[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CRZMHAMX71CH6A0FRE4TYH":3,"skill-same:01M7CRZMHAMX71CH6A0FRE4TYH":53},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7CRZMHAMX71CH6A0FRE4TYH","learning-aggregator-ci",null,"[Beta] CI-only learning aggregation workflow using gh-aw (GitHub Agentic Workflows). Scans .learnings\u002F files on a schedule, groups entries by pattern_key, identifies promotion-ready patterns, and posts a gap report as a PR or issue comment. Use when: you want automated cross-session pattern detection in CI\u002Fheadless pipelines without interactive prompts. For interactive use, use learning-aggregator.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-pskoett-ai-skills\u002Fskills\u002Flearning-aggregator-ci\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: learning-aggregator-ci\ndescription: \"[Beta] CI-only learning aggregation workflow using gh-aw (GitHub Agentic Workflows). Scans .learnings\u002F files on a schedule, groups entries by pattern_key, identifies promotion-ready patterns, and posts a gap report as a PR or issue comment. Use when: you want automated cross-session pattern detection in CI\u002Fheadless pipelines without interactive prompts. For interactive use, use learning-aggregator.\"\n---\n\n# Learning Aggregator CI\n\n## Install\n\n```bash\ngh skill install pskoett\u002Fpskoett-skills learning-aggregator-ci\n```\n\nFor interactive sessions, use:\n\n```bash\ngh skill install pskoett\u002Fpskoett-skills learning-aggregator\n```\n\nFallback using the Agent Skills CLI:\n\n```bash\nnpx skills add pskoett\u002Fpskoett-skills\u002Fskills\u002Flearning-aggregator-ci\nnpx skills add pskoett\u002Fpskoett-skills\u002Fskills\u002Flearning-aggregator\n```\n\n## Purpose\n\nRuns the outer loop's **inspect** step in CI. Reads accumulated `.learnings\u002F` files, groups entries by `pattern_key`, computes cross-session recurrence, and produces a ranked gap report — all without human interaction.\n\nThe interactive `learning-aggregator` skill is designed for in-session use where the user can review and act on findings immediately. This CI variant runs on a schedule (weekly, per-sprint, or on-demand) and posts its findings as a GitHub issue comment for async review.\n\n## Context Limitation (Important)\n\nCI agents do not have session context. They cannot see what the user is currently working on or what task area is relevant. The CI variant scans **all** `.learnings\u002F` entries without relevance filtering. The gap report is comprehensive rather than targeted.\n\n## Prerequisites\n\n- GitHub Actions enabled on the repository\n- `gh` CLI authenticated with repo access\n- `gh-aw` extension installed (`gh extension install github\u002Fgh-aw`, v0.40.1+)\n- `.learnings\u002F` directory with structured entries from `self-improvement`\n\n## CI Contract\n\nHard rules for headless execution:\n\n1. **Read-only** — do not modify `.learnings\u002F` files, project instruction files (CLAUDE.md, AGENTS.md, .github\u002Fcopilot-instructions.md), or any repo files\n2. **Headless** — no interactive prompts, no approval gates\n3. **Structured output** — emit findings as YAML under `learning_aggregator_ci` key\n4. **Single comment** — post one consolidated comment per run, not per finding\n5. **Deterministic** — same `.learnings\u002F` state produces the same gap report\n\n## Authoring Workflow (gh-aw)\n\n1. Copy `references\u002Fworkflow-example.md` into `.github\u002Fworkflows\u002Flearning-aggregator-ci.md`\n2. Customize the schedule for your cadence (supports fuzzy schedules like `weekly on mondays`)\n3. Validate: `gh aw compile` (optionally add `--actionlint --zizmor` for full security scan)\n4. Push to enable\n\n### Persistence and Chaining\n\n- **`cache-memory:`** stores aggregation state (pattern groups, recurrence counts) across runs. Survives up to 90 days in Actions cache. Avoids re-scanning unchanged entries on every run.\n- **`call-workflow:`** triggers `eval-creator-ci` after aggregation completes to create evals from newly promoted patterns. Compile-time fan-out with proper dependency wiring.\n- **`upload-artifact:`** persists the gap report YAML for consumption by downstream workflows or human review.\n\n## Workflow Rules\n\nThe CI agent follows these rules in order:\n\n1. Read all files in `.learnings\u002F`: `LEARNINGS.md`, `ERRORS.md`, `FEATURE_REQUESTS.md`\n2. Parse each entry's metadata: `Pattern-Key`, `Recurrence-Count`, `First-Seen`, `Last-Seen`, `Priority`, `Status`, `Area`, `Related Files`, `Tags`\n3. Group entries by `Pattern-Key` (exact match only — no fuzzy grouping in CI)\n4. For each group: sum recurrences, count distinct tasks, compute time window, collect evidence\n5. Flag entries without `Pattern-Key` as ungrouped\n6. Classify each group's gap type: knowledge gap, tool gap, skill gap, ambiguity, or reasoning failure\n7. Rank groups by: promotion-ready first, then approaching threshold, then by priority (critical > high > medium > low)\n8. Emit structured YAML under key `learning_aggregator_ci`\n9. Post gap report as a comment on the triggering issue or as a new issue if running on schedule\n10. Do not modify repository files\n\n## Output Schema\n\n```yaml\nlearning_aggregator_ci:\n  version: \"0.1.0\"\n  source:\n    run_id: \"\u003Cworkflow run ID>\"\n    trigger: \"schedule | workflow_dispatch | issue_comment\"\n    scan_date: \"YYYY-MM-DD\"\n  scan:\n    entries_total: 42\n    entries_with_pattern_key: 35\n    entries_ungrouped: 7\n    patterns_found: 18\n    promotion_ready: 3\n    approaching_threshold: 5\n  promotion_ready:\n    - pattern_key: \"harden.input_validation\"\n      recurrence_count: 5\n      distinct_tasks: 3\n      window_days: 21\n      priority: \"high\"\n      gap_type: \"knowledge_gap\"\n      area: \"backend\"\n      evidence:\n        - \"LRN-20260301-001: Missing bounds check on pagination params\"\n        - \"ERR-20260308-002: Unconstrained string length caused OOM\"\n        - \"LRN-20260315-003: API params not validated before DB query\"\n      recommended_action: \"Add to project instruction files: Always validate and bound-check external inputs before use\"\n      eval_candidate: true\n  approaching:\n    - pattern_key: \"simplify.dead_code\"\n      recurrence_count: 2\n      distinct_tasks: 1\n      priority: \"low\"\n      needs: \"1 more distinct task\"\n  ungrouped:\n    - id: \"LRN-20260320-005\"\n      summary: \"Discovered undocumented rate limit on external API\"\n      recommendation: \"Assign pattern_key for future tracking\"\n  stale:\n    - pattern_key: \"harden.error_handling\"\n      last_seen: \"2025-12-01\"\n      recommendation: \"Dismiss — not seen in 90+ days\"\n  summary:\n    promotion_ready_total: 3\n    approaching_total: 5\n    ungrouped_total: 7\n    stale_total: 1\n    followup_required: true\n```\n\n## Recommended Outputs\n\n| Output | Destination | Content |\n|--------|------------|---------|\n| Gap report | Issue comment or new issue | Human-readable summary with promotion candidates and evidence |\n| YAML artifact | Workflow artifact | Machine-readable `learning_aggregator_ci` payload |\n| Check annotation | Check run summary | Count of promotion-ready and approaching patterns |\n\n## Trigger Configuration\n\n**Recommended: weekly schedule + manual dispatch**\n\n```yaml\non:\n  schedule:\n    - cron: '0 9 * * 1'  # Monday 9am UTC\n  workflow_dispatch:\n  issue_comment:\n    types: [created]\n```\n\nThe schedule ensures regular outer-loop cadence. Manual dispatch allows on-demand runs after incidents or sprints. Issue comment trigger allows `\u002Faggregate-learnings` commands.\n\n## Integration with Other Skills\n\n### Upstream (feeds from)\n- `self-improvement` and `self-improvement-ci` — produce `.learnings\u002F` entries\n- `simplify-and-harden-ci` — produces `learning_loop.candidates` consumed by self-improvement-ci\n\n### Downstream (feeds into)\n- **harness-updater** (interactive) — takes promotion-ready patterns from the gap report and applies them\n- **eval-creator-ci** — takes eval candidates and creates permanent test cases\n- **Human review** — gap report posted as issue comment for team triage\n\n### Data Flow\n\n```\nself-improvement → .learnings\u002F*.md\n                       ↓\n              learning-aggregator-ci (scheduled)\n                       ↓\n              gap report (issue comment + artifact)\n                       ↓\n              harness-updater (interactive, human-gated)\n                       ↓\n              eval-creator-ci (creates evals from promoted patterns)\n```\n\n## Differences from Interactive Version\n\n| Aspect | Interactive (`learning-aggregator`) | CI (`learning-aggregator-ci`) |\n|--------|------|------|\n| Trigger | Manual or session-start | Scheduled cron or workflow_dispatch |\n| Relevance filter | Filters by current task area | Scans all entries (no task context) |\n| Grouping | Conservative + area\u002Ftag matching | Pattern-key exact match only |\n| Output | In-session gap report | Issue comment + YAML artifact |\n| Human interaction | User reviews inline | Async review via GitHub |\n| Scope | Current session context | Full .learnings\u002F history |\n","# Learning Aggregator CI\n\n## Install\n\n```bash\ngh skill install pskoett\u002Fpskoett-skills learning-aggregator-ci\n```\n\nFor interactive sessions, use:\n\n```bash\ngh skill install pskoett\u002Fpskoett-skills learning-aggregator\n```\n\nFallback using the Agent Skills CLI:\n\n```bash\nnpx skills add pskoett\u002Fpskoett-skills\u002Fskills\u002Flearning-aggregator-ci\nnpx skills add pskoett\u002Fpskoett-skills\u002Fskills\u002Flearning-aggregator\n```\n\n## Purpose\n\nRuns the outer loop's **inspect** step in CI. Reads accumulated `.learnings\u002F` files, groups entries by `pattern_key`, computes cross-session recurrence, and produces a ranked gap report — all without human interaction.\n\nThe interactive `learning-aggregator` skill is designed for in-session use where the user can review and act on findings immediately. This CI variant runs on a schedule (weekly, per-sprint, or on-demand) and posts its findings as a GitHub issue comment for async review.\n\n## Context Limitation (Important)\n\nCI agents do not have session context. They cannot see what the user is currently working on or what task area is relevant. The CI variant scans **all** `.learnings\u002F` entries without relevance filtering. The gap report is comprehensive rather than targeted.\n\n## Prerequisites\n\n- GitHub Actions enabled on the repository\n- `gh` CLI authenticated with repo access\n- `gh-aw` extension installed (`gh extension install github\u002Fgh-aw`, v0.40.1+)\n- `.learnings\u002F` directory with structured entries from `self-improvement`\n\n## CI Contract\n\nHard rules for headless execution:\n\n1. **Read-only** — do not modify `.learnings\u002F` files, project instruction files (CLAUDE.md, AGENTS.md, .github\u002Fcopilot-instructions.md), or any repo files\n2. **Headless** — no interactive prompts, no approval gates\n3. **Structured output** — emit findings as YAML under `learning_aggregator_ci` key\n4. **Single comment** — post one consolidated comment per run, not per finding\n5. **Deterministic** — same `.learnings\u002F` state produces the same gap report\n\n## Authoring Workflow (gh-aw)\n\n1. Copy `references\u002Fworkflow-example.md` into `.github\u002Fworkflows\u002Flearning-aggregator-ci.md`\n2. Customize the schedule for your cadence (supports fuzzy schedules like `weekly on mondays`)\n3. Validate: `gh aw compile` (optionally add `--actionlint --zizmor` for full security scan)\n4. Push to enable\n\n### Persistence and Chaining\n\n- **`cache-memory:`** stores aggregation state (pattern groups, recurrence counts) across runs. Survives up to 90 days in Actions cache. Avoids re-scanning unchanged entries on every run.\n- **`call-workflow:`** triggers `eval-creator-ci` after aggregation completes to create evals from newly promoted patterns. Compile-time fan-out with proper dependency wiring.\n- **`upload-artifact:`** persists the gap report YAML for consumption by downstream workflows or human review.\n\n## Workflow Rules\n\nThe CI agent follows these rules in order:\n\n1. Read all files in `.learnings\u002F`: `LEARNINGS.md`, `ERRORS.md`, `FEATURE_REQUESTS.md`\n2. Parse each entry's metadata: `Pattern-Key`, `Recurrence-Count`, `First-Seen`, `Last-Seen`, `Priority`, `Status`, `Area`, `Related Files`, `Tags`\n3. Group entries by `Pattern-Key` (exact match only — no fuzzy grouping in CI)\n4. For each group: sum recurrences, count distinct tasks, compute time window, collect evidence\n5. Flag entries without `Pattern-Key` as ungrouped\n6. Classify each group's gap type: knowledge gap, tool gap, skill gap, ambiguity, or reasoning failure\n7. Rank groups by: promotion-ready first, then approaching threshold, then by priority (critical > high > medium > low)\n8. Emit structured YAML under key `learning_aggregator_ci`\n9. Post gap report as a comment on the triggering issue or as a new issue if running on schedule\n10. Do not modify repository files\n\n## Output Schema\n\n```yaml\nlearning_aggregator_ci:\n  version: \"0.1.0\"\n  source:\n    run_id: \"\u003Cworkflow run ID>\"\n    trigger: \"schedule | workflow_dispatch | issue_comment\"\n    scan_date: \"YYYY-MM-DD\"\n  scan:\n    entries_total: 42\n    entries_with_pattern_key: 35\n    entries_ungrouped: 7\n    patterns_found: 18\n    promotion_ready: 3\n    approaching_threshold: 5\n  promotion_ready:\n    - pattern_key: \"harden.input_validation\"\n      recurrence_count: 5\n      distinct_tasks: 3\n      window_days: 21\n      priority: \"high\"\n      gap_type: \"knowledge_gap\"\n      area: \"backend\"\n      evidence:\n        - \"LRN-20260301-001: Missing bounds check on pagination params\"\n        - \"ERR-20260308-002: Unconstrained string length caused OOM\"\n        - \"LRN-20260315-003: API params not validated before DB query\"\n      recommended_action: \"Add to project instruction files: Always validate and bound-check external inputs before use\"\n      eval_candidate: true\n  approaching:\n    - pattern_key: \"simplify.dead_code\"\n      recurrence_count: 2\n      distinct_tasks: 1\n      priority: \"low\"\n      needs: \"1 more distinct task\"\n  ungrouped:\n    - id: \"LRN-20260320-005\"\n      summary: \"Discovered undocumented rate limit on external API\"\n      recommendation: \"Assign pattern_key for future tracking\"\n  stale:\n    - pattern_key: \"harden.error_handling\"\n      last_seen: \"2025-12-01\"\n      recommendation: \"Dismiss — not seen in 90+ days\"\n  summary:\n    promotion_ready_total: 3\n    approaching_total: 5\n    ungrouped_total: 7\n    stale_total: 1\n    followup_required: true\n```\n\n## Recommended Outputs\n\n| Output | Destination | Content |\n|--------|------------|---------|\n| Gap report | Issue comment or new issue | Human-readable summary with promotion candidates and evidence |\n| YAML artifact | Workflow artifact | Machine-readable `learning_aggregator_ci` payload |\n| Check annotation | Check run summary | Count of promotion-ready and approaching patterns |\n\n## Trigger Configuration\n\n**Recommended: weekly schedule + manual dispatch**\n\n```yaml\non:\n  schedule:\n    - cron: '0 9 * * 1'  # Monday 9am UTC\n  workflow_dispatch:\n  issue_comment:\n    types: [created]\n```\n\nThe schedule ensures regular outer-loop cadence. Manual dispatch allows on-demand runs after incidents or sprints. Issue comment trigger allows `\u002Faggregate-learnings` commands.\n\n## Integration with Other Skills\n\n### Upstream (feeds from)\n- `self-improvement` and `self-improvement-ci` — produce `.learnings\u002F` entries\n- `simplify-and-harden-ci` — produces `learning_loop.candidates` consumed by self-improvement-ci\n\n### Downstream (feeds into)\n- **harness-updater** (interactive) — takes promotion-ready patterns from the gap report and applies them\n- **eval-creator-ci** — takes eval candidates and creates permanent test cases\n- **Human review** — gap report posted as issue comment for team triage\n\n### Data Flow\n\n```\nself-improvement → .learnings\u002F*.md\n                       ↓\n              learning-aggregator-ci (scheduled)\n                       ↓\n              gap report (issue comment + artifact)\n                       ↓\n              harness-updater (interactive, human-gated)\n                       ↓\n              eval-creator-ci (creates evals from promoted patterns)\n```\n\n## Differences from Interactive Version\n\n| Aspect | Interactive (`learning-aggregator`) | CI (`learning-aggregator-ci`) |\n|--------|------|------|\n| Trigger | Manual or session-start | Scheduled cron or workflow_dispatch |\n| Relevance filter | Filters by current task area | Scans all entries (no task context) |\n| Grouping | Conservative + area\u002Ftag matching | Pattern-key exact match only |\n| Output | In-session gap report | Issue comment + YAML artifact |\n| Human interaction | User reviews inline | Async review via GitHub |\n| Scope | Current session context | Full .learnings\u002F history |\n",{"name":5,"description":7},"main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-pskoett-ai-skills\u002Fskills\u002Flearning-aggregator-ci",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill learning-aggregator-ci",{"tool":39,"command":40},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill learning-aggregator-ci",{"tool":42,"command":43},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill learning-aggregator-ci","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-pskoett-ai-skills\u002Fskills\u002Flearning-aggregator-ci\u002FSKILL.md",true,[47],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fworkflow-example.md","REFERENCE","参考文档",3740,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-pskoett-ai-skills\u002Fskills\u002Flearning-aggregator-ci\u002Freferences\u002Fworkflow-example.md",[54,61,68,75,82,89],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]