[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDESTRRCCSRQW86HNF7PW9":3,"skill-same:01M7FDESTRRCCSRQW86HNF7PW9":66},{"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":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":41,"updatedAt":42,"install":43,"resources":55},"01M7FDESTRRCCSRQW86HNF7PW9","workspace",null,"Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fworkspace\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: workspace\nlicense: MIT\ndescription: >-\n  Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims,\n  discovery relay, wave-based execution -- but the unit of work is a repo,\n  not a file. Coordinates campaigns across repositories with shared context.\nuser-invocable: true\nauto-trigger: false\ntrigger_keywords:\n  - workspace\n  - multi-repo\n  - cross-repo\n  - across repos\n  - multiple repos\n  - coordinate repos\n  - add redis and snowflake\n  - split into repos\nlast-updated: 2026-03-29\neffort: high\n---\n\n# \u002Fworkspace -- Multi-Repo Campaign Coordinator\n\n## When to Use\n\n- Adding infrastructure that spans repos (new database, shared service, API contract)\n- Coordinating changes across a frontend repo, backend repo, and infra repo\n- Breaking a monolith into services (each service becomes a repo-scoped campaign)\n- Any task where changes in repo A depend on or inform changes in repo B\n\n**Do not use when:**\n- All work is in one repo (use `\u002Ffleet` or `\u002Farchon`)\n- The repos are truly independent with no shared contracts (just run separate campaigns)\n\n## Protocol\n\n### Step 1: ORIENT\n\n1. Check for existing workspace session: `.planning\u002Fworkspace\u002Fsession-{slug}.md` — resume if `status: active` or `needs-continue`\n2. If starting fresh: identify repos, verify each path is a git repo, read each repo's `CLAUDE.md`, check `.planning\u002Fcampaigns\u002F` for active campaigns (avoid collisions)\n3. **Load prior session context and start watcher**:\n   ```bash\n   node .citadel\u002Fscripts\u002Fmomentum-watch-start.cjs\n   node .citadel\u002Fscripts\u002Fmomentum-read.cjs\n   ```\n   Skip momentum injection if output is empty.\n\n### Step 2: DECOMPOSE\n\nBreak the direction into repo-scoped work items (one campaign per repo per wave). Table format: `# | Repo | Campaign Direction | Scope | Deps | Wave`.\n\n**Rules:** items with no deps → Wave 1; dependents → Wave 2+. Max 3 repo-campaigns per wave. Scope format: `{repo}:{path}`.\n\nFor each inter-wave dependency, specify the cross-repo contract: what the producer will produce, what the consumer expects, and where the contract lives (shared types package, OpenAPI spec, env var).\n\n### Step 3: WORKSPACE SESSION FILE\n\nCreate `.planning\u002Fworkspace\u002Fsession-{slug}.md` with frontmatter: `version`, `id`, `status: active`, `started`, `completed_at: null`, `direction`, `repos` (path + name + branch per repo), `wave_count`, `current_wave: 1`, `campaigns_total`, `campaigns_complete: 0`.\n\nBody sections: Direction, Repos table (name\u002Fpath\u002Fbranch\u002Fstatus), Work Queue (table from Step 2), Cross-Repo Contracts (producer\u002Fconsumer\u002Fcontract\u002Flocation), Wave Execution Log (per wave: status, campaigns, started, completed), Shared Context (discovery relay accumulation).\n\n### Step 4: WAVE EXECUTION\n\nFor each wave:\n\n#### 4a. Pre-flight\n- Verify all dependency campaigns from prior waves completed successfully\n- Check cross-repo contracts: did producer repos create the expected outputs?\n- If a dependency failed: park the dependent campaign, flag for user decision\n\n#### 4b. Spawn campaigns\nFor each repo-campaign in this wave:\n\n1. Create branch: `git checkout -b workspace\u002F{slug}\u002F{repo-name}`\n2. Spawn agent with direction: `\u002Farchon` for complex (3+ phases), `\u002Ffleet` if parallelizable, `\u002Fmarshal` or direct skill for simple (1-2 steps)\n3. Inject context: discovery briefs from prior waves, prior session context (re-read `momentum.json` via `node .citadel\u002Fscripts\u002Fmomentum-read.cjs`, inject as `=== PRIOR SESSION CONTEXT ===`, skip if empty), cross-repo contracts, relevant `CLAUDE.md` sections from other repos\n\n#### 4c. Collect results\nExtract HANDOFF blocks, compress into cross-repo discovery brief, write persistent discovery records:\n  ```bash\n  node .citadel\u002Fscripts\u002Fdiscovery-write.cjs \\\n    --session {session-slug} --agent {repo-name}-{campaign-type} \\\n    --wave {wave-number} --status {success|partial|failed} \\\n    --scope \"{repo-name}:{scope-path}\" --handoff \"{json-array}\" \\\n    --decisions \"{json-array}\" --files \"{json-array}\" --failures \"{json-array}\"\n  ```\n\n#### 4d. Discovery relay\nWrite `workspace\u002Fbriefs\u002Fwave{N}-{repo-name}.md` for each completed campaign.\nAlso write `workspace\u002Fbriefs\u002Fwave{N}-cross-repo.md` summarizing:\n- New API endpoints or types created\n- Config changes that affect other repos\n- Contract fulfillment status (did the producer deliver what was promised?)\n\n#### 4e. Contract verification\nFor each cross-repo contract: verify the producer created the expected output (file + export for types, route existence for endpoints). If verification fails, flag and do not proceed with consumers.\n\n#### 4f. Update session\nMark completed campaigns, update wave status, write discovery relay, advance `current_wave`.\n\n### Step 5: COMPLETION\n\n1. Run typecheck\u002Fbuild for each repo in isolation (build shared types package first if present)\n2. Set session `status: completed`, `completed_at: {ISO timestamp}`\n3. Run `node .citadel\u002Fscripts\u002Fmomentum-synthesize.cjs`\n4. List all branches created across repos with suggested merge order based on dependency graph\n5. Output HANDOFF\n\n## Fringe Cases\n\n- **Repo not a git repo:** Skip it. Report which repos were skipped and why.\n- **Repo has uncommitted changes:** Stash before branching. Record stash ref in session file.\n  Pop on completion or failure.\n- **Active campaign in target repo:** Do not start a second campaign. Report the conflict\n  and ask the user whether to wait, park the existing campaign, or merge scopes.\n- **`.planning\u002Fworkspace\u002F` does not exist:** Create it (and `workspace\u002Fbriefs\u002F`).\n- **Cross-repo contract broken:** Park all downstream campaigns. Report which contract\n  failed, which producer was responsible, and what the consumer expected. Do not\n  attempt to fix the producer -- surface the issue for the user or re-run the producer campaign.\n- **One repo fails, others succeed:** Mark the failed repo-campaign. Do not roll back\n  successful repos. The user decides whether to fix-and-continue or abandon.\n- **Repos on different machines or remotes:** Not supported. All repos must be locally\n  accessible. If a repo is remote-only, the user must clone it first.\n- **Monorepo with multiple packages:** Treat each package as a \"repo\" for scoping purposes.\n  Use `{monorepo}:{package-path}` as the scope identifier.\n\n## Contextual Gates\n\n**Disclosure:** \"Running multi-repo campaign across [repos]. Changes committed to each repo independently.\"\n**Reversibility:** red — coordinates changes across multiple repositories; cross-repo commits are hard to revert in bulk.\n**Trust gates:**\n- Familiar (5+ sessions): coordinates multi-repo campaigns autonomously; novices should use \u002Fmarshal per repo.\n\n## Quality Gates\n\n- [ ] All repos verified as accessible git repositories before starting\n- [ ] Work queue has no scope overlaps within the same repo\n- [ ] Cross-repo contracts specified for every inter-wave dependency\n- [ ] Discovery relay written after each wave\n- [ ] Contract verification run before spawning consumer campaigns\n- [ ] Each repo's typecheck\u002Fbuild passes independently after completion\n- [ ] Session file updated after every wave (not just at the end)\n- [ ] No campaigns left in `active` state on completion\n\n## Exit Protocol\n\n```\n---HANDOFF---\n- Workspace: {slug} -- {direction summary}\n- Repos: {N} repos, {M} campaigns across {W} waves\n- Results: {completed}\u002F{total} campaigns succeeded\n- Branches: {list branches ready for review}\n- Merge order: {suggested order based on dependency graph}\n- Unresolved: {any failed campaigns or broken contracts}\n---\n```\n","# \u002Fworkspace -- Multi-Repo Campaign Coordinator\n\n## When to Use\n\n- Adding infrastructure that spans repos (new database, shared service, API contract)\n- Coordinating changes across a frontend repo, backend repo, and infra repo\n- Breaking a monolith into services (each service becomes a repo-scoped campaign)\n- Any task where changes in repo A depend on or inform changes in repo B\n\n**Do not use when:**\n- All work is in one repo (use `\u002Ffleet` or `\u002Farchon`)\n- The repos are truly independent with no shared contracts (just run separate campaigns)\n\n## Protocol\n\n### Step 1: ORIENT\n\n1. Check for existing workspace session: `.planning\u002Fworkspace\u002Fsession-{slug}.md` — resume if `status: active` or `needs-continue`\n2. If starting fresh: identify repos, verify each path is a git repo, read each repo's `CLAUDE.md`, check `.planning\u002Fcampaigns\u002F` for active campaigns (avoid collisions)\n3. **Load prior session context and start watcher**:\n   ```bash\n   node .citadel\u002Fscripts\u002Fmomentum-watch-start.cjs\n   node .citadel\u002Fscripts\u002Fmomentum-read.cjs\n   ```\n   Skip momentum injection if output is empty.\n\n### Step 2: DECOMPOSE\n\nBreak the direction into repo-scoped work items (one campaign per repo per wave). Table format: `# | Repo | Campaign Direction | Scope | Deps | Wave`.\n\n**Rules:** items with no deps → Wave 1; dependents → Wave 2+. Max 3 repo-campaigns per wave. Scope format: `{repo}:{path}`.\n\nFor each inter-wave dependency, specify the cross-repo contract: what the producer will produce, what the consumer expects, and where the contract lives (shared types package, OpenAPI spec, env var).\n\n### Step 3: WORKSPACE SESSION FILE\n\nCreate `.planning\u002Fworkspace\u002Fsession-{slug}.md` with frontmatter: `version`, `id`, `status: active`, `started`, `completed_at: null`, `direction`, `repos` (path + name + branch per repo), `wave_count`, `current_wave: 1`, `campaigns_total`, `campaigns_complete: 0`.\n\nBody sections: Direction, Repos table (name\u002Fpath\u002Fbranch\u002Fstatus), Work Queue (table from Step 2), Cross-Repo Contracts (producer\u002Fconsumer\u002Fcontract\u002Flocation), Wave Execution Log (per wave: status, campaigns, started, completed), Shared Context (discovery relay accumulation).\n\n### Step 4: WAVE EXECUTION\n\nFor each wave:\n\n#### 4a. Pre-flight\n- Verify all dependency campaigns from prior waves completed successfully\n- Check cross-repo contracts: did producer repos create the expected outputs?\n- If a dependency failed: park the dependent campaign, flag for user decision\n\n#### 4b. Spawn campaigns\nFor each repo-campaign in this wave:\n\n1. Create branch: `git checkout -b workspace\u002F{slug}\u002F{repo-name}`\n2. Spawn agent with direction: `\u002Farchon` for complex (3+ phases), `\u002Ffleet` if parallelizable, `\u002Fmarshal` or direct skill for simple (1-2 steps)\n3. Inject context: discovery briefs from prior waves, prior session context (re-read `momentum.json` via `node .citadel\u002Fscripts\u002Fmomentum-read.cjs`, inject as `=== PRIOR SESSION CONTEXT ===`, skip if empty), cross-repo contracts, relevant `CLAUDE.md` sections from other repos\n\n#### 4c. Collect results\nExtract HANDOFF blocks, compress into cross-repo discovery brief, write persistent discovery records:\n  ```bash\n  node .citadel\u002Fscripts\u002Fdiscovery-write.cjs \\\n    --session {session-slug} --agent {repo-name}-{campaign-type} \\\n    --wave {wave-number} --status {success|partial|failed} \\\n    --scope \"{repo-name}:{scope-path}\" --handoff \"{json-array}\" \\\n    --decisions \"{json-array}\" --files \"{json-array}\" --failures \"{json-array}\"\n  ```\n\n#### 4d. Discovery relay\nWrite `workspace\u002Fbriefs\u002Fwave{N}-{repo-name}.md` for each completed campaign.\nAlso write `workspace\u002Fbriefs\u002Fwave{N}-cross-repo.md` summarizing:\n- New API endpoints or types created\n- Config changes that affect other repos\n- Contract fulfillment status (did the producer deliver what was promised?)\n\n#### 4e. Contract verification\nFor each cross-repo contract: verify the producer created the expected output (file + export for types, route existence for endpoints). If verification fails, flag and do not proceed with consumers.\n\n#### 4f. Update session\nMark completed campaigns, update wave status, write discovery relay, advance `current_wave`.\n\n### Step 5: COMPLETION\n\n1. Run typecheck\u002Fbuild for each repo in isolation (build shared types package first if present)\n2. Set session `status: completed`, `completed_at: {ISO timestamp}`\n3. Run `node .citadel\u002Fscripts\u002Fmomentum-synthesize.cjs`\n4. List all branches created across repos with suggested merge order based on dependency graph\n5. Output HANDOFF\n\n## Fringe Cases\n\n- **Repo not a git repo:** Skip it. Report which repos were skipped and why.\n- **Repo has uncommitted changes:** Stash before branching. Record stash ref in session file.\n  Pop on completion or failure.\n- **Active campaign in target repo:** Do not start a second campaign. Report the conflict\n  and ask the user whether to wait, park the existing campaign, or merge scopes.\n- **`.planning\u002Fworkspace\u002F` does not exist:** Create it (and `workspace\u002Fbriefs\u002F`).\n- **Cross-repo contract broken:** Park all downstream campaigns. Report which contract\n  failed, which producer was responsible, and what the consumer expected. Do not\n  attempt to fix the producer -- surface the issue for the user or re-run the producer campaign.\n- **One repo fails, others succeed:** Mark the failed repo-campaign. Do not roll back\n  successful repos. The user decides whether to fix-and-continue or abandon.\n- **Repos on different machines or remotes:** Not supported. All repos must be locally\n  accessible. If a repo is remote-only, the user must clone it first.\n- **Monorepo with multiple packages:** Treat each package as a \"repo\" for scoping purposes.\n  Use `{monorepo}:{package-path}` as the scope identifier.\n\n## Contextual Gates\n\n**Disclosure:** \"Running multi-repo campaign across [repos]. Changes committed to each repo independently.\"\n**Reversibility:** red — coordinates changes across multiple repositories; cross-repo commits are hard to revert in bulk.\n**Trust gates:**\n- Familiar (5+ sessions): coordinates multi-repo campaigns autonomously; novices should use \u002Fmarshal per repo.\n\n## Quality Gates\n\n- [ ] All repos verified as accessible git repositories before starting\n- [ ] Work queue has no scope overlaps within the same repo\n- [ ] Cross-repo contracts specified for every inter-wave dependency\n- [ ] Discovery relay written after each wave\n- [ ] Contract verification run before spawning consumer campaigns\n- [ ] Each repo's typecheck\u002Fbuild passes independently after completion\n- [ ] Session file updated after every wave (not just at the end)\n- [ ] No campaigns left in `active` state on completion\n\n## Exit Protocol\n\n```\n---HANDOFF---\n- Workspace: {slug} -- {direction summary}\n- Repos: {N} repos, {M} campaigns across {W} waves\n- Results: {completed}\u002F{total} campaigns succeeded\n- Branches: {list branches ready for review}\n- Merge order: {suggested order based on dependency graph}\n- Unresolved: {any failed campaigns or broken contracts}\n---\n```\n",{"name":5,"effort":24,"license":15,"description":7,"auto-trigger":20,"last-updated":25,"user-invocable":26,"trigger_keywords":27},"high",1774742400000,true,[5,28,29,30,31,32,33,34],"multi-repo","cross-repo","across repos","multiple repos","coordinate repos","add redis and snowflake","split into repos","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fworkspace",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":26},[45,48,51],{"tool":46,"command":47},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill workspace",{"tool":49,"command":50},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill workspace",{"tool":52,"command":53},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill workspace","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fworkspace\u002FSKILL.md",[56,62],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"__benchmarks__\u002Fmulti-repo-direction.md","REFERENCE","参考文档",1102,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fworkspace\u002F__benchmarks__\u002Fmulti-repo-direction.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"__benchmarks__\u002Fno-repos-configured.md",739,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fworkspace\u002F__benchmarks__\u002Fno-repos-configured.md",[67,74,79,86,93,100],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":75,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]