[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73FFJXV2JFG8PS41KYGZXDZ":3,"skill-same:01M73FFJXV2JFG8PS41KYGZXDZ":51},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M73FFJXV2JFG8PS41KYGZXDZ","research-team",null,"Autonomous multi-source research agent group. Given an unknown bug or technology topic, research-team spawns parallel sub-agents to search StackOverflow, GitHub Issues, official docs, and changelogs. Synthesizes findings into a ranked solution report. Inspired by assafelovic\u002Fgpt-researcher closed-loop research architecture.","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fresearch-team\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: research-team\ndescription: Autonomous multi-source research agent group. Given an unknown bug or technology topic, research-team spawns parallel sub-agents to search StackOverflow, GitHub Issues, official docs, and changelogs. Synthesizes findings into a ranked solution report. Inspired by assafelovic\u002Fgpt-researcher closed-loop research architecture.\norigin: assafelovic\u002Fgpt-researcher (Apache 2.0) — multi-source parallel research loop\nlicense: MIT\nversion: 1.0.0\ncompatibility: Claude Code, any project\n---\n\n# research-team\n\n## When to Use\n\n- An unknown bug has no match in L1 memory — need external knowledge\n- A library has released a new version and APIs may have changed\n- You need to compare multiple solutions before committing to one\n- Triggered by: \"research this\", \"find a fix for\", \"investigate\", \"what's the best approach for\", \"look up\", \"research team\", \"autonomous research\"\n\n## Do NOT use for\n\n- Known bugs already documented in L1 (`core\u002Fmemory\u002FL1\u002F`) — read L1 first\n- Simple API lookups that a single WebSearch handles\n- Tasks requiring code execution — hand off to `autonomous-patching-loop` after research\n- See `ingest-repo` for structured code-level repo analysis\n\n---\n\n## Team Roles\n\n```\nResearcher-A  → searches StackOverflow + GitHub Issues for the exact error\nResearcher-B  → reads official docs \u002F changelog for the library version in use\nResearcher-C  → searches for alternative approaches \u002F known workarounds\nSynthesizer   → cross-references all 3 findings, ranks solutions by reliability\n```\n\n---\n\n## Research Loop Architecture\n\n```python\n# Conceptual: multi-agent research pipeline (adapt to Claude Code subagents)\n\nfrom dataclasses import dataclass\nfrom typing import Callable\n\n@dataclass\nclass ResearchQuery:\n    topic: str\n    context: str        # error message \u002F file \u002F line number\n    library: str        # e.g. \"react@18.3.0\"\n    max_sources: int = 10\n\ndef research_team(query: ResearchQuery, search_fn: Callable) -> dict:\n    \"\"\"\n    Parallel research across 3 lanes, then synthesize.\n    \"\"\"\n    # Lane A: Stack-style QA\n    lane_a = search_fn(f\"{query.topic} site:stackoverflow.com OR site:github.com\u002Fissues\")\n\n    # Lane B: Official docs + changelog\n    lane_b = search_fn(f\"{query.library} changelog deprecation {query.topic}\")\n\n    # Lane C: Alternative approaches\n    lane_c = search_fn(f\"alternative to {query.topic} {query.library} workaround\")\n\n    # Synthesizer: rank by recency + vote count + library version match\n    all_results = lane_a + lane_b + lane_c\n    ranked = sorted(\n        all_results,\n        key=lambda r: (r.get(\"votes\", 0) + r.get(\"recency_score\", 0)),\n        reverse=True\n    )[:query.max_sources]\n\n    return {\n        \"query\": query.topic,\n        \"sources\": len(ranked),\n        \"top_solution\": ranked[0] if ranked else None,\n        \"alternatives\": ranked[1:3],\n        \"confidence\": \"high\" if len(ranked) >= 5 else \"medium\",\n    }\n```\n\n---\n\n## Claude Code Subagent Pattern\n\n```\n# ORCHESTRATOR prompt to spawn research-team\nTask: Bug in [library]@[version]: [error message]\n\nSpawn 3 parallel research agents:\n\nAgent-A: Search StackOverflow and GitHub Issues for exact error.\n  Query: \"[error message] [library]\"\n  Output: top 3 matches with URL + date + vote count → write to .claude\u002Fsignals\u002Fresearch-a.json\n\nAgent-B: Read official docs\u002Fchangelog for [library]@[version].\n  Focus: breaking changes, deprecated APIs, migration guides.\n  Output: relevant section → write to .claude\u002Fsignals\u002Fresearch-b.json\n\nAgent-C: Find alternative approaches for [topic] that avoid the error.\n  Output: top 2 alternatives → write to .claude\u002Fsignals\u002Fresearch-c.json\n\nSynthesizer (after A+B+C complete):\n  Read all 3 signal files.\n  Rank solutions by: recency > vote count > version match.\n  Write final report to .claude\u002Fsignals\u002Fresearch-report.md\n  Promote confirmed fix to L1: bash core\u002Fscripts\u002Fadd-fact.sh \"bug-fix\" \"\u003Csolution>\" \"high\"\n```\n\n---\n\n## Output Report Format\n\n```markdown\n# Research Report — [topic]\nDate: [timestamp]  Sources scanned: [n]  Confidence: high|medium|low\n\n## Recommended Fix\n[Solution text + code snippet]\nSource: [URL] ([date], [votes] votes)\n\n## Why This Works\n[1-2 sentence explanation tied to the library's behavior]\n\n## Alternative Approaches\n1. [Alt A] — [tradeoff]\n2. [Alt B] — [tradeoff]\n\n## Outdated \u002F Rejected Solutions\n- [Stack answer from 2020] — library API changed in v18, no longer applicable\n\n## L1 Promotion\n[ ] Promoted to core\u002Fmemory\u002FL1\u002F — bash core\u002Fscripts\u002Fadd-fact.sh \"bug-fix\" \"...\" \"high\"\n```\n\n---\n\n## Integration with autonomous-patching-loop\n\n```\nresearch-team  →  finds solution\n       │\n       ▼\nautonomous-patching-loop  →  applies fix on isolated branch\n       │\n       ▼\nverify gate passes  →  merge + L1 promotion\n```\n\n---\n\n## Anti-Fake-Pass Checklist\n\n- [ ] At least 3 sources consulted (not just 1 web search)\n- [ ] Results filtered for library version match — old answers flagged as \"may be outdated\"\n- [ ] Confidence level stated: high (≥5 sources), medium (3–4), low (\u003C3)\n- [ ] Rejected\u002Foutdated solutions documented — not silently dropped\n- [ ] Confirmed fix promoted to L1 via `add-fact.sh`\n- [ ] Report written to `.claude\u002Fsignals\u002Fresearch-report.md` — not left in chat only\n- [ ] Agent does NOT apply the fix directly — hands off to `autonomous-patching-loop`\n","# research-team\n\n## When to Use\n\n- An unknown bug has no match in L1 memory — need external knowledge\n- A library has released a new version and APIs may have changed\n- You need to compare multiple solutions before committing to one\n- Triggered by: \"research this\", \"find a fix for\", \"investigate\", \"what's the best approach for\", \"look up\", \"research team\", \"autonomous research\"\n\n## Do NOT use for\n\n- Known bugs already documented in L1 (`core\u002Fmemory\u002FL1\u002F`) — read L1 first\n- Simple API lookups that a single WebSearch handles\n- Tasks requiring code execution — hand off to `autonomous-patching-loop` after research\n- See `ingest-repo` for structured code-level repo analysis\n\n---\n\n## Team Roles\n\n```\nResearcher-A  → searches StackOverflow + GitHub Issues for the exact error\nResearcher-B  → reads official docs \u002F changelog for the library version in use\nResearcher-C  → searches for alternative approaches \u002F known workarounds\nSynthesizer   → cross-references all 3 findings, ranks solutions by reliability\n```\n\n---\n\n## Research Loop Architecture\n\n```python\n# Conceptual: multi-agent research pipeline (adapt to Claude Code subagents)\n\nfrom dataclasses import dataclass\nfrom typing import Callable\n\n@dataclass\nclass ResearchQuery:\n    topic: str\n    context: str        # error message \u002F file \u002F line number\n    library: str        # e.g. \"react@18.3.0\"\n    max_sources: int = 10\n\ndef research_team(query: ResearchQuery, search_fn: Callable) -> dict:\n    \"\"\"\n    Parallel research across 3 lanes, then synthesize.\n    \"\"\"\n    # Lane A: Stack-style QA\n    lane_a = search_fn(f\"{query.topic} site:stackoverflow.com OR site:github.com\u002Fissues\")\n\n    # Lane B: Official docs + changelog\n    lane_b = search_fn(f\"{query.library} changelog deprecation {query.topic}\")\n\n    # Lane C: Alternative approaches\n    lane_c = search_fn(f\"alternative to {query.topic} {query.library} workaround\")\n\n    # Synthesizer: rank by recency + vote count + library version match\n    all_results = lane_a + lane_b + lane_c\n    ranked = sorted(\n        all_results,\n        key=lambda r: (r.get(\"votes\", 0) + r.get(\"recency_score\", 0)),\n        reverse=True\n    )[:query.max_sources]\n\n    return {\n        \"query\": query.topic,\n        \"sources\": len(ranked),\n        \"top_solution\": ranked[0] if ranked else None,\n        \"alternatives\": ranked[1:3],\n        \"confidence\": \"high\" if len(ranked) >= 5 else \"medium\",\n    }\n```\n\n---\n\n## Claude Code Subagent Pattern\n\n```\n# ORCHESTRATOR prompt to spawn research-team\nTask: Bug in [library]@[version]: [error message]\n\nSpawn 3 parallel research agents:\n\nAgent-A: Search StackOverflow and GitHub Issues for exact error.\n  Query: \"[error message] [library]\"\n  Output: top 3 matches with URL + date + vote count → write to .claude\u002Fsignals\u002Fresearch-a.json\n\nAgent-B: Read official docs\u002Fchangelog for [library]@[version].\n  Focus: breaking changes, deprecated APIs, migration guides.\n  Output: relevant section → write to .claude\u002Fsignals\u002Fresearch-b.json\n\nAgent-C: Find alternative approaches for [topic] that avoid the error.\n  Output: top 2 alternatives → write to .claude\u002Fsignals\u002Fresearch-c.json\n\nSynthesizer (after A+B+C complete):\n  Read all 3 signal files.\n  Rank solutions by: recency > vote count > version match.\n  Write final report to .claude\u002Fsignals\u002Fresearch-report.md\n  Promote confirmed fix to L1: bash core\u002Fscripts\u002Fadd-fact.sh \"bug-fix\" \"\u003Csolution>\" \"high\"\n```\n\n---\n\n## Output Report Format\n\n```markdown\n# Research Report — [topic]\nDate: [timestamp]  Sources scanned: [n]  Confidence: high|medium|low\n\n## Recommended Fix\n[Solution text + code snippet]\nSource: [URL] ([date], [votes] votes)\n\n## Why This Works\n[1-2 sentence explanation tied to the library's behavior]\n\n## Alternative Approaches\n1. [Alt A] — [tradeoff]\n2. [Alt B] — [tradeoff]\n\n## Outdated \u002F Rejected Solutions\n- [Stack answer from 2020] — library API changed in v18, no longer applicable\n\n## L1 Promotion\n[ ] Promoted to core\u002Fmemory\u002FL1\u002F — bash core\u002Fscripts\u002Fadd-fact.sh \"bug-fix\" \"...\" \"high\"\n```\n\n---\n\n## Integration with autonomous-patching-loop\n\n```\nresearch-team  →  finds solution\n       │\n       ▼\nautonomous-patching-loop  →  applies fix on isolated branch\n       │\n       ▼\nverify gate passes  →  merge + L1 promotion\n```\n\n---\n\n## Anti-Fake-Pass Checklist\n\n- [ ] At least 3 sources consulted (not just 1 web search)\n- [ ] Results filtered for library version match — old answers flagged as \"may be outdated\"\n- [ ] Confidence level stated: high (≥5 sources), medium (3–4), low (\u003C3)\n- [ ] Rejected\u002Foutdated solutions documented — not silently dropped\n- [ ] Confirmed fix promoted to L1 via `add-fact.sh`\n- [ ] Report written to `.claude\u002Fsignals\u002Fresearch-report.md` — not left in chat only\n- [ ] Agent does NOT apply the fix directly — hands off to `autonomous-patching-loop`\n",{"name":5,"origin":24,"license":15,"version":25,"description":7,"compatibility":26},"assafelovic\u002Fgpt-researcher (Apache 2.0) — multi-source parallel research loop","1.0.0","Claude Code, any project","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Fresearch-team",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-13 13:15:29",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill research-team",{"tool":43,"command":44},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill research-team",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill research-team","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fresearch-team\u002FSKILL.md",true,[],[52,59,67,75,83,91],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"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":63,"licenseFileUrl":71,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\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":63,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]