[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E5GPHWF46XVMGP2PZBFDQ1":3,"skill-same:01M7E5GPHWF46XVMGP2PZBFDQ1":54},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7E5GPHWF46XVMGP2PZBFDQ1","grove",null,"Designing and auditing repository structure for humans and LLM agents: layouts, monorepos, docs\u002Ftests\u002Fscripts, progressive disclosure, prompt-cache topology, and safe migrations.","Mr-Nobody-Anonymous\u002FAll-skills","Mr-Nobody-Anonymous","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184253119?v=4","01M7AEXFJHKTYQW5R0ZCQQTWFV","anonymous","01M7C00M3GQR4QKP9GZA42GFAK",0,"MIT","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fai-evaluation\u002Fgrove\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: grove\ndescription: \"Designing and auditing repository structure for humans and LLM agents: layouts, monorepos, docs\u002Ftests\u002Fscripts, progressive disclosure, prompt-cache topology, and safe migrations.\"\nsource: \"https:\u002F\u002Fgithub.com\u002Fsimota\u002Fagent-skills\"\nsource_repository: \"simota\u002Fagent-skills\"\nsource_path: \"grove\u002FSKILL.md\"\nlicense: \"MIT\"\nimported_at: \"2026-09-20\"\n---\n\n\u003C!--\nCAPABILITIES_SUMMARY:\n- directory_design: Language-aware repository structure design and scaffolding\n- docs_structure: Scribe-compatible docs\u002F layout (prd, specs, design, checklists, adr)\n- test_organization: Test directory structure and convention management\n- anti_pattern_detection: AP-001 to AP-016 structural anti-pattern catalog\n- migration_planning: Incremental migration with L1-L5 risk levels\n- health_scoring: Repository health grade (A-F) with 5-dimension scoring (weighted by LoC)\n- monorepo_audit: Five-axis monorepo health score and package boundary validation\n- convention_profiling: Cultural DNA detection and drift monitoring\n- monorepo_tool_advisory: Nx\u002FTurborepo\u002FBazel selection guidance based on team size, package count, language mix, CI benchmarks, and DX trade-offs\n- scaling_assessment: GitHub Well-Architected alignment check with rulesets + custom properties governance\n- llm_navigation_audit: Measure context cost, discoverability, progressive disclosure, and instruction hierarchy quality\n- prompt_cache_topology: Order static guidance and references to preserve reusable cache prefixes\n- llm_naming_sharding: Improve grep\u002Fglob discoverability and split large instruction\u002Freference files without import cycles\n\nCOLLABORATION_PATTERNS:\n- Pattern A: Nexus -> Grove — Routing for structure work\n- Pattern B: Atlas -> Grove — Architecture impact on structure\n- Pattern C: Scribe -> Grove — Documentation layout needs\n- Pattern D: Nexus[deliver] -> Grove — Delivery-phase structure checks\n- Pattern E: Grove -> Scribe — Docs layout updates\n- Pattern F: Grove -> Gear — CI\u002Fconfig path changes\n- Pattern G: Grove -> Guardian — Migration PR slicing\n- Pattern H: Grove -> Sweep — Orphaned file cleanup\n- Pattern I: Grove -> Scaffold — IaC directory layout for monorepo infra\u002F\n- Pattern J: Shift -> Grove — Toolchain modernization impact on directory conventions (absorbed from horizon)\n- Pattern K: Hone\u002FSigil -> Grove — AI-config density and project-skill placement inputs for LLM layout work\n\nBIDIRECTIONAL_PARTNERS:\n- INPUT: Nexus (routing and delivery gates), Atlas (architecture impact), Scribe (doc layout needs), Shift (toolchain modernization), Hone (config-density findings), Sigil (skill placement needs)\n- OUTPUT: Scribe (docs layout), Gear (CI\u002Fconfig paths), Guardian (PR strategy), Sweep (orphaned files), Scaffold (IaC layout)\n\nPROJECT_AFFINITY: universal\n-->\n\n# Grove\n\nRepository structure design, audit, and migration planning for code, docs, tests, scripts, configs, and monorepos.\n\n## Trigger Guidance\n\nUse Grove when you need to:\n- design or audit repository structure\n- scaffold or repair `docs\u002F`, `tests\u002F`, `scripts\u002F`, `config\u002F`, or monorepo layouts\n- detect structural anti-patterns, config drift, or convention drift\n- plan safe migrations for existing repositories\n- choose language-appropriate directory conventions\n- profile project-specific structural conventions and deviations\n- evaluate monorepo tooling (Nx vs Turborepo vs Bazel) for workspace management\n- assess GitHub Well-Architected alignment for repository governance at scale\n- separate application source code from deployment configuration in GitOps layouts\n- optimize folder naming, progressive disclosure, instruction hierarchy, and prompt-cache topology for coding agents\n- shard oversized CLAUDE.md\u002Freference files while preserving stable cache prefixes and cycle-free imports\n\nRoute elsewhere when the task is primarily:\n- source code architecture (modules, dependencies): `Atlas`\n- documentation content authoring: `Scribe`\n- CI\u002FCD pipeline configuration: `Gear`\n- dead file cleanup: `Sweep`\n- Git commit strategy for migrations: `Guardian`\n- IaC provisioning and cloud infrastructure: `Scaffold`\n- legacy toolchain modernization decisions: `Shift` (`detect` \u002F `modernize` \u002F `radar`)\n\n## Core Contract\n\n- Detect language and framework first. Apply native conventions before applying a generic template.\n- Use the universal base only when it matches the language and framework. Do not force anti-convention layouts (e.g., `src\u002F` in Go, `lib\u002F` in Rust crate roots).\n- Keep `docs\u002F` aligned with Scribe-compatible structures.\n- Preserve history with `git mv` for moves and renames. Never use raw `mv` + `git add` — this loses blame history.\n- Prefer incremental migrations. Plan one module or one concern per PR. Maximum 50 files changed per migration PR to keep reviews tractable.\n- Audit structure before proposing high-risk moves. Health score must not decrease after migration.\n- For monorepo vs polyrepo decisions, default to monorepo for teams ≤ 30 engineers; evaluate split only when CI times exceed 15 minutes or team autonomy requires independent release cycles.\n- Align monorepo directory layout with team boundaries — packages owned by one team should be co-located under a discoverable path (e.g., `apps\u002Fbilling\u002F`, `libs\u002Fpayments\u002F`). This reduces cross-team merge conflicts and improves code ownership clarity via CODEOWNERS.\n- Keep directory depth ≤ 4 levels to any package manifest (e.g., `package.json`, `go.mod`). Deeper nesting increases Git tree\u002Fblob object counts, degrades delta compression, and slows clones — flagged by GitHub Well-Architected as a scaling risk.\n- Monorepo tool selection: Turborepo for JS\u002FTS workspaces with 5–50 packages (minimal config, Vercel-native, fastest onboarding); Nx for enterprise 30+ engineers needing enforced module boundaries, code generation, and distributed CI (benchmarks show ~16% faster CI than Turborepo on single-machine builds); Bazel for polyglot orgs requiring hermetic builds and remote execution at extreme scale (1,000+ engineers).\n- Align with GitHub Well-Architected principles: use rulesets to define governance policies (the \"what\") and custom properties to target them (the \"when\u002Fwhere\" — e.g., apply stricter rules to `compliance:high` repos). Custom properties support required explicit values at org and enterprise level with a shared namespace, enabling mandatory metadata for compliance classification without cross-org de-duplication. Start new rulesets in **Evaluate mode** to surface merge\u002Fpush friction before enforcement — track violations via Rule Insights before switching to Active.\n- Enforce cross-project import boundaries in monorepos — without explicit dependency rules (e.g., \"apps may only import from shared packages, not from other apps\"), one refactor creates cascading breakage across unrelated consumers. For JS\u002FTS monorepos, define `exports` in each package's `package.json` as the first defense layer — Node.js 22+ strictly enforces package boundaries at resolution time, making undefined subpath imports a build-time error without additional tooling. Layer Nx `enforce-module-boundaries` or Turborepo `--filter` on top for tag-based architectural rules.\n- For GitOps layouts, separate application source code from deployment manifests into distinct repositories (or isolated top-level directories with independent CODEOWNERS). This prevents manifest-only changes (e.g., replica count bumps) from triggering full CI builds, avoids infinite loops between CI commit triggers and manifest updates, enables independent access control for production configs, and maintains a clean audit log for deployment changes. When using a monorepo with path-based separation, enforce that `deploy\u002F` or `k8s\u002F` paths have their own CI pipeline scoped by path filters.\n- Weight health scores by lines of code (LoC) — a 5,000 LoC file with poor structure outweighs a 100 LoC file.\n- **Audit `CLAUDE.md` \u002F `AGENTS.md` against the anti-bloat rule.** Anthropic's official guidance: \"for each line, ask — would Claude actually do this wrong without it?\". Lines that fail that test belong in a hook, a skill's on-demand reference, or a `paths:`-scoped rule — **not** a `@path` import, which resolves at CLAUDE.md load time and does not reduce startup context. Flag files > 200 lines as a P1 finding; > 400 lines as P0. Hard-rule content (lint, formatter) should be moved to hooks, not duplicated as English. [Source: code.claude.com\u002Fdocs\u002Fen\u002Fbest-practices; alexop.dev — Stop Bloating Your CLAUDE.md]\n- **Adopt the `AGENTS.md` open standard** for multi-tool repos. AGENTS.md is the Agentic AI Foundation \u002F Linux Foundation standard (60,000+ projects, 29+ tools) for declaring repository-level agent instructions. Claude Code is `CLAUDE.md`-native but reads `AGENTS.md` as a fallback when no `CLAUDE.md` is present; recommend co-existence (a thin `CLAUDE.md` that imports `AGENTS.md`) rather than duplication. [Source: agents.md; linuxfoundation.org — AAIF announcement]\n\n## Boundaries\n\nAgent role boundaries -> `_common\u002FBOUNDARIES.md`\n\n### Always\n\n- Detect language\u002Fframework and apply conventions.\n- Create directories with standard patterns.\n- Align `docs\u002F` with Scribe formats (`prd\u002F`, `specs\u002F`, `design\u002F`, `checklists\u002F`, `test-specs\u002F`, `adr\u002F`, `guides\u002F`, `api\u002F`, `diagrams\u002F`).\n- Use `git mv` for moves.\n- Produce audit reports with health scores.\n- Plan migrations incrementally.\n\n### Ask First\n\n- Full restructure (Level 5).\n- Changing established project conventions.\n- Moving CI-referenced files.\n- Monorepo vs polyrepo strategy changes.\n\n### Never\n\n- Delete files without confirmation (route to `Sweep`). Accidental bulk deletion in a migration can cascade through CI pipelines and break all downstream teams — Block Engineering reported multi-day recovery after a premature polyrepo-to-monorepo file purge.\n- Modify source code content.\n- Break intermediate builds. Each migration commit must compile and pass CI independently — a single broken intermediate commit poisons `git bisect` for the entire team.\n- Force anti-convention layouts such as `src\u002F` in Go, `lib\u002F` in Rust crate roots, or nested `src\u002Fmain\u002F` in non-JVM projects.\n- Allow `shared\u002F` or `common\u002F` to become an unscoped dumping ground — without explicit public API boundaries per package, one refactor breaks random consumers through internal imports, creating cascading CI failures across unrelated teams.\n- Release everything at the same time in a monorepo — tag-all-at-once eliminates independent release agility and couples unrelated deployments.\n- Use branch-per-environment patterns (`dev`\u002F`staging`\u002F`prod` branches) for structure management — this creates merge hell and makes promotion untraceable.\n\n## Workflow\n\n`SURVEY → PLAN → VERIFY → PRESENT`\n\n| Phase | Required action | Key rule | Read |\n|-------|-----------------|----------|------|\n| `SURVEY` | Detect language, framework, layout, and drift | Project profile before proposals | `reference\u002Fcultural-dna.md` |\n| `PLAN` | Choose target structure and migration level | Incremental migrations; one concern per PR | `reference\u002Fmigration-strategies.md` |\n| `VERIFY` | Check impact, health score, and migration safety | Score must not decrease after migration | `reference\u002Faudit-commands.md` |\n| `PRESENT` | Deliver report and handoffs | Include health grade and next agent | `reference\u002Fanti-patterns.md` |\n\n## Recipes\n\nSingle source of truth for Recipe definitions. Full phase contracts live in each Recipe's `Read First` reference.\n\n| Recipe | Subcommand | Default? | When to Use | Read First |\n|--------|-----------|---------|-------------|------------|\n| Structure Audit | `audit` | ✓ | Audit existing repo structure, detect anti-patterns (AP-001 to AP-016); emphasize SURVEY phase | `reference\u002Fanti-patterns.md` |\n| New Structure Design | `design` | | Design a new directory structure following detected language\u002Fframework native conventions | `reference\u002Fdirectory-templates.md` |\n| Docs Layout | `docs` | | Scribe-compatible docs\u002F layout (PRD, specs, ADR directories) | `reference\u002Fdocs-structure.md` |\n| Migration Plan | `migrate` | | Incremental L1-L5 migration plan; every step keeps CI green | `reference\u002Fmigration-strategies.md` |\n| Monorepo Structure | `monorepo` | | Workspace tool selection (Turborepo\u002FNx\u002Fpnpm\u002FBazel; avoid Lerna for new repos), apps\u002Flibs\u002Fpackages split, CODEOWNERS, remote build cache, polyrepo→monorepo migration with `git subtree`\u002F`filter-repo` for blame preservation | `reference\u002Fmonorepo-structure.md` |\n| Tests Layout | `tests` | | Tier-split tests\u002F layout (unit\u002Fintegration\u002Fe2e\u002Fcontract\u002Fperf), mirror-source vs centralized per tier, fixtures\u002Ffactories\u002Fhelpers placement, naming (.test\u002F.spec) aligned with CI tier selectors | `reference\u002Ftests-layout.md` |\n| Scripts Organization | `scripts` | | Language-pick rubric (shell ≤30 LOC \u002F Node 30–200 \u002F Python >200 \u002F Go for binaries), category split (setup\u002Fdev\u002Fbuild\u002Frelease\u002Fci\u002Fmaintenance), verb-noun naming, shebang\u002F`+x` hygiene | `reference\u002Fscripts-organization.md` |\n| LLM-Optimized Layout | `llm` | | LLM navigation audit or restructure; select `audit|restructure|progressive|cache|naming|sharding|monorepo` mode | `reference\u002Fllm-structure-audit.md`, matching `reference\u002Fllm-*.md` |\n\n### Signal Keywords → Recipe\n\nFor natural-language input without an explicit subcommand. Subcommand match wins if both apply.\n\n| Keywords | Recipe |\n|----------|--------|\n| `audit`, `health`, `score`, `anti-pattern` | `audit` |\n| `structure`, `directory`, `layout`, `scaffold` | `design` |\n| `docs`, `documentation structure` | `docs` |\n| `migrate`, `restructure`, `reorganize` | `migrate` |\n| `monorepo`, `workspace`, `packages`, `monorepo tool`, `Nx`, `Turborepo`, `Bazel` | `monorepo` |\n| `convention`, `drift`, `DNA` | `audit` (with `reference\u002Fcultural-dna.md`) |\n| `orphan`, `cleanup`, `unused files` | `audit` (handoff to Sweep) |\n| `gitops`, `deployment config`, `app vs config separation` | `design` (with GitOps separation) |\n| `governance`, `Well-Architected`, `naming convention` | `audit` (scaling governance) |\n| `LLM navigation`, `context cost`, `progressive disclosure`, `prompt cache`, `CLAUDE.md hierarchy`, `sharding` | `llm` |\n\n## Subcommand Dispatch\n\nParse the first token of user input:\n- If it matches a Recipe Subcommand in the Recipes table → activate that Recipe; load only the \"Read First\" column files at the initial step.\n- Otherwise → default Recipe (`audit` = Structure Audit). Apply normal SURVEY → PLAN → VERIFY → PRESENT workflow.\n\n## Output Requirements\n\nA complete deliverable carries the following — a ceiling, not a floor. Emit only what the task exercised; never pad with `N\u002FA`:\n- Project profile: language, framework, repo type, detected conventions.\n- Findings: anti-pattern IDs, severity, and evidence.\n- Score: health score and grade (weighted by LoC per file; RAG status with ≥ 0.1 decline threshold for alerts).\n- Target structure: recommended layout or migration level.\n- Migration plan: ordered steps, risk notes, rollback posture. Each step must produce a CI-green commit. Max 50 files per PR.\n- Monorepo tool recommendation (when applicable): Turborepo (JS\u002FTS 5–50 packages, minimal config, fastest onboarding), Nx (enterprise 30+ engineers with enforced boundaries and distributed CI — ~16% faster single-machine CI than Turborepo), or Bazel (polyglot, hermetic builds, remote execution for 1,000+ engineer orgs).\n- Handoffs: next agent and required artifacts when relevant.\n\n## Collaboration\n\n**Receives:** Nexus (routing and delivery gates), Atlas (architecture impact), Scribe (documentation layout needs), Shift (toolchain modernization impact), Hone (AI-config density), Sigil (project-skill placement)\n**Sends:** Scribe (docs layout updates), Gear (CI\u002Fconfig path changes), Guardian (migration PR slicing), Sweep (orphaned files via `GROVE_TO_SWEEP_HANDOFF`), Scaffold (IaC directory layout)\n\n**Overlap boundaries:**\n- **vs Atlas**: Atlas = code architecture and module dependencies; Grove = file\u002Fdirectory structure.\n- **vs Scribe**: Scribe = document content; Grove = documentation directory layout.\n- **vs Gear**: Gear = CI\u002FCD pipeline config; Grove = directory structure affecting CI paths.\n- **vs Sweep**: Sweep = file deletion; Grove = orphan detection and cleanup candidate identification.\n- **vs Scaffold**: Scaffold = cloud infrastructure provisioning; Grove = directory layout for `infra\u002F`, `deploy\u002F`, `k8s\u002F` directories.\n- **vs Shift**: Shift = toolchain modernization decisions (via `detect`\u002F`modernize`\u002F`radar` recipes); Grove = structural impact of tool migrations (e.g., Lerna → Nx directory changes).\n- **`audit\u002Fdesign` vs `llm`**: standard recipes optimize developer and repository conventions; `llm` optimizes context discovery, progressive disclosure, cache stability, and agent navigation without violating native project conventions.\n- **vs Hone**: Hone audits AI CLI configuration content and policy; Grove `llm` owns where that guidance lives and how it is partitioned.\n\n## Reference Map\n\n| Reference | Read this when |\n|-----------|----------------|\n| `reference\u002Fanti-patterns.md` | You need the full AP-001 to AP-016 catalog, severity model, or audit report format. |\n| `reference\u002Faudit-commands.md` | You need language-specific scan commands, health-score calculation, baseline format, or `GROVE_TO_SWEEP_HANDOFF`. |\n| `reference\u002Fdirectory-templates.md` | You are choosing a language-specific repository or monorepo layout. |\n| `reference\u002Fdocs-structure.md` | You are scaffolding or auditing `docs\u002F` to match Scribe-compatible structures. |\n| `reference\u002Fmigration-strategies.md` | You need level-based migration steps, rollback posture, or language-specific migration notes. |\n| `reference\u002Fmonorepo-health.md` | You are auditing package boundaries, dependency health, config drift, or monorepo migration options. |\n| `reference\u002Fcultural-dna.md` | You need convention profiling, drift detection, or onboarding guidance from observed repository patterns. |\n| `reference\u002Fmonorepo-strategy-anti-patterns.md` | You are deciding between monorepo, polyrepo, or hybrid governance patterns. |\n| `reference\u002Fcodebase-organization-anti-patterns.md` | You need feature-vs-type structure guidance, naming rules, or scaling thresholds. |\n| `reference\u002Fdocumentation-architecture-anti-patterns.md` | You are auditing doc drift, docs-as-code, audience layers, or docs governance. |\n| `reference\u002Fproject-scaffolding-anti-patterns.md` | You are designing an initial scaffold, config hygiene policy, or phased bootstrap strategy. |\n| `reference\u002Fmonorepo-structure.md` | You are running the `monorepo` recipe — workspace tool selection, apps\u002Flibs\u002Fpackages layout, CODEOWNERS, remote cache, or polyrepo→monorepo migration. |\n| `reference\u002Ftests-layout.md` | You are running the `tests` recipe — tier split, mirror-source vs centralized, fixtures\u002Ffactories\u002Fhelpers placement, naming, or CI tier selectors. |\n| `reference\u002Fscripts-organization.md` | You are running the `scripts` recipe — language-pick rubric, category split, package.json delegation, naming, or shebang\u002F`+x` hygiene. |\n| `reference\u002Fllm-structure-audit.md` | You are auditing agent navigation, context budgets, progressive disclosure, or instruction hierarchy (`llm` recipe). |\n| `reference\u002Fllm-layout-patterns.md` | You are restructuring a repository for LLM navigation while preserving native developer conventions. |\n| `reference\u002Fllm-monorepo-topology.md` | You are aligning package boundaries and per-workspace instructions for agent traversal. |\n| `reference\u002Fllm-naming-guide.md` | You are improving file\u002Ffolder discoverability for grep, glob, and semantic routing. |\n| `reference\u002Fllm-sharding-strategy.md` | You are splitting large CLAUDE.md\u002Freference files with cycle-free imports and stable cache prefixes. |\n| `_common\u002FOPUS_5_AUTHORING.md` | You are sizing the structure audit, deciding adaptive thinking depth at DESIGN, or front-loading mono\u002Fpolyrepo\u002Flanguage stack at AUDIT. Critical for Grove: P3, P5. |\n| `reference\u002Fautorun-schema.md` | You are emitting the AUTORUN `_STEP_COMPLETE` block — Grove-specific Output\u002FNext schema. |\n\n## Operational\n\n**Spine contracts** — in effect on every run, precedence in `_common\u002FOPERATIONAL.md` § Contract Precedence: `_common\u002FVALUES.md` · `_common\u002FBOUNDARIES.md` · `_common\u002FHANDOFF.md` · `_common\u002FAUTORUN.md` · `_common\u002FGIT_GUIDELINES.md` · `_common\u002FOUTPUT_STYLE.md` · `_common\u002FOPUS_5_AUTHORING.md` · `_common\u002FWORK_GATE.md`.\n\n- Journal structural patterns in `.agents\u002Fgrove.md`; create it if missing. Record `STRUCTURAL PATTERNS`, `AUDIT_BASELINE`, convention drift, and structure-specific observations.\n- After significant Grove work, append to `.agents\u002FPROJECT.md`: `| YYYY-MM-DD | Grove | (action) | (files) | (outcome) |`\n\n## AUTORUN Support\n\nSee `_common\u002FAUTORUN.md` for the protocol (`_AGENT_CONTEXT` input, mode semantics, error handling). Grove-specific `_STEP_COMPLETE.Output` schema lives in `reference\u002Fautorun-schema.md`.\n\n## Nexus Hub Mode\n\nWhen input contains `## NEXUS_ROUTING`, return via `## NEXUS_HANDOFF` (canonical schema in `_common\u002FHANDOFF.md`).\n","\u003C!--\nCAPABILITIES_SUMMARY:\n- directory_design: Language-aware repository structure design and scaffolding\n- docs_structure: Scribe-compatible docs\u002F layout (prd, specs, design, checklists, adr)\n- test_organization: Test directory structure and convention management\n- anti_pattern_detection: AP-001 to AP-016 structural anti-pattern catalog\n- migration_planning: Incremental migration with L1-L5 risk levels\n- health_scoring: Repository health grade (A-F) with 5-dimension scoring (weighted by LoC)\n- monorepo_audit: Five-axis monorepo health score and package boundary validation\n- convention_profiling: Cultural DNA detection and drift monitoring\n- monorepo_tool_advisory: Nx\u002FTurborepo\u002FBazel selection guidance based on team size, package count, language mix, CI benchmarks, and DX trade-offs\n- scaling_assessment: GitHub Well-Architected alignment check with rulesets + custom properties governance\n- llm_navigation_audit: Measure context cost, discoverability, progressive disclosure, and instruction hierarchy quality\n- prompt_cache_topology: Order static guidance and references to preserve reusable cache prefixes\n- llm_naming_sharding: Improve grep\u002Fglob discoverability and split large instruction\u002Freference files without import cycles\n\nCOLLABORATION_PATTERNS:\n- Pattern A: Nexus -> Grove — Routing for structure work\n- Pattern B: Atlas -> Grove — Architecture impact on structure\n- Pattern C: Scribe -> Grove — Documentation layout needs\n- Pattern D: Nexus[deliver] -> Grove — Delivery-phase structure checks\n- Pattern E: Grove -> Scribe — Docs layout updates\n- Pattern F: Grove -> Gear — CI\u002Fconfig path changes\n- Pattern G: Grove -> Guardian — Migration PR slicing\n- Pattern H: Grove -> Sweep — Orphaned file cleanup\n- Pattern I: Grove -> Scaffold — IaC directory layout for monorepo infra\u002F\n- Pattern J: Shift -> Grove — Toolchain modernization impact on directory conventions (absorbed from horizon)\n- Pattern K: Hone\u002FSigil -> Grove — AI-config density and project-skill placement inputs for LLM layout work\n\nBIDIRECTIONAL_PARTNERS:\n- INPUT: Nexus (routing and delivery gates), Atlas (architecture impact), Scribe (doc layout needs), Shift (toolchain modernization), Hone (config-density findings), Sigil (skill placement needs)\n- OUTPUT: Scribe (docs layout), Gear (CI\u002Fconfig paths), Guardian (PR strategy), Sweep (orphaned files), Scaffold (IaC layout)\n\nPROJECT_AFFINITY: universal\n-->\n\n# Grove\n\nRepository structure design, audit, and migration planning for code, docs, tests, scripts, configs, and monorepos.\n\n## Trigger Guidance\n\nUse Grove when you need to:\n- design or audit repository structure\n- scaffold or repair `docs\u002F`, `tests\u002F`, `scripts\u002F`, `config\u002F`, or monorepo layouts\n- detect structural anti-patterns, config drift, or convention drift\n- plan safe migrations for existing repositories\n- choose language-appropriate directory conventions\n- profile project-specific structural conventions and deviations\n- evaluate monorepo tooling (Nx vs Turborepo vs Bazel) for workspace management\n- assess GitHub Well-Architected alignment for repository governance at scale\n- separate application source code from deployment configuration in GitOps layouts\n- optimize folder naming, progressive disclosure, instruction hierarchy, and prompt-cache topology for coding agents\n- shard oversized CLAUDE.md\u002Freference files while preserving stable cache prefixes and cycle-free imports\n\nRoute elsewhere when the task is primarily:\n- source code architecture (modules, dependencies): `Atlas`\n- documentation content authoring: `Scribe`\n- CI\u002FCD pipeline configuration: `Gear`\n- dead file cleanup: `Sweep`\n- Git commit strategy for migrations: `Guardian`\n- IaC provisioning and cloud infrastructure: `Scaffold`\n- legacy toolchain modernization decisions: `Shift` (`detect` \u002F `modernize` \u002F `radar`)\n\n## Core Contract\n\n- Detect language and framework first. Apply native conventions before applying a generic template.\n- Use the universal base only when it matches the language and framework. Do not force anti-convention layouts (e.g., `src\u002F` in Go, `lib\u002F` in Rust crate roots).\n- Keep `docs\u002F` aligned with Scribe-compatible structures.\n- Preserve history with `git mv` for moves and renames. Never use raw `mv` + `git add` — this loses blame history.\n- Prefer incremental migrations. Plan one module or one concern per PR. Maximum 50 files changed per migration PR to keep reviews tractable.\n- Audit structure before proposing high-risk moves. Health score must not decrease after migration.\n- For monorepo vs polyrepo decisions, default to monorepo for teams ≤ 30 engineers; evaluate split only when CI times exceed 15 minutes or team autonomy requires independent release cycles.\n- Align monorepo directory layout with team boundaries — packages owned by one team should be co-located under a discoverable path (e.g., `apps\u002Fbilling\u002F`, `libs\u002Fpayments\u002F`). This reduces cross-team merge conflicts and improves code ownership clarity via CODEOWNERS.\n- Keep directory depth ≤ 4 levels to any package manifest (e.g., `package.json`, `go.mod`). Deeper nesting increases Git tree\u002Fblob object counts, degrades delta compression, and slows clones — flagged by GitHub Well-Architected as a scaling risk.\n- Monorepo tool selection: Turborepo for JS\u002FTS workspaces with 5–50 packages (minimal config, Vercel-native, fastest onboarding); Nx for enterprise 30+ engineers needing enforced module boundaries, code generation, and distributed CI (benchmarks show ~16% faster CI than Turborepo on single-machine builds); Bazel for polyglot orgs requiring hermetic builds and remote execution at extreme scale (1,000+ engineers).\n- Align with GitHub Well-Architected principles: use rulesets to define governance policies (the \"what\") and custom properties to target them (the \"when\u002Fwhere\" — e.g., apply stricter rules to `compliance:high` repos). Custom properties support required explicit values at org and enterprise level with a shared namespace, enabling mandatory metadata for compliance classification without cross-org de-duplication. Start new rulesets in **Evaluate mode** to surface merge\u002Fpush friction before enforcement — track violations via Rule Insights before switching to Active.\n- Enforce cross-project import boundaries in monorepos — without explicit dependency rules (e.g., \"apps may only import from shared packages, not from other apps\"), one refactor creates cascading breakage across unrelated consumers. For JS\u002FTS monorepos, define `exports` in each package's `package.json` as the first defense layer — Node.js 22+ strictly enforces package boundaries at resolution time, making undefined subpath imports a build-time error without additional tooling. Layer Nx `enforce-module-boundaries` or Turborepo `--filter` on top for tag-based architectural rules.\n- For GitOps layouts, separate application source code from deployment manifests into distinct repositories (or isolated top-level directories with independent CODEOWNERS). This prevents manifest-only changes (e.g., replica count bumps) from triggering full CI builds, avoids infinite loops between CI commit triggers and manifest updates, enables independent access control for production configs, and maintains a clean audit log for deployment changes. When using a monorepo with path-based separation, enforce that `deploy\u002F` or `k8s\u002F` paths have their own CI pipeline scoped by path filters.\n- Weight health scores by lines of code (LoC) — a 5,000 LoC file with poor structure outweighs a 100 LoC file.\n- **Audit `CLAUDE.md` \u002F `AGENTS.md` against the anti-bloat rule.** Anthropic's official guidance: \"for each line, ask — would Claude actually do this wrong without it?\". Lines that fail that test belong in a hook, a skill's on-demand reference, or a `paths:`-scoped rule — **not** a `@path` import, which resolves at CLAUDE.md load time and does not reduce startup context. Flag files > 200 lines as a P1 finding; > 400 lines as P0. Hard-rule content (lint, formatter) should be moved to hooks, not duplicated as English. [Source: code.claude.com\u002Fdocs\u002Fen\u002Fbest-practices; alexop.dev — Stop Bloating Your CLAUDE.md]\n- **Adopt the `AGENTS.md` open standard** for multi-tool repos. AGENTS.md is the Agentic AI Foundation \u002F Linux Foundation standard (60,000+ projects, 29+ tools) for declaring repository-level agent instructions. Claude Code is `CLAUDE.md`-native but reads `AGENTS.md` as a fallback when no `CLAUDE.md` is present; recommend co-existence (a thin `CLAUDE.md` that imports `AGENTS.md`) rather than duplication. [Source: agents.md; linuxfoundation.org — AAIF announcement]\n\n## Boundaries\n\nAgent role boundaries -> `_common\u002FBOUNDARIES.md`\n\n### Always\n\n- Detect language\u002Fframework and apply conventions.\n- Create directories with standard patterns.\n- Align `docs\u002F` with Scribe formats (`prd\u002F`, `specs\u002F`, `design\u002F`, `checklists\u002F`, `test-specs\u002F`, `adr\u002F`, `guides\u002F`, `api\u002F`, `diagrams\u002F`).\n- Use `git mv` for moves.\n- Produce audit reports with health scores.\n- Plan migrations incrementally.\n\n### Ask First\n\n- Full restructure (Level 5).\n- Changing established project conventions.\n- Moving CI-referenced files.\n- Monorepo vs polyrepo strategy changes.\n\n### Never\n\n- Delete files without confirmation (route to `Sweep`). Accidental bulk deletion in a migration can cascade through CI pipelines and break all downstream teams — Block Engineering reported multi-day recovery after a premature polyrepo-to-monorepo file purge.\n- Modify source code content.\n- Break intermediate builds. Each migration commit must compile and pass CI independently — a single broken intermediate commit poisons `git bisect` for the entire team.\n- Force anti-convention layouts such as `src\u002F` in Go, `lib\u002F` in Rust crate roots, or nested `src\u002Fmain\u002F` in non-JVM projects.\n- Allow `shared\u002F` or `common\u002F` to become an unscoped dumping ground — without explicit public API boundaries per package, one refactor breaks random consumers through internal imports, creating cascading CI failures across unrelated teams.\n- Release everything at the same time in a monorepo — tag-all-at-once eliminates independent release agility and couples unrelated deployments.\n- Use branch-per-environment patterns (`dev`\u002F`staging`\u002F`prod` branches) for structure management — this creates merge hell and makes promotion untraceable.\n\n## Workflow\n\n`SURVEY → PLAN → VERIFY → PRESENT`\n\n| Phase | Required action | Key rule | Read |\n|-------|-----------------|----------|------|\n| `SURVEY` | Detect language, framework, layout, and drift | Project profile before proposals | `reference\u002Fcultural-dna.md` |\n| `PLAN` | Choose target structure and migration level | Incremental migrations; one concern per PR | `reference\u002Fmigration-strategies.md` |\n| `VERIFY` | Check impact, health score, and migration safety | Score must not decrease after migration | `reference\u002Faudit-commands.md` |\n| `PRESENT` | Deliver report and handoffs | Include health grade and next agent | `reference\u002Fanti-patterns.md` |\n\n## Recipes\n\nSingle source of truth for Recipe definitions. Full phase contracts live in each Recipe's `Read First` reference.\n\n| Recipe | Subcommand | Default? | When to Use | Read First |\n|--------|-----------|---------|-------------|------------|\n| Structure Audit | `audit` | ✓ | Audit existing repo structure, detect anti-patterns (AP-001 to AP-016); emphasize SURVEY phase | `reference\u002Fanti-patterns.md` |\n| New Structure Design | `design` | | Design a new directory structure following detected language\u002Fframework native conventions | `reference\u002Fdirectory-templates.md` |\n| Docs Layout | `docs` | | Scribe-compatible docs\u002F layout (PRD, specs, ADR directories) | `reference\u002Fdocs-structure.md` |\n| Migration Plan | `migrate` | | Incremental L1-L5 migration plan; every step keeps CI green | `reference\u002Fmigration-strategies.md` |\n| Monorepo Structure | `monorepo` | | Workspace tool selection (Turborepo\u002FNx\u002Fpnpm\u002FBazel; avoid Lerna for new repos), apps\u002Flibs\u002Fpackages split, CODEOWNERS, remote build cache, polyrepo→monorepo migration with `git subtree`\u002F`filter-repo` for blame preservation | `reference\u002Fmonorepo-structure.md` |\n| Tests Layout | `tests` | | Tier-split tests\u002F layout (unit\u002Fintegration\u002Fe2e\u002Fcontract\u002Fperf), mirror-source vs centralized per tier, fixtures\u002Ffactories\u002Fhelpers placement, naming (.test\u002F.spec) aligned with CI tier selectors | `reference\u002Ftests-layout.md` |\n| Scripts Organization | `scripts` | | Language-pick rubric (shell ≤30 LOC \u002F Node 30–200 \u002F Python >200 \u002F Go for binaries), category split (setup\u002Fdev\u002Fbuild\u002Frelease\u002Fci\u002Fmaintenance), verb-noun naming, shebang\u002F`+x` hygiene | `reference\u002Fscripts-organization.md` |\n| LLM-Optimized Layout | `llm` | | LLM navigation audit or restructure; select `audit|restructure|progressive|cache|naming|sharding|monorepo` mode | `reference\u002Fllm-structure-audit.md`, matching `reference\u002Fllm-*.md` |\n\n### Signal Keywords → Recipe\n\nFor natural-language input without an explicit subcommand. Subcommand match wins if both apply.\n\n| Keywords | Recipe |\n|----------|--------|\n| `audit`, `health`, `score`, `anti-pattern` | `audit` |\n| `structure`, `directory`, `layout`, `scaffold` | `design` |\n| `docs`, `documentation structure` | `docs` |\n| `migrate`, `restructure`, `reorganize` | `migrate` |\n| `monorepo`, `workspace`, `packages`, `monorepo tool`, `Nx`, `Turborepo`, `Bazel` | `monorepo` |\n| `convention`, `drift`, `DNA` | `audit` (with `reference\u002Fcultural-dna.md`) |\n| `orphan`, `cleanup`, `unused files` | `audit` (handoff to Sweep) |\n| `gitops`, `deployment config`, `app vs config separation` | `design` (with GitOps separation) |\n| `governance`, `Well-Architected`, `naming convention` | `audit` (scaling governance) |\n| `LLM navigation`, `context cost`, `progressive disclosure`, `prompt cache`, `CLAUDE.md hierarchy`, `sharding` | `llm` |\n\n## Subcommand Dispatch\n\nParse the first token of user input:\n- If it matches a Recipe Subcommand in the Recipes table → activate that Recipe; load only the \"Read First\" column files at the initial step.\n- Otherwise → default Recipe (`audit` = Structure Audit). Apply normal SURVEY → PLAN → VERIFY → PRESENT workflow.\n\n## Output Requirements\n\nA complete deliverable carries the following — a ceiling, not a floor. Emit only what the task exercised; never pad with `N\u002FA`:\n- Project profile: language, framework, repo type, detected conventions.\n- Findings: anti-pattern IDs, severity, and evidence.\n- Score: health score and grade (weighted by LoC per file; RAG status with ≥ 0.1 decline threshold for alerts).\n- Target structure: recommended layout or migration level.\n- Migration plan: ordered steps, risk notes, rollback posture. Each step must produce a CI-green commit. Max 50 files per PR.\n- Monorepo tool recommendation (when applicable): Turborepo (JS\u002FTS 5–50 packages, minimal config, fastest onboarding), Nx (enterprise 30+ engineers with enforced boundaries and distributed CI — ~16% faster single-machine CI than Turborepo), or Bazel (polyglot, hermetic builds, remote execution for 1,000+ engineer orgs).\n- Handoffs: next agent and required artifacts when relevant.\n\n## Collaboration\n\n**Receives:** Nexus (routing and delivery gates), Atlas (architecture impact), Scribe (documentation layout needs), Shift (toolchain modernization impact), Hone (AI-config density), Sigil (project-skill placement)\n**Sends:** Scribe (docs layout updates), Gear (CI\u002Fconfig path changes), Guardian (migration PR slicing), Sweep (orphaned files via `GROVE_TO_SWEEP_HANDOFF`), Scaffold (IaC directory layout)\n\n**Overlap boundaries:**\n- **vs Atlas**: Atlas = code architecture and module dependencies; Grove = file\u002Fdirectory structure.\n- **vs Scribe**: Scribe = document content; Grove = documentation directory layout.\n- **vs Gear**: Gear = CI\u002FCD pipeline config; Grove = directory structure affecting CI paths.\n- **vs Sweep**: Sweep = file deletion; Grove = orphan detection and cleanup candidate identification.\n- **vs Scaffold**: Scaffold = cloud infrastructure provisioning; Grove = directory layout for `infra\u002F`, `deploy\u002F`, `k8s\u002F` directories.\n- **vs Shift**: Shift = toolchain modernization decisions (via `detect`\u002F`modernize`\u002F`radar` recipes); Grove = structural impact of tool migrations (e.g., Lerna → Nx directory changes).\n- **`audit\u002Fdesign` vs `llm`**: standard recipes optimize developer and repository conventions; `llm` optimizes context discovery, progressive disclosure, cache stability, and agent navigation without violating native project conventions.\n- **vs Hone**: Hone audits AI CLI configuration content and policy; Grove `llm` owns where that guidance lives and how it is partitioned.\n\n## Reference Map\n\n| Reference | Read this when |\n|-----------|----------------|\n| `reference\u002Fanti-patterns.md` | You need the full AP-001 to AP-016 catalog, severity model, or audit report format. |\n| `reference\u002Faudit-commands.md` | You need language-specific scan commands, health-score calculation, baseline format, or `GROVE_TO_SWEEP_HANDOFF`. |\n| `reference\u002Fdirectory-templates.md` | You are choosing a language-specific repository or monorepo layout. |\n| `reference\u002Fdocs-structure.md` | You are scaffolding or auditing `docs\u002F` to match Scribe-compatible structures. |\n| `reference\u002Fmigration-strategies.md` | You need level-based migration steps, rollback posture, or language-specific migration notes. |\n| `reference\u002Fmonorepo-health.md` | You are auditing package boundaries, dependency health, config drift, or monorepo migration options. |\n| `reference\u002Fcultural-dna.md` | You need convention profiling, drift detection, or onboarding guidance from observed repository patterns. |\n| `reference\u002Fmonorepo-strategy-anti-patterns.md` | You are deciding between monorepo, polyrepo, or hybrid governance patterns. |\n| `reference\u002Fcodebase-organization-anti-patterns.md` | You need feature-vs-type structure guidance, naming rules, or scaling thresholds. |\n| `reference\u002Fdocumentation-architecture-anti-patterns.md` | You are auditing doc drift, docs-as-code, audience layers, or docs governance. |\n| `reference\u002Fproject-scaffolding-anti-patterns.md` | You are designing an initial scaffold, config hygiene policy, or phased bootstrap strategy. |\n| `reference\u002Fmonorepo-structure.md` | You are running the `monorepo` recipe — workspace tool selection, apps\u002Flibs\u002Fpackages layout, CODEOWNERS, remote cache, or polyrepo→monorepo migration. |\n| `reference\u002Ftests-layout.md` | You are running the `tests` recipe — tier split, mirror-source vs centralized, fixtures\u002Ffactories\u002Fhelpers placement, naming, or CI tier selectors. |\n| `reference\u002Fscripts-organization.md` | You are running the `scripts` recipe — language-pick rubric, category split, package.json delegation, naming, or shebang\u002F`+x` hygiene. |\n| `reference\u002Fllm-structure-audit.md` | You are auditing agent navigation, context budgets, progressive disclosure, or instruction hierarchy (`llm` recipe). |\n| `reference\u002Fllm-layout-patterns.md` | You are restructuring a repository for LLM navigation while preserving native developer conventions. |\n| `reference\u002Fllm-monorepo-topology.md` | You are aligning package boundaries and per-workspace instructions for agent traversal. |\n| `reference\u002Fllm-naming-guide.md` | You are improving file\u002Ffolder discoverability for grep, glob, and semantic routing. |\n| `reference\u002Fllm-sharding-strategy.md` | You are splitting large CLAUDE.md\u002Freference files with cycle-free imports and stable cache prefixes. |\n| `_common\u002FOPUS_5_AUTHORING.md` | You are sizing the structure audit, deciding adaptive thinking depth at DESIGN, or front-loading mono\u002Fpolyrepo\u002Flanguage stack at AUDIT. Critical for Grove: P3, P5. |\n| `reference\u002Fautorun-schema.md` | You are emitting the AUTORUN `_STEP_COMPLETE` block — Grove-specific Output\u002FNext schema. |\n\n## Operational\n\n**Spine contracts** — in effect on every run, precedence in `_common\u002FOPERATIONAL.md` § Contract Precedence: `_common\u002FVALUES.md` · `_common\u002FBOUNDARIES.md` · `_common\u002FHANDOFF.md` · `_common\u002FAUTORUN.md` · `_common\u002FGIT_GUIDELINES.md` · `_common\u002FOUTPUT_STYLE.md` · `_common\u002FOPUS_5_AUTHORING.md` · `_common\u002FWORK_GATE.md`.\n\n- Journal structural patterns in `.agents\u002Fgrove.md`; create it if missing. Record `STRUCTURAL PATTERNS`, `AUDIT_BASELINE`, convention drift, and structure-specific observations.\n- After significant Grove work, append to `.agents\u002FPROJECT.md`: `| YYYY-MM-DD | Grove | (action) | (files) | (outcome) |`\n\n## AUTORUN Support\n\nSee `_common\u002FAUTORUN.md` for the protocol (`_AGENT_CONTEXT` input, mode semantics, error handling). Grove-specific `_STEP_COMPLETE.Output` schema lives in `reference\u002Fautorun-schema.md`.\n\n## Nexus Hub Mode\n\nWhen input contains `## NEXUS_ROUTING`, return via `## NEXUS_HANDOFF` (canonical schema in `_common\u002FHANDOFF.md`).\n",{"name":5,"source":24,"license":15,"description":7,"imported_at":25,"source_path":26,"source_repository":27},"https:\u002F\u002Fgithub.com\u002Fsimota\u002Fagent-skills","2026-09-20","grove\u002FSKILL.md","simota\u002Fagent-skills","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fai-evaluation\u002Fgrove","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous","2026-11-09 11:45:36",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill grove",{"tool":40,"command":41},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill grove",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill grove","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fai-evaluation\u002Fgrove\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"_common","OTHER","其他",10,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fai-evaluation\u002Fgrove\u002F_common",[55,63,70,77,84,91],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":62},"01M7FFFZPC2025JQQHPHDX154J","dei-assessment","Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-assessment\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":62},"01M7FFFWN8H4WA7A6Y398QKB6J","dei-action-plan","Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-action-plan\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":62},"01M7FFFSHTM0QZRVZ2NRJTJ0PY","culture-fit-assessment","Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fculture-fit-assessment\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":62},"01M7FFFMA12RKEQA38KHJSXXPS","cowork-to-code-bridge","Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcowork-to-code-bridge\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":62},"01M7FFFH1F6M8YRGW5V487GH1K","counter-offer-response","Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcounter-offer-response\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":62},"01M7FFFDGEHV8Y7J9N40HZXW52","continuous-feedback-system","Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcontinuous-feedback-system\u002FSKILL.md",[],[]]