[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CTGNQBVXCGJ72CGSERVM1C":3,"skill-same:01M6CTGNQBVXCGJ72CGSERVM1C":139},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":64},"01M6CTGNQBVXCGJ72CGSERVM1C","token-cost-ledger",null,"Tracks AI token usage and spend: logs entries, reports, checks budget and shows cost per feature. Use when reviewing AI spend or logging a session's cost.","vibbs\u002Fcompany-os","vibbs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7379149?v=4","01M6CT6M03CAS1H7RA89F3965B","Vibbs Dod","01M6CT6M4MY60C9FFQ3AAR2RSK",6,"MIT","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Fos\u002Fskills\u002Ftoken-cost-ledger\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000040","财务","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34],"cost","token cost ledger","report","logging","logs","Budget","check","session","use","log","reports","2026-11-10 10:12:30",false,"---\nname: token-cost-ledger\ndescription: \"Tracks AI token usage and spend: logs entries, reports, checks budget and shows cost per feature. Use when reviewing AI spend or logging a session's cost.\"\nruntimes:\n  claude:\n    user-invocable: true\n    argument-hint: \"[log | report | budget-check | feature-cost]\"\n---\n\n# Token Cost Ledger\n\n## Reference\n- **ID**: S-OPS-08\n- **Category**: Ops & Risk\n- **Inputs**: token usage data, company.config.yaml (ai.cost_budget_monthly, ai.cost_tracking_enabled, ai.cost_alert_threshold_percent)\n- **Outputs**: ledger entries in `cogs\u002Fai-ledger\u002Fentries.jsonl`, summary in `cogs\u002Fai-ledger\u002Fsummary.md`\n- **Used by**: Ops & Risk Agent, Orchestrator Agent (post-ship advisory)\n- **Tool scripts**: `.\u002Ftools\u002Fops\u002Ftoken-ledger.sh`\n\n## Purpose\n\nTrack AI token consumption and costs as Cost of Goods Sold (COGS). Provides a lightweight, git-trackable cost accounting system for solo developers using AI agents. Supports logging individual entries, generating period summaries, showing per-feature cost breakdowns, monitoring budget health, and exporting data for financial reporting.\n\n## When to Use\n\n- After completing a ship flow or significant AI-assisted work session\n- When reviewing monthly AI spend against budget\n- When preparing investor updates or financial reports (feeds into pricing-unit-economics)\n- When deciding whether to use Opus vs Sonnet for a task (cost awareness)\n- When company.stage transitions (budgets should be reassessed)\n\n## Procedure\n\n### Step 1: Check Configuration\n\nRead `company.config.yaml` and extract:\n- `ai.cost_budget_monthly` — monthly spend cap\n- `ai.cost_tracking_enabled` — whether tracking is active (default: true if budget is set)\n- `ai.cost_alert_threshold_percent` — warning threshold (default: 80)\n\nIf `ai.cost_budget_monthly` is empty, suggest the user set a budget with guidance by stage:\n- **idea**: $25-50\u002Fmonth (exploration, light usage)\n- **mvp**: $50-200\u002Fmonth (active development, ship flows)\n- **growth**: $200-1000\u002Fmonth (multiple features, more agent usage)\n- **scale**: $1000+\u002Fmonth (heavy automation, multiple concurrent flows)\n\n### Step 2: Subcommand Routing\n\n#### Subcommand: `log`\n\nLog a token cost entry:\n\n```bash\n.\u002Ftools\u002Fops\u002Ftoken-ledger.sh log \\\n  --model \"claude-sonnet-4-20250514\" \\\n  --input-tokens 12500 \\\n  --output-tokens 3200 \\\n  --cache-read 8000 \\\n  --cache-write 1500 \\\n  --agent engineering \\\n  --category ship-flow \\\n  --feature PRD-001 \\\n  --session \"ship-user-auth-20260301\" \\\n  --notes \"RFC generation for user auth\"\n```\n\nIf the user provides raw numbers from their session, help them fill in the fields. Cost is auto-calculated from the model rates in `standards\u002Fops\u002Ftoken-cost-tracking.md` when not provided via `--cost`.\n\nAfter logging, the tool shows budget impact:\n```\nEntry logged: $0.08\n  Budget: $13.82 \u002F $100.00 (13.8%)\n```\n\n#### Subcommand: `report`\n\nGenerate a cost report:\n\n```bash\n.\u002Ftools\u002Fops\u002Ftoken-ledger.sh summary --period monthly\n```\n\nPresent the results with analysis:\n1. Total spend by category (ship-flow, agent-session, research, ad-hoc)\n2. Total spend by model (which models are costing the most)\n3. Total spend by agent (which agents are most expensive)\n4. Budget health with color coding\n\nAlso regenerates `cogs\u002Fai-ledger\u002Fsummary.md` for human review.\n\nIf the user has investor reporting set up, note that token costs feed into the infrastructure cost line item in `standards\u002Fops\u002Finvestor-reporting-template.md`.\n\n#### Subcommand: `budget-check`\n\nQuick budget health check:\n\n```bash\n.\u002Ftools\u002Fops\u002Ftoken-ledger.sh budget\n```\n\nPresent results:\n- Current month spend vs budget\n- Projected end-of-month spend (based on daily average)\n- Recommendation: stay the course \u002F reduce usage \u002F increase budget\n\n#### Subcommand: `feature-cost`\n\nShow total cost of building a specific feature:\n\n```bash\n.\u002Ftools\u002Fops\u002Ftoken-ledger.sh feature-cost PRD-001\n```\n\nPresent the feature cost report:\n- Total cost with entry count\n- Breakdown by agent (who spent what)\n- Breakdown by phase (ship-flow, research, etc.)\n- Timeline showing each entry chronologically\n\nThis is the key command for understanding \"how much did this feature cost to build?\"\n\n### Step 3: Cost Optimization Suggestions\n\nBased on the report data, suggest optimizations:\n- **Model downgrade**: If Opus is used for template-driven tasks, suggest Sonnet\n- **Cache utilization**: If cache_read_tokens is consistently 0, suggest enabling prompt caching\n- **Category rebalancing**: If research spend exceeds ship-flow spend, suggest more focused sessions\n- **Budget adjustment**: If consistently under 50% budget, suggest reducing to free up capital\n\nRefer to the full optimization playbook in `standards\u002Fops\u002Ftoken-cost-tracking.md`.\n\n### Step 4: Cross-Reference with Unit Economics\n\nWhen generating reports, if artifacts exist in `artifacts\u002Ffinance\u002F`, note how AI COGS relates to:\n- Gross margin (AI costs reduce margin)\n- CAC (AI-assisted customer acquisition costs)\n- Infrastructure costs in the investor template\n\n### Typical Session Cost Estimates\n\nReference ranges for planning (based on Claude Opus\u002FSonnet pricing):\n\n| Flow | Typical Input Tokens | Typical Output Tokens | Estimated Cost |\n|------|---------------------|-----------------------|---------------|\n| `\u002Fship` (full) | 150-300K | 30-60K | $3-8 |\n| `\u002Frapid-prototype` | 50-100K | 15-30K | $1-3 |\n| `\u002Fcode-review` | 30-80K | 10-20K | $0.50-2 |\n| `\u002Fstatus` | 10-30K | 5-10K | $0.20-0.50 |\n| Single skill | 20-50K | 5-15K | $0.30-1 |\n| Agent sub-delegation | 15-40K per agent | 5-10K per agent | $0.25-1 per agent |\n\nThese are estimates only. Actual costs depend on codebase size, artifact count, and conversation length.\n\n## Cross-References\n\n- **pricing-unit-economics** — consumes AI cost data for infrastructure cost calculations\n- **ship** — advisory integration at Step 7.5 (suggest logging session cost after release)\n- **investor-reporting-template** — AI COGS feeds into burn rate reporting\n\n## Quality Checklist\n\n- [ ] company.config.yaml was read for budget and tracking config\n- [ ] Ledger entry has all required fields (timestamp, model, tokens, cost, category)\n- [ ] Cost calculation matches model rate table (if auto-calculated)\n- [ ] Budget status uses color coding (green\u002Fyellow\u002Fred)\n- [ ] Summary report regenerates `cogs\u002Fai-ledger\u002Fsummary.md`\n- [ ] Empty ledger is handled gracefully\n- [ ] Feature ID is tagged when applicable (especially during ship flows)\n- [ ] Cross-reference to unit economics noted when applicable\n","# Token Cost Ledger\n\n## Reference\n- **ID**: S-OPS-08\n- **Category**: Ops & Risk\n- **Inputs**: token usage data, company.config.yaml (ai.cost_budget_monthly, ai.cost_tracking_enabled, ai.cost_alert_threshold_percent)\n- **Outputs**: ledger entries in `cogs\u002Fai-ledger\u002Fentries.jsonl`, summary in `cogs\u002Fai-ledger\u002Fsummary.md`\n- **Used by**: Ops & Risk Agent, Orchestrator Agent (post-ship advisory)\n- **Tool scripts**: `.\u002Ftools\u002Fops\u002Ftoken-ledger.sh`\n\n## Purpose\n\nTrack AI token consumption and costs as Cost of Goods Sold (COGS). Provides a lightweight, git-trackable cost accounting system for solo developers using AI agents. Supports logging individual entries, generating period summaries, showing per-feature cost breakdowns, monitoring budget health, and exporting data for financial reporting.\n\n## When to Use\n\n- After completing a ship flow or significant AI-assisted work session\n- When reviewing monthly AI spend against budget\n- When preparing investor updates or financial reports (feeds into pricing-unit-economics)\n- When deciding whether to use Opus vs Sonnet for a task (cost awareness)\n- When company.stage transitions (budgets should be reassessed)\n\n## Procedure\n\n### Step 1: Check Configuration\n\nRead `company.config.yaml` and extract:\n- `ai.cost_budget_monthly` — monthly spend cap\n- `ai.cost_tracking_enabled` — whether tracking is active (default: true if budget is set)\n- `ai.cost_alert_threshold_percent` — warning threshold (default: 80)\n\nIf `ai.cost_budget_monthly` is empty, suggest the user set a budget with guidance by stage:\n- **idea**: $25-50\u002Fmonth (exploration, light usage)\n- **mvp**: $50-200\u002Fmonth (active development, ship flows)\n- **growth**: $200-1000\u002Fmonth (multiple features, more agent usage)\n- **scale**: $1000+\u002Fmonth (heavy automation, multiple concurrent flows)\n\n### Step 2: Subcommand Routing\n\n#### Subcommand: `log`\n\nLog a token cost entry:\n\n```bash\n.\u002Ftools\u002Fops\u002Ftoken-ledger.sh log \\\n  --model \"claude-sonnet-4-20250514\" \\\n  --input-tokens 12500 \\\n  --output-tokens 3200 \\\n  --cache-read 8000 \\\n  --cache-write 1500 \\\n  --agent engineering \\\n  --category ship-flow \\\n  --feature PRD-001 \\\n  --session \"ship-user-auth-20260301\" \\\n  --notes \"RFC generation for user auth\"\n```\n\nIf the user provides raw numbers from their session, help them fill in the fields. Cost is auto-calculated from the model rates in `standards\u002Fops\u002Ftoken-cost-tracking.md` when not provided via `--cost`.\n\nAfter logging, the tool shows budget impact:\n```\nEntry logged: $0.08\n  Budget: $13.82 \u002F $100.00 (13.8%)\n```\n\n#### Subcommand: `report`\n\nGenerate a cost report:\n\n```bash\n.\u002Ftools\u002Fops\u002Ftoken-ledger.sh summary --period monthly\n```\n\nPresent the results with analysis:\n1. Total spend by category (ship-flow, agent-session, research, ad-hoc)\n2. Total spend by model (which models are costing the most)\n3. Total spend by agent (which agents are most expensive)\n4. Budget health with color coding\n\nAlso regenerates `cogs\u002Fai-ledger\u002Fsummary.md` for human review.\n\nIf the user has investor reporting set up, note that token costs feed into the infrastructure cost line item in `standards\u002Fops\u002Finvestor-reporting-template.md`.\n\n#### Subcommand: `budget-check`\n\nQuick budget health check:\n\n```bash\n.\u002Ftools\u002Fops\u002Ftoken-ledger.sh budget\n```\n\nPresent results:\n- Current month spend vs budget\n- Projected end-of-month spend (based on daily average)\n- Recommendation: stay the course \u002F reduce usage \u002F increase budget\n\n#### Subcommand: `feature-cost`\n\nShow total cost of building a specific feature:\n\n```bash\n.\u002Ftools\u002Fops\u002Ftoken-ledger.sh feature-cost PRD-001\n```\n\nPresent the feature cost report:\n- Total cost with entry count\n- Breakdown by agent (who spent what)\n- Breakdown by phase (ship-flow, research, etc.)\n- Timeline showing each entry chronologically\n\nThis is the key command for understanding \"how much did this feature cost to build?\"\n\n### Step 3: Cost Optimization Suggestions\n\nBased on the report data, suggest optimizations:\n- **Model downgrade**: If Opus is used for template-driven tasks, suggest Sonnet\n- **Cache utilization**: If cache_read_tokens is consistently 0, suggest enabling prompt caching\n- **Category rebalancing**: If research spend exceeds ship-flow spend, suggest more focused sessions\n- **Budget adjustment**: If consistently under 50% budget, suggest reducing to free up capital\n\nRefer to the full optimization playbook in `standards\u002Fops\u002Ftoken-cost-tracking.md`.\n\n### Step 4: Cross-Reference with Unit Economics\n\nWhen generating reports, if artifacts exist in `artifacts\u002Ffinance\u002F`, note how AI COGS relates to:\n- Gross margin (AI costs reduce margin)\n- CAC (AI-assisted customer acquisition costs)\n- Infrastructure costs in the investor template\n\n### Typical Session Cost Estimates\n\nReference ranges for planning (based on Claude Opus\u002FSonnet pricing):\n\n| Flow | Typical Input Tokens | Typical Output Tokens | Estimated Cost |\n|------|---------------------|-----------------------|---------------|\n| `\u002Fship` (full) | 150-300K | 30-60K | $3-8 |\n| `\u002Frapid-prototype` | 50-100K | 15-30K | $1-3 |\n| `\u002Fcode-review` | 30-80K | 10-20K | $0.50-2 |\n| `\u002Fstatus` | 10-30K | 5-10K | $0.20-0.50 |\n| Single skill | 20-50K | 5-15K | $0.30-1 |\n| Agent sub-delegation | 15-40K per agent | 5-10K per agent | $0.25-1 per agent |\n\nThese are estimates only. Actual costs depend on codebase size, artifact count, and conversation length.\n\n## Cross-References\n\n- **pricing-unit-economics** — consumes AI cost data for infrastructure cost calculations\n- **ship** — advisory integration at Step 7.5 (suggest logging session cost after release)\n- **investor-reporting-template** — AI COGS feeds into burn rate reporting\n\n## Quality Checklist\n\n- [ ] company.config.yaml was read for budget and tracking config\n- [ ] Ledger entry has all required fields (timestamp, model, tokens, cost, category)\n- [ ] Cost calculation matches model rate table (if auto-calculated)\n- [ ] Budget status uses color coding (green\u002Fyellow\u002Fred)\n- [ ] Summary report regenerates `cogs\u002Fai-ledger\u002Fsummary.md`\n- [ ] Empty ledger is handled gracefully\n- [ ] Feature ID is tagged when applicable (especially during ship flows)\n- [ ] Cross-reference to unit economics noted when applicable\n",{"name":5,"runtimes":40,"description":7},{"claude":41},{"argument-hint":42,"user-invocable":43},"[log | report | budget-check | feature-cost]",true,"main","e842fb6d0e04360c47db78bc2e2e2987314d64d4","os\u002Fskills\u002Ftoken-cost-ledger",2,"https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os","https:\u002F\u002Fgithub.com\u002Fvibbs","Principal Engineer · Applied AI · building ArcAI @ GrowthArc","2026-10-21 02:08:08",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":43},[54,57,60],{"tool":55,"command":56},"npx","npx skills add vibbs\u002Fcompany-os --skill token-cost-ledger",{"tool":58,"command":59},"bunx","bunx skills add vibbs\u002Fcompany-os --skill token-cost-ledger",{"tool":61,"command":62},"pnpm","pnpm dlx skills add vibbs\u002Fcompany-os --skill token-cost-ledger","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Fos\u002Fskills\u002Ftoken-cost-ledger\u002FSKILL.md",[65,71,75,79,83,87,91,95,99,103,107,111,115,119,123,127,131,135],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"bmad-skill-manifest.yaml","REFERENCE","参考文档",12,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fbmad-skill-manifest.yaml",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"steps\u002Fstep-01-init.md",5785,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-01-init.md",{"path":76,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":77,"sourceHtmlUrl":78},"steps\u002Fstep-01b-continue.md",4862,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-01b-continue.md",{"path":80,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":81,"sourceHtmlUrl":82},"steps\u002Fstep-02-discovery.md",6803,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-02-discovery.md",{"path":84,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":85,"sourceHtmlUrl":86},"steps\u002Fstep-03-core-experience.md",8292,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-03-core-experience.md",{"path":88,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":89,"sourceHtmlUrl":90},"steps\u002Fstep-04-emotional-response.md",8331,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-04-emotional-response.md",{"path":92,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":93,"sourceHtmlUrl":94},"steps\u002Fstep-05-inspiration.md",8733,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-05-inspiration.md",{"path":96,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":97,"sourceHtmlUrl":98},"steps\u002Fstep-06-design-system.md",8833,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-06-design-system.md",{"path":100,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":101,"sourceHtmlUrl":102},"steps\u002Fstep-07-defining-experience.md",8835,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-07-defining-experience.md",{"path":104,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":105,"sourceHtmlUrl":106},"steps\u002Fstep-08-visual-foundation.md",8435,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-08-visual-foundation.md",{"path":108,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":109,"sourceHtmlUrl":110},"steps\u002Fstep-09-design-directions.md",8620,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-09-design-directions.md",{"path":112,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":113,"sourceHtmlUrl":114},"steps\u002Fstep-10-user-journeys.md",8451,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-10-user-journeys.md",{"path":116,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":117,"sourceHtmlUrl":118},"steps\u002Fstep-11-component-strategy.md",8744,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-11-component-strategy.md",{"path":120,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":121,"sourceHtmlUrl":122},"steps\u002Fstep-12-ux-patterns.md",7996,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-12-ux-patterns.md",{"path":124,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":125,"sourceHtmlUrl":126},"steps\u002Fstep-13-responsive-accessibility.md",9096,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-13-responsive-accessibility.md",{"path":128,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":129,"sourceHtmlUrl":130},"steps\u002Fstep-14-complete.md",6834,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fsteps\u002Fstep-14-complete.md",{"path":132,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":133,"sourceHtmlUrl":134},"ux-design-template.md",236,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fux-design-template.md",{"path":136,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":137,"sourceHtmlUrl":138},"workflow.md",1421,"https:\u002F\u002Fgithub.com\u002Fcodeasice\u002Fagentcore-presentation\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fgds-create-ux-design\u002Fworkflow.md",[140,149,157,167,183,201],{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":35},"01M6CTHBW1E64ECYGD105N4S5E","typo-field","Fixture skill with a misspelled top-level field.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Ftypo-field\u002FSKILL.md",[],[147,148],"typo field","fixture skill",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":35},"01M6CTHABTV8FKVDHFMMKPAV51","spaced-comments","Fixture skill with comments and spaces after block keys.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fspaced-comments\u002FSKILL.md",[],[156,148],"spaced comments",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":35},"01M6CTH8MHC14KB65ZDHYBJW1N","crlf-comments","Fixture skill with Windows line endings.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fcrlf-comments\u002FSKILL.md",[],[164,165,166,148],"crlf comments","CRLF","windows",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":35},"01M6CTH6TBKTDP9G8QB1Z2K0TY","claude-fields","Fixture skill using top-level fields Claude Code documents.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fclaude-fields\u002FSKILL.md",[],[174,175,176,177,178,179,148,180,181,182],"claude fields","explore","documents","src","grep","read","Bash","code","testing",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":194,"publishedAt":35},"01M6CTH46BGKXH80RWS876Y2CW","workflow-router","Maps an objective to the artifacts, stages and agents it needs. Use when deciding what happens next or which agents to involve.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Fos\u002Fskills\u002Fworkflow-router\u002FSKILL.md",[189],{"categoryNo":190,"categoryName":191,"taxonomyType":192,"taxonomyTypeDesc":193},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[195,196,197,198,199,32,200],"workflow","router","workflow router","next","maps","artifacts",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":207,"publishedAt":35},"01M6CTH27653SRVP2FMEQN3J5B","weekly-review","Summarizes your week: what shipped, AI spend, support themes, security health and next priorities. Use at the end of each week.","https:\u002F\u002Fgithub.com\u002Fvibbs\u002Fcompany-os\u002Fblob\u002Fmain\u002Fos\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[208,209,210,198,32,211,212,213,214],"weekly review","review","priorities","health","save","support","security"]