passes; fix and re-check instead of skipping:\n1. `AGENTS.md` and `CLAUDE.md` exist; `CLAUDE.md` contains a line `@AGENTS.md`.\n2. No content duplication: the Claude-notes block must not restate `AGENTS.md` sections.\n3. `.aiboarding\u002Ftools\u002Fcheck-size-budget AGENTS.md` passes as a local sensor (no FAIL;\n   resolve WARNs or get the user's explicit OK), and\n   `.aiboarding\u002Ftools\u002Faudit-onboarding-evidence \u003Crepo-root>` reports no Codex\n   project-chain failure.\n4. Every command quoted in `Build, Test, Run` and `Verification Before Completion`\n   resolves against the repo (package scripts, Makefile targets, CI workflows, or a\n   binary on PATH).\n5. `state.json:last_synced_commit` equals `git rev-parse HEAD`.\n6. On Claude Code: the settings merge contains exactly one aiboarding entry per event\n   and no `pre-task`\u002F`post-commit` references.\n\nAfter every required validator passes, write one compact `onboarding-validation`\nrecord with validator identities and repository-relative subjects using\n`.aiboarding\u002Ftools\u002Fwrite-evidence`; do not retain raw output. Recheck `HEAD`, then\nwrite the initial `state.json` with that exact `last_synced_commit`. If validation,\nevidence writing, or the head recheck fails, do not create or advance canonical state.\n\nThen report which files were created or updated and which hook entries were installed.\nOn Windows without Git Bash, tell the user once: hooks will not fire (`run-hook.cmd`\ndegrades silently), but native `CLAUDE.md`\u002F`AGENTS.md` loading still works.\n","# Creating agent onboarding files\n\nTreat the AI as a fresh engineer. Generate a compressed, high-signal `AGENTS.md`\nat the repo root - the canonical, tool-agnostic onboarding document read natively\nby Codex, Copilot, Cursor and imported by Claude Code via a thin `CLAUDE.md`\nwrapper - then bootstrap the lifecycle that keeps it current.\n\n**Announce at start:** \"Using create-agent-onboarding to generate this repo's onboarding files.\"\n\n## Runtime awareness\nThe generation phases below are tool-agnostic and work under Claude Code, Codex,\nCopilot CLI, or any SKILL.md-compatible agent. Phase 6 installs repo-local hooks\nonly for Claude Code. The Codex plugin supplies optional native hooks after `\u002Fhooks`\ntrust review; copied standalone skills never install Codex settings. When hooks are\ndisabled, unavailable, or untrusted, run `update-agent-onboarding` manually after\nmeaningful commits.\n\n## Phase 0: Pre-flight routing\nInspect the repo root before generating anything:\n- **`AIBOARDING.md` exists (legacy v1 layout):** stop and run `migrate-aiboarding`\n  instead - never regenerate from scratch over an existing onboarding investment.\n- **`AGENTS.md` already exists:** treat it as primary input. Skip greenfield\n  grilling; interrogate only the gaps against the section schema below, then\n  propose a restructure as an approval-gated diff. Never overwrite silently.\n- **`CLAUDE.md` already exists:** preserve it. The only changes allowed are adding\n  the `@AGENTS.md` import line and managing an aiboarding-owned block via\n  `.aiboarding\u002Ftools\u002Finject-fenced` (marker-fenced, idempotent, removable).\n\n## Shared contracts\n**`AGENTS.md` schema** - tool-agnostic, no frontmatter, no Claude-specific syntax.\nH2 sections in this exact order:\n1. `## Project Purpose`\n2. `## Stack and Runtime`\n3. `## Build, Test, Run` - exact commands; fast checks and full checks\n4. `## Architecture Map` - directories, boundaries, data flow, dependency direction\n5. `## Domain Model` - entities, workflows, invariants, vocabulary\n6. `## Agent Guardrails` - what agents must NOT assume\u002Frefactor\u002Fdelete\u002Frename\u002F\"simplify\"\n7. `## Known Failure Modes` - mistakes previous agents made or will likely make\n8. `## Verification Before Completion` - commands agents must run before claiming done\n9. `## Escalation - Ask the User When` - stop-and-ask cases\n\nBacktick-quote every command, identifier, file path, and error string - the\ncompression byte-preservation checker treats backtick spans as protected.\n\n**`CLAUDE.md` wrapper** - first line `@AGENTS.md`, then an aiboarding-fenced block\nof Claude-only workflow notes. Never duplicate `AGENTS.md` content: imports expand\ninto context at launch, so duplication doubles token cost for zero benefit.\n\n**`.aiboarding\u002Fstate.json`** - operational state, one top-level key per line\n(hooks read it with a line scanner, not a JSON parser):\n```json\n{\n  \"aiboarding_version\": 2,\n  \"canonical_file\": \"AGENTS.md\",\n  \"claude_wrapper\": \"CLAUDE.md\",\n  \"generated\": \"YYYY-MM-DD\",\n  \"last_synced_commit\": \"\u003Cgit rev-parse HEAD>\",\n  \"last_drift_classification\": {},\n  \"receipts\": [\n  ]\n}\n```\nState is committed. Advancing `last_synced_commit` must never modify `AGENTS.md`\nor `CLAUDE.md` - that separation is what prevents self-referential drift loops.\n\n## Phase 1: Background crawl + initial grilling\nRun two tracks. A single agent cannot truly act in parallel: perform Track A's file\nreads first and hold the findings, then immediately open Track B and keep grilling.\n\n**Track A - automated discovery (no user input):** read dependency manifests\n(`package.json`, `pyproject.toml`, `go.mod`, `Cargo.toml`, etc.), the directory\nstructure, CI configs, and any README\u002Fdocs. Extract tech stack, build\u002Ftest\u002Frun\ncommands, and standard engineering basics. Hold these findings for Phase 3.\n\n**Track B - grilling interrogation:** open with:\n> \"I'm scanning your codebase structure in the background for the tech stack. While I\n> do that: what is the core business problem this project solves?\"\nThen walk the conceptual tree **one question at a time**, challenging vague answers and\nincentivizing a targeted brain-dump per micro-topic. Do not batch questions.\n\n## Phase 2: Architectural & AI context\nSteer the grilling toward architecture and AI-specific guardrails. Extract constraints\nand known AI failure modes, e.g.:\n> \"You mentioned a custom Auth provider. What are the architectural gotchas or AI\n> failure modes around it that a future sub-agent must not trip over?\"\nAlso cover the two sections agents skip most: what must be verified before claiming\nwork done (`Verification Before Completion`) and which situations demand stopping to\nask the user (`Escalation`). Continue until you have at least one architectural\nconstraint, one AI-specific failure mode or guardrail, one verification command, and\none escalation case.\n\n## Phase 3: Reconciliation & gap analysis\n**HARD GATE - do not start until BOTH Track A (crawl) and Track B (grilling) are\ncomplete.** Cross-examine Track A findings against Track B answers. Run a short, final\ngrilling pass focused only on discrepancies, e.g.:\n> \"The crawl found a Postgres connection string, but you didn't mention a database. How\n> does Postgres fit the core domain, and are there AI constraints here?\"\n\n## Phase 4: Synthesis & generation\nWhen the reconciliation pass is complete and no open discrepancies remain, combine\nverified Track A findings with reconciled Track B domain knowledge. Draft `AGENTS.md`\nagainst the schema above. Nothing Claude-specific goes in it; Claude-only workflow\nnotes belong in the `CLAUDE.md` wrapper block.\n\n## Phase 5: Token compression\nCompress the draft by following the `compress-onboarding` skill: level from\n`config.json` (`compression_level`, default `full`), high-consequence preservation\nand any per-region opt-in handled only by that skill, byte-preservation verified with\n`.aiboarding\u002Ftools\u002Fcheck-preservation`, receipt appended to `state.json`. Present the\ncompressed document to the user for approval before writing it to the repo root.\n\n## Phase 6: Install & bootstrap\nAfter the document is approved and written, install the lifecycle with your own file\ntools (no shell installer), for cross-platform safety. Every step is idempotent  - \nrunning create twice must not duplicate hooks, settings entries, or fenced blocks.\n\n1. **Locate the templates** at `\u003Cplugin-root>\u002Ftemplates\u002F`, where `\u003Cplugin-root>` is\n   two levels up from this skill. Use `${CLAUDE_PLUGIN_ROOT}\u002Ftemplates` if set;\n   otherwise resolve relative to this skill's own directory.\n2. **Write `CLAUDE.md`**: line one `@AGENTS.md`, then the Claude-notes block via\n   `inject-fenced \u003Crepo>\u002FCLAUDE.md claude-notes \u003Cnotes-file>`. If `CLAUDE.md` exists,\n   only add the import line (if absent) and the fenced block.\n3. **Write config**: copy `templates\u002Fstate\u002Fconfig.json` to\n   `\u003Crepo>\u002F.aiboarding\u002Fconfig.json` (keep an existing config) and\n   `templates\u002Fstate\u002Fdot-gitignore` to `\u003Crepo>\u002F.aiboarding\u002F.gitignore`. Defer the\n   initial `state.json` pointer until the Phase 7 validation record is persisted.\n4. **Copy hook scripts** *(Claude Code runtimes only)*: create\n   `\u003Crepo>\u002F.aiboarding\u002Fhooks\u002F` and copy these six files from\n   `\u003Cplugin-root>\u002Ftemplates\u002Fhooks\u002F` verbatim: `run-hook.cmd`, `_lib`, `session-start`,\n   `subagent-start`, `drift-check`, `instructions-loaded`.\n5. **Copy tools**: create `\u003Crepo>\u002F.aiboarding\u002Ftools\u002F` and copy `inject-fenced`,\n   `check-size-budget`, `check-preservation`, `classify-drift`, and\n   `lifecycle-decision`, `audit-onboarding-evidence`, `verify-onboarding-mutations`, and `write-evidence`. Installed tools must\n   byte-match their `templates\u002Ftools\u002F` sources.\n   Evidence is created lazily; inspect it directly at\n   `.aiboarding\u002Fevidence\u002Fv1\u002F` by matching a record's `repository.head`, `type`, and\n   `outcome`—never add it to `state.json` or onboarding files.\n6. **Merge settings** *(Claude Code runtimes only)*: merge the `hooks` block of\n   `\u003Cplugin-root>\u002Ftemplates\u002Fsettings\u002Fhooks.json` into `\u003Crepo>\u002F.claude\u002Fsettings.json`,\n   per top-level event. Before adding an entry, check for an existing aiboarding entry\n   for that event (a `command` containing `.aiboarding\u002Fhooks\u002Frun-hook.cmd`) and replace\n   it in place. **Remove** stale entries pointing at the retired `pre-task` and\n   `post-commit` hooks, and delete those files from `\u003Crepo>\u002F.aiboarding\u002Fhooks\u002F` if\n   present.\n\n## Phase 7: Validation gate (blocking)\nDo not report success until every check passes; fix and re-check instead of skipping:\n1. `AGENTS.md` and `CLAUDE.md` exist; `CLAUDE.md` contains a line `@AGENTS.md`.\n2. No content duplication: the Claude-notes block must not restate `AGENTS.md` sections.\n3. `.aiboarding\u002Ftools\u002Fcheck-size-budget AGENTS.md` passes as a local sensor (no FAIL;\n   resolve WARNs or get the user's explicit OK), and\n   `.aiboarding\u002Ftools\u002Faudit-onboarding-evidence \u003Crepo-root>` reports no Codex\n   project-chain failure.\n4. Every command quoted in `Build, Test, Run` and `Verification Before Completion`\n   resolves against the repo (package scripts, Makefile targets, CI workflows, or a\n   binary on PATH).\n5. `state.json:last_synced_commit` equals `git rev-parse HEAD`.\n6. On Claude Code: the settings merge contains exactly one aiboarding entry per event\n   and no `pre-task`\u002F`post-commit` references.\n\nAfter every required validator passes, write one compact `onboarding-validation`\nrecord with validator identities and repository-relative subjects using\n`.aiboarding\u002Ftools\u002Fwrite-evidence`; do not retain raw output. Recheck `HEAD`, then\nwrite the initial `state.json` with that exact `last_synced_commit`. If validation,\nevidence writing, or the head recheck fails, do not create or advance canonical state.\n\nThen report which files were created or updated and which hook entries were installed.\nOn Windows without Git Bash, tell the user once: hooks will not fire (`run-hook.cmd`\ndegrades silently), but native `CLAUDE.md`\u002F`AGENTS.md` loading still works.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fgustavo-meilus\u002Faiboarding\u002Fskills\u002Fcreate-agent-onboarding",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":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill create-agent-onboarding",{"tool":71,"command":72},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill create-agent-onboarding",{"tool":74,"command":75},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill create-agent-onboarding","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fgustavo-meilus\u002Faiboarding\u002Fskills\u002Fcreate-agent-onboarding\u002FSKILL.md",true,[],[80,90,98,106,114,122],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":89},"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":89},"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":89},"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":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":89},"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":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":89},"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":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":126,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":89},"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",[],[]]