[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M736XHA73KZ5G2TKWSED5P1B":3,"skill-same:01M736XHA73KZ5G2TKWSED5P1B":60},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":28,"updatedAt":29,"install":30,"resources":43},"01M736XHA73KZ5G2TKWSED5P1B","topic-radar",null,"Aggregate read-only AI and technology trend signals (Polymarket, Hacker News, GitHub, arXiv, Hugging Face, news search) into source-grounded Markdown or JSON; the lower-level data engine behind `daily-brief`.","graysurf\u002Fagent-runtime-kit","graysurf","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10785178?v=4","01M736PQHYKHFMNBYF8BT93NM4","01M736PQJWYH7G046WAN7EQCHD",0,"MIT","https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fexpected\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: topic-radar\ndescription: >\n  Aggregate read-only AI and technology trend signals (Polymarket, Hacker\n  News, GitHub, arXiv, Hugging Face, news search) into source-grounded\n  Markdown or JSON; the lower-level data engine behind `daily-brief`.\n---\n\n# Topic Radar\n\n## Contract\n\nPrereqs:\n\n- Python 3.11 or newer is available on `PATH` (used by the bundled `topic_radar.py` script, which is stdlib-only).\n- Network access for live lookups.\n- Optional upstreams may rate-limit anonymous requests; the skill must degrade per-source instead of failing the whole digest.\n- Polymarket source support prefers read-only MCP tool output when available; otherwise the bundled `polymarket-readonly` fallback (when the\n  domain is installed alongside `reporting`) is invoked transparently by the script.\n\nInputs:\n\n- Natural-language AI or technology topics.\n- Optional profile name: `terry-ai-tech` by default, `ai-tech` for the generic baseline, or aliases `terry`, `personal`, and `default`.\n- Optional preset: `radar` by default, or `ai-news` for a faster daily AI news scan focused on official\u002Fnews\u002FHN sources.\n- Optional source list: `polymarket`, `hn`, `github`, `arxiv`, `hf`, `official`, `news`, or `all`.\n- Daily, weekly, or monthly report request, custom rolling day window, fixed `--from\u002F--to` or `--month` window, result limit, parallel fetch\n  count, cache TTL, news provider strategy, brief mode, and output format.\n- Optional Polymarket MCP JSON export path passed with `--polymarket-mcp-json`.\n\nOutputs:\n\n- Source-grounded AI\u002Ftechnology trend digest in Markdown or JSON.\n- Optional clustered brief for fast reading across product, agent\u002Ftooling, enterprise, security\u002Fgovernance, and research\u002Fopen-ecosystem signals.\n- Ranked cross-source signal list with source metadata, URLs, timestamps, fixed or rolling window metadata, score rationale, `signalTier`,\n  `signalMetrics`, and per-source sections.\n- Optional `Early Watchlist` entries for relevant but low-signal items. These entries stay in raw `items` output but should not be treated as\n  Topline or adoption evidence.\n- Per-source errors when an upstream is unavailable, rate-limited, or malformed, including short response snippets when available.\n- Public-response cache metadata so repeated follow-up scans are auditable.\n- Sample-mode output for offline smoke checks and report-format review.\n\nExit codes:\n\n- `0`: success\n- `1`: failure\n- `2`: usage error\n- `3`: unsafe delegated source environment detected\n\nFailure modes:\n\n- Unknown source, report type, format, profile, invalid fixed-window shape, or invalid numeric option.\n- Live source returns invalid data, times out, or rate-limits; the affected source is reported in `errors`, while other sources continue.\n- The broad `radar` preset uses `news-provider=auto`: GDELT first, then Google News RSS fallback when GDELT is unavailable or empty.\n- The faster `ai-news` preset uses `news-provider=google` by default to avoid GDELT rate-limit stalls during daily scans.\n- Polymarket MCP output is missing, malformed, or has no usable records; continue to helper fallback unless `--polymarket-fallback none` is\n  set.\n- Delegated Polymarket helper detects unsafe trading credentials; stop with exit `3`.\n\n## Scripts (only entrypoints)\n\n- $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh\n\nWrite temporary raw collection output under:\n\nagent-out path-for --domain tools\n\n## References\n\n- Read [references\u002Fsource-strategy.md](references\u002Fsource-strategy.md) before changing source selection, ranking, or report sections.\n\n## Role Boundary\n\n- Use `topic-radar` directly when the user asks for source-level scanning, custom sources, raw Markdown\u002FJSON digest output, or automation\n  input.\n- Use reporting.daily-brief when the user wants the normal daily information entrypoint: concise user-language synthesis,\n  preference steering, freshness notes, and source-health explanation.\n- `topic-radar` owns source fetching, ranking, fallback behavior, public-response caching, brief clusters, and per-source errors.\n- `daily-brief` must not reimplement fetchers, ranking, cache, RSS\u002FAPI parsing, or Polymarket fallback logic; it should consume\n  `topic-radar --format json`.\n\n## Workflow\n\n1. Treat this skill as read-only content and trend research. Do not request or configure trading credentials, social posting credentials, or\n   paid news API keys by default.\n\n2. For \"AI news today \u002F this week \u002F these days\" requests, start with the faster AI news preset. It uses a 5-day window, clustered brief\n   output, public-response caching, Google News RSS for mainstream coverage, and the source order `official,news,hn`:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh --preset ai-news\n   ```\n\n   Use `--refresh` when the user asks for exact latest\u002Fcurrent results and cached responses should be bypassed:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh --preset ai-news --refresh\n   ```\n\n3. Use the broad radar preset when the user asks for general AI\u002FTech trend scanning across market, developer, research, model, official, and\n   news surfaces. The default profile tracks AI agents, agentic coding, model releases, developer tools, AI infrastructure, inference\n   serving, semiconductors, NVIDIA, robotics, embodied AI, OpenAI, Anthropic, Google DeepMind, and Hugging Face:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh --report daily\n   ```\n\n4. Use personal memory only as a steering layer for recurring interests and source preferences before running the script. Do not write\n   secrets, temporary task state, or project state into memory. Keep the report grounded in the script output and linked source items.\n\n5. When Polymarket is requested and the current agent has the `polymarket` MCP tools, query read-only MCP first:\n\n   - `gamma_list_events` with `active=true`, `closed=false`, and a small `limit`\n   - `gamma_list_markets` with `active=true`, `closed=false`, and a small `limit`\n   - `gamma_search_public` for the user's focused topic when broad lists are too noisy\n\n   Save those raw MCP results as JSON shaped like this:\n\n   ```json\n   {\n     \"events\": [],\n     \"markets\": [],\n     \"search\": []\n   }\n   ```\n\n   Then pass the file to the radar:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh \\\n     --sources polymarket,hn,github \\\n     --polymarket-mcp-json \u002Fpath\u002Fto\u002Fpolymarket-mcp.json \\\n     --report daily\n   ```\n\n6. If no MCP output is available, omit `--polymarket-mcp-json`; the script falls back to its bundled `polymarket-readonly` helper logic and\n   reports per-source errors if the local network blocks Polymarket REST.\n\n7. For focused research, pass topics and source filters:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh \\\n     --topic \"AI agents\" \\\n     --topic \"developer tools\" \\\n     --sources hn,github,arxiv,hf,polymarket \\\n     --report weekly\n   ```\n\n8. For monthly trend archive work, use a fixed calendar window rather than a rolling `--days` window:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh \\\n     --preset radar \\\n     --report monthly \\\n     --month 2026-01 \\\n     --format json\n   ```\n\n   For a partial current month, use explicit inclusive dates:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh \\\n     --preset radar \\\n     --from 2026-05-01 \\\n     --to 2026-05-15 \\\n     --format json\n   ```\n\n   Treat fixed windows as source-bounded evidence. Some sources are current snapshots rather than reliable historical archives; the JSON\n   `errors` field reports those gaps instead of silently inventing monthly history.\n\n9. Use JSON when another tool, scheduled job, or agent synthesis step will consume the output:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh --preset ai-news --format json\n   ```\n\n10. Use sample mode for smoke checks, demos, or local validation without network access:\n\n    ```bash\n    $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh --sample --format markdown\n    ```\n\n11. Keep the report source-grounded. Separate observed source signals from inference, and do not present heuristic ranking as objective\n    importance. Treat `signalTier` as a presentation hint: high\u002Fmedium signal can feed Topline and brief clusters, while\n    `early-watchlist` items are relevant topic samples that need visible metrics such as HN points\u002Fcomments or GitHub stars\u002Fforks.\n","# Topic Radar\n\n## Contract\n\nPrereqs:\n\n- Python 3.11 or newer is available on `PATH` (used by the bundled `topic_radar.py` script, which is stdlib-only).\n- Network access for live lookups.\n- Optional upstreams may rate-limit anonymous requests; the skill must degrade per-source instead of failing the whole digest.\n- Polymarket source support prefers read-only MCP tool output when available; otherwise the bundled `polymarket-readonly` fallback (when the\n  domain is installed alongside `reporting`) is invoked transparently by the script.\n\nInputs:\n\n- Natural-language AI or technology topics.\n- Optional profile name: `terry-ai-tech` by default, `ai-tech` for the generic baseline, or aliases `terry`, `personal`, and `default`.\n- Optional preset: `radar` by default, or `ai-news` for a faster daily AI news scan focused on official\u002Fnews\u002FHN sources.\n- Optional source list: `polymarket`, `hn`, `github`, `arxiv`, `hf`, `official`, `news`, or `all`.\n- Daily, weekly, or monthly report request, custom rolling day window, fixed `--from\u002F--to` or `--month` window, result limit, parallel fetch\n  count, cache TTL, news provider strategy, brief mode, and output format.\n- Optional Polymarket MCP JSON export path passed with `--polymarket-mcp-json`.\n\nOutputs:\n\n- Source-grounded AI\u002Ftechnology trend digest in Markdown or JSON.\n- Optional clustered brief for fast reading across product, agent\u002Ftooling, enterprise, security\u002Fgovernance, and research\u002Fopen-ecosystem signals.\n- Ranked cross-source signal list with source metadata, URLs, timestamps, fixed or rolling window metadata, score rationale, `signalTier`,\n  `signalMetrics`, and per-source sections.\n- Optional `Early Watchlist` entries for relevant but low-signal items. These entries stay in raw `items` output but should not be treated as\n  Topline or adoption evidence.\n- Per-source errors when an upstream is unavailable, rate-limited, or malformed, including short response snippets when available.\n- Public-response cache metadata so repeated follow-up scans are auditable.\n- Sample-mode output for offline smoke checks and report-format review.\n\nExit codes:\n\n- `0`: success\n- `1`: failure\n- `2`: usage error\n- `3`: unsafe delegated source environment detected\n\nFailure modes:\n\n- Unknown source, report type, format, profile, invalid fixed-window shape, or invalid numeric option.\n- Live source returns invalid data, times out, or rate-limits; the affected source is reported in `errors`, while other sources continue.\n- The broad `radar` preset uses `news-provider=auto`: GDELT first, then Google News RSS fallback when GDELT is unavailable or empty.\n- The faster `ai-news` preset uses `news-provider=google` by default to avoid GDELT rate-limit stalls during daily scans.\n- Polymarket MCP output is missing, malformed, or has no usable records; continue to helper fallback unless `--polymarket-fallback none` is\n  set.\n- Delegated Polymarket helper detects unsafe trading credentials; stop with exit `3`.\n\n## Scripts (only entrypoints)\n\n- $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh\n\nWrite temporary raw collection output under:\n\nagent-out path-for --domain tools\n\n## References\n\n- Read [references\u002Fsource-strategy.md](references\u002Fsource-strategy.md) before changing source selection, ranking, or report sections.\n\n## Role Boundary\n\n- Use `topic-radar` directly when the user asks for source-level scanning, custom sources, raw Markdown\u002FJSON digest output, or automation\n  input.\n- Use reporting.daily-brief when the user wants the normal daily information entrypoint: concise user-language synthesis,\n  preference steering, freshness notes, and source-health explanation.\n- `topic-radar` owns source fetching, ranking, fallback behavior, public-response caching, brief clusters, and per-source errors.\n- `daily-brief` must not reimplement fetchers, ranking, cache, RSS\u002FAPI parsing, or Polymarket fallback logic; it should consume\n  `topic-radar --format json`.\n\n## Workflow\n\n1. Treat this skill as read-only content and trend research. Do not request or configure trading credentials, social posting credentials, or\n   paid news API keys by default.\n\n2. For \"AI news today \u002F this week \u002F these days\" requests, start with the faster AI news preset. It uses a 5-day window, clustered brief\n   output, public-response caching, Google News RSS for mainstream coverage, and the source order `official,news,hn`:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh --preset ai-news\n   ```\n\n   Use `--refresh` when the user asks for exact latest\u002Fcurrent results and cached responses should be bypassed:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh --preset ai-news --refresh\n   ```\n\n3. Use the broad radar preset when the user asks for general AI\u002FTech trend scanning across market, developer, research, model, official, and\n   news surfaces. The default profile tracks AI agents, agentic coding, model releases, developer tools, AI infrastructure, inference\n   serving, semiconductors, NVIDIA, robotics, embodied AI, OpenAI, Anthropic, Google DeepMind, and Hugging Face:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh --report daily\n   ```\n\n4. Use personal memory only as a steering layer for recurring interests and source preferences before running the script. Do not write\n   secrets, temporary task state, or project state into memory. Keep the report grounded in the script output and linked source items.\n\n5. When Polymarket is requested and the current agent has the `polymarket` MCP tools, query read-only MCP first:\n\n   - `gamma_list_events` with `active=true`, `closed=false`, and a small `limit`\n   - `gamma_list_markets` with `active=true`, `closed=false`, and a small `limit`\n   - `gamma_search_public` for the user's focused topic when broad lists are too noisy\n\n   Save those raw MCP results as JSON shaped like this:\n\n   ```json\n   {\n     \"events\": [],\n     \"markets\": [],\n     \"search\": []\n   }\n   ```\n\n   Then pass the file to the radar:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh \\\n     --sources polymarket,hn,github \\\n     --polymarket-mcp-json \u002Fpath\u002Fto\u002Fpolymarket-mcp.json \\\n     --report daily\n   ```\n\n6. If no MCP output is available, omit `--polymarket-mcp-json`; the script falls back to its bundled `polymarket-readonly` helper logic and\n   reports per-source errors if the local network blocks Polymarket REST.\n\n7. For focused research, pass topics and source filters:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh \\\n     --topic \"AI agents\" \\\n     --topic \"developer tools\" \\\n     --sources hn,github,arxiv,hf,polymarket \\\n     --report weekly\n   ```\n\n8. For monthly trend archive work, use a fixed calendar window rather than a rolling `--days` window:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh \\\n     --preset radar \\\n     --report monthly \\\n     --month 2026-01 \\\n     --format json\n   ```\n\n   For a partial current month, use explicit inclusive dates:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh \\\n     --preset radar \\\n     --from 2026-05-01 \\\n     --to 2026-05-15 \\\n     --format json\n   ```\n\n   Treat fixed windows as source-bounded evidence. Some sources are current snapshots rather than reliable historical archives; the JSON\n   `errors` field reports those gaps instead of silently inventing monthly history.\n\n9. Use JSON when another tool, scheduled job, or agent synthesis step will consume the output:\n\n   ```bash\n   $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh --preset ai-news --format json\n   ```\n\n10. Use sample mode for smoke checks, demos, or local validation without network access:\n\n    ```bash\n    $HOME\u002F.hermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fscripts\u002Ftopic-radar.sh --sample --format markdown\n    ```\n\n11. Keep the report source-grounded. Separate observed source signals from inference, and do not present heuristic ranking as objective\n    importance. Treat `signalTier` as a presentation hint: high\u002Fmedium signal can feed Topline and brief clusters, while\n    `early-watchlist` items are relevant topic samples that need visible metrics such as HN points\u002Fcomments or GitHub stars\u002Fforks.\n",{"name":5,"description":7},"main","da7119f2ebece510d6955cea72743069f5496c73","tests\u002Fgolden\u002Fhermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fexpected","https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit","https:\u002F\u002Fgithub.com\u002Fgraysurf","Building reliable tools for teams of AI coding agents · Rust \u002F TypeScript · @sympoies","2026-08-29 05:27:47",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add graysurf\u002Fagent-runtime-kit --skill topic-radar",{"tool":36,"command":37},"bunx","bunx skills add graysurf\u002Fagent-runtime-kit --skill topic-radar",{"tool":39,"command":40},"pnpm","pnpm dlx skills add graysurf\u002Fagent-runtime-kit --skill topic-radar","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fexpected\u002FSKILL.md",true,[44,50,56],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"bin\u002Ftopic_radar.py","SCRIPT","脚本",87603,"https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fexpected\u002Fbin\u002Ftopic_radar.py",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fsource-strategy.md","REFERENCE","参考文档",5831,"https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fexpected\u002Freferences\u002Fsource-strategy.md",{"path":57,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":58,"sourceHtmlUrl":59},"scripts\u002Ftopic-radar.sh",206,"https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Fplugins\u002Freporting\u002Fskills\u002Ftopic-radar\u002Fexpected\u002Fscripts\u002Ftopic-radar.sh",[61,67,72,79,86,93],{"skillNo":62,"name":63,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M736XWK14DFRERMQ8RT3HS0Z","removable-skill","https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit\u002Fblob\u002Fmain\u002Ftests\u002Fruntime-smoke\u002Ffixtures\u002Fskill-lifecycle\u002Fremove-skill\u002Ftests\u002Fgolden\u002Fcodex\u002Fplugins\u002Ffixture\u002Fskills\u002Fremovable-skill\u002FSKILL.md",[],[],{"skillNo":68,"name":63,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M736XTPQEKAYESDM1REN2KAN","https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit\u002Fblob\u002Fmain\u002Ftests\u002Fruntime-smoke\u002Ffixtures\u002Fskill-lifecycle\u002Fremove-skill\u002Ftests\u002Fgolden\u002Fclaude\u002Fplugins\u002Ffixture\u002Fskills\u002Fremovable-skill\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M736XRMWHMJB4X563G9J6QYY","removable-project-skill","Fixture project-local skill used to prove remove-project-skill dry-run coverage.","https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit\u002Fblob\u002Fmain\u002Ftests\u002Fruntime-smoke\u002Ffixtures\u002Fskill-lifecycle\u002Fremove-project-skill\u002F.agents\u002Fskills\u002Fremovable-project-skill\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M736XPT65YZMPCBD4K3RHV4P","project-sample-skill","Fixture project-local skill used to prove create-project-skill governance coverage.","https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit\u002Fblob\u002Fmain\u002Ftests\u002Fruntime-smoke\u002Ffixtures\u002Fskill-lifecycle\u002Fcreate-project-skill\u002F.agents\u002Fskills\u002Fproject-sample-skill\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M736XKZVYWVQA1YB0P459WND","project-local-skill","Fixture project-local skill used by runtime-kit project-local smoke checks.","https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit\u002Fblob\u002Fmain\u002Ftests\u002Fprojects\u002Fproject-local-smoke\u002F.agents\u002Fskills\u002Fproject-local-skill\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M736XF1YSAWCY1D88QM945X1","project-retro","Generate a repo-local project implementation retrospective by consuming the nils-cli `repo-retro` command — local git history only, no remote API enrichment.","https:\u002F\u002Fgithub.com\u002Fgraysurf\u002Fagent-runtime-kit\u002Fblob\u002Fmain\u002Ftests\u002Fgolden\u002Fhermes\u002Fplugins\u002Freporting\u002Fskills\u002Fproject-retro\u002Fexpected\u002FSKILL.md",[],[]]