[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M738FNF9Z2QJ5G1HQASP4JRJ":3,"skill-same:01M738FNF9Z2QJ5G1HQASP4JRJ":50},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M738FNF9Z2QJ5G1HQASP4JRJ","adversarial-team-pattern",null,"Template pattern for multi-agent analysis where agents hold opposing mandates. Use when spawning subagents for complex research, code review, architecture decisions, or risk assessment. Triggers on: 'adversarial team', 'devil's advocate analysis', 'multi-perspective review', 'challenge this decision', 'stress test this plan', 'red team this'.","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fadversarial-team-pattern\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: adversarial-team-pattern\ndescription: \"Template pattern for multi-agent analysis where agents hold opposing mandates. Use when spawning subagents for complex research, code review, architecture decisions, or risk assessment. Triggers on: 'adversarial team', 'devil's advocate analysis', 'multi-perspective review', 'challenge this decision', 'stress test this plan', 'red team this'.\"\nsource: ai-berkshire\u002Fxbtlin (MIT) — pattern adapted from investment-team.md four-master debate model\ntier: TIER 2 — CORRECTNESS\n---\n\n# Adversarial Team Pattern\n\nMulti-agent analysis using opposing mandates — not consensus. Agents challenge each other rather than reinforce each other.\n\n**Core principle:** consensus from multiple agents = one agent with extra compute. Value comes from *productive disagreement*.\n\n---\n\n## When to use\n\n- High-stakes decisions (architecture, security, major refactor)\n- Analysis where confirmation bias is a real risk\n- Any time you'd normally just \"get a second opinion\" (make it an adversarial second opinion)\n- Code review of critical paths\n- Research where you want to surface what could go wrong, not just what looks right\n\nDo NOT use for: simple lookups, single-file changes, mechanical tasks with a clear right answer.\n\n---\n\n## Team structure\n\nSpawn these roles in a single message (parallel, `run_in_background: true`):\n\n```\nROLE A — Advocate\n  Mandate: Build the strongest case FOR the proposal.\n  Find evidence that supports it. Assume it will work.\n  Deliver: 3–5 concrete supporting arguments with evidence.\n\nROLE B — Challenger  \n  Mandate: Find everything wrong with the proposal.\n  Assume it will fail. Find the weakest points.\n  Deliver: 3–5 specific failure modes or risks with evidence.\n\nROLE C — Constraint Finder\n  Mandate: Find what's missing, what's not accounted for,\n  what the other two missed. Be the skeptic of both sides.\n  Deliver: unknowns, edge cases, unstated assumptions.\n\nROLE D — Synthesizer  (run AFTER A, B, C complete)\n  Mandate: Read all three reports. Produce a forced conclusion.\n  Cannot say \"it depends\". Must pick a side or a modified path.\n  Deliver: verdict + confidence % + 1 concrete next action.\n```\n\n---\n\n## Execution template\n\n```\nAnalyze [TOPIC] using adversarial team pattern.\n\nAgent A (Advocate): Make the strongest case FOR [TOPIC].\nFind 3–5 concrete supporting arguments with evidence.\nDo not hedge. Assume success.\n\nAgent B (Challenger): Find everything wrong with [TOPIC].\nFind 3–5 specific failure modes or risks.\nAssume failure. Do not soften findings.\n\nAgent C (Constraint Finder): Find what A and B both missed.\nSurface unknowns, unstated assumptions, edge cases.\nBe skeptical of both the advocate and challenger.\n\nAfter all three complete, Agent D (Synthesizer) reads all reports\nand produces a forced conclusion: verdict + confidence % + next action.\nNo \"it depends\" in the conclusion.\n```\n\n---\n\n## Output Contract\n\n```\nAdvocate findings:   [3–5 supporting arguments]\nChallenger findings: [3–5 failure modes]\nMissing\u002Funknowns:    [what neither side saw]\n\nVERDICT:     [clear position — not neutral]\nCONFIDENCE:  [0–100%]\nREASONING:   [which argument won and why]\nNEXT ACTION: [one concrete step]\n```\n\n---\n\n## In-Skill Verification\n\nBefore Synthesizer produces verdict:\n1. Check: did Advocate cite at least 1 concrete piece of evidence (not just assertion)?\n2. Check: did Challenger identify at least 1 specific failure mode (not generic risk)?\n3. If either check fails → Synthesizer notes \"incomplete input\" in output with confidence ≤ 50%\n\n---\n\n## Anti-patterns\n\n```\n❌ All agents instructed to \"analyze objectively\" — that's consensus, not adversarial\n❌ Synthesizer allowed to conclude \"both sides have merit, consider your context\"\n❌ Challenger role that softens findings (\"on the other hand, it could work if...\")\n❌ Running agents sequentially where later agents read earlier agents' output (anchoring bias)\n❌ Skipping Synthesizer — raw debate without forced conclusion wastes the pattern\n```\n\n---\n\n## Confidence calibration\n\n| Situation | Max confidence |\n|-----------|---------------|\n| All 3 roles agree | 90% |\n| Advocate + Synthesizer agree, Challenger has weak evidence | 75% |\n| Split between roles, Synthesizer forced to pick | 60% |\n| Missing data flagged by Constraint Finder | 50% |\n| Insufficient evidence from any role | 35% |\n","# Adversarial Team Pattern\n\nMulti-agent analysis using opposing mandates — not consensus. Agents challenge each other rather than reinforce each other.\n\n**Core principle:** consensus from multiple agents = one agent with extra compute. Value comes from *productive disagreement*.\n\n---\n\n## When to use\n\n- High-stakes decisions (architecture, security, major refactor)\n- Analysis where confirmation bias is a real risk\n- Any time you'd normally just \"get a second opinion\" (make it an adversarial second opinion)\n- Code review of critical paths\n- Research where you want to surface what could go wrong, not just what looks right\n\nDo NOT use for: simple lookups, single-file changes, mechanical tasks with a clear right answer.\n\n---\n\n## Team structure\n\nSpawn these roles in a single message (parallel, `run_in_background: true`):\n\n```\nROLE A — Advocate\n  Mandate: Build the strongest case FOR the proposal.\n  Find evidence that supports it. Assume it will work.\n  Deliver: 3–5 concrete supporting arguments with evidence.\n\nROLE B — Challenger  \n  Mandate: Find everything wrong with the proposal.\n  Assume it will fail. Find the weakest points.\n  Deliver: 3–5 specific failure modes or risks with evidence.\n\nROLE C — Constraint Finder\n  Mandate: Find what's missing, what's not accounted for,\n  what the other two missed. Be the skeptic of both sides.\n  Deliver: unknowns, edge cases, unstated assumptions.\n\nROLE D — Synthesizer  (run AFTER A, B, C complete)\n  Mandate: Read all three reports. Produce a forced conclusion.\n  Cannot say \"it depends\". Must pick a side or a modified path.\n  Deliver: verdict + confidence % + 1 concrete next action.\n```\n\n---\n\n## Execution template\n\n```\nAnalyze [TOPIC] using adversarial team pattern.\n\nAgent A (Advocate): Make the strongest case FOR [TOPIC].\nFind 3–5 concrete supporting arguments with evidence.\nDo not hedge. Assume success.\n\nAgent B (Challenger): Find everything wrong with [TOPIC].\nFind 3–5 specific failure modes or risks.\nAssume failure. Do not soften findings.\n\nAgent C (Constraint Finder): Find what A and B both missed.\nSurface unknowns, unstated assumptions, edge cases.\nBe skeptical of both the advocate and challenger.\n\nAfter all three complete, Agent D (Synthesizer) reads all reports\nand produces a forced conclusion: verdict + confidence % + next action.\nNo \"it depends\" in the conclusion.\n```\n\n---\n\n## Output Contract\n\n```\nAdvocate findings:   [3–5 supporting arguments]\nChallenger findings: [3–5 failure modes]\nMissing\u002Funknowns:    [what neither side saw]\n\nVERDICT:     [clear position — not neutral]\nCONFIDENCE:  [0–100%]\nREASONING:   [which argument won and why]\nNEXT ACTION: [one concrete step]\n```\n\n---\n\n## In-Skill Verification\n\nBefore Synthesizer produces verdict:\n1. Check: did Advocate cite at least 1 concrete piece of evidence (not just assertion)?\n2. Check: did Challenger identify at least 1 specific failure mode (not generic risk)?\n3. If either check fails → Synthesizer notes \"incomplete input\" in output with confidence ≤ 50%\n\n---\n\n## Anti-patterns\n\n```\n❌ All agents instructed to \"analyze objectively\" — that's consensus, not adversarial\n❌ Synthesizer allowed to conclude \"both sides have merit, consider your context\"\n❌ Challenger role that softens findings (\"on the other hand, it could work if...\")\n❌ Running agents sequentially where later agents read earlier agents' output (anchoring bias)\n❌ Skipping Synthesizer — raw debate without forced conclusion wastes the pattern\n```\n\n---\n\n## Confidence calibration\n\n| Situation | Max confidence |\n|-----------|---------------|\n| All 3 roles agree | 90% |\n| Advocate + Synthesizer agree, Challenger has weak evidence | 75% |\n| Split between roles, Synthesizer forced to pick | 60% |\n| Missing data flagged by Constraint Finder | 50% |\n| Insufficient evidence from any role | 35% |\n",{"name":5,"tier":24,"source":25,"description":7},"TIER 2 — CORRECTNESS","ai-berkshire\u002Fxbtlin (MIT) — pattern adapted from investment-team.md four-master debate model","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Fadversarial-team-pattern",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.","2026-11-14 13:24:09",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill adversarial-team-pattern",{"tool":42,"command":43},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill adversarial-team-pattern",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill adversarial-team-pattern","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fadversarial-team-pattern\u002FSKILL.md",true,[],[51,59,66,74,82,90],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":55,"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`.","MIT","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":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":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":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":6,"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},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]