[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M731MZ43F6TYENTHKECYBMPW":3,"skill-same:01M731MZ43F6TYENTHKECYBMPW":59},{"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":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M731MZ43F6TYENTHKECYBMPW","council-of-minds",null,"Convene 6 intellectual personas across multiple LLM providers for hard decisions. Each persona runs on a different provider for genuinely different reasoning — not costume changes on one model. Inspired by council-of-high-intelligence (CC0).","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\u002F.claude\u002Fskills\u002Fcouncil-of-minds\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: council-of-minds\ndescription: Convene 6 intellectual personas across multiple LLM providers for hard decisions. Each persona runs on a different provider for genuinely different reasoning — not costume changes on one model. Inspired by council-of-high-intelligence (CC0).\norigin: yana-ai — inspired by 0xNyk\u002Fcouncil-of-high-intelligence (CC0)\nlicense: MIT\nversion: 1.0.0\ntriggers:\n  - \u002Fcouncil-of-minds\n  - council of minds\n  - convene the council\n  - multi-mind deliberation\nmodes:\n  full: 6 personas, 2 rounds (~4 min)\n  quick: 3 personas, 1 round (~90s)\n  duo: 2 opposing personas, 1 round (~45s)\n---\n\n# \u002Fcouncil-of-minds\n\nSix intellectual personas deliberate your hardest decisions across multiple AI providers.\nOne command. Structured disagreement. No fake consensus.\n\n## Modes\n\n```\n\u002Fcouncil-of-minds \"question\"           → full (6 personas, 2 rounds)\n\u002Fcouncil-of-minds --quick \"question\"   → quick (3 personas, 1 round)\n\u002Fcouncil-of-minds --duo \"question\"     → duo (2 opposing voices, 1 round)\n```\n\n## When to Use\n\n- Decision has ≥2 credible paths and no obvious winner\n- You want structured disagreement, not a polished \"yes\"\n- You suspect your own anchoring bias\n- High stakes: architecture, strategy, go\u002Fno-go, hiring, product direction\n\n## When NOT to Use\n\n- Single correct answer (use tools or research instead)\n- Pure implementation task (use `\u002Fplan`)\n- Code review (use `\u002Fcode-review`)\n- Factual lookup (just ask directly)\n\n---\n\n## The Six Personas\n\nEach persona is routed to a different provider to ensure genuinely different reasoning.\n\n| Persona | Intellectual Tradition | Provider | Lens |\n|---------|----------------------|----------|------|\n| **The Architect** | Systems thinking, long-term | Claude | Correctness, maintainability, 5-year consequence |\n| **Socrates** | Socratic questioning | Gemini | Destroys premises, finds the hidden assumption |\n| **Feynman** | First-principles empiricism | DeepSeek | \"What does evidence actually say? Rebuild from scratch.\" |\n| **The Pragmatist** | Execution realism | Groq | Shipping speed, operational reality, resource constraints |\n| **Kahneman** | Behavioral economics | OpenAI | Cognitive bias traps, System 1 vs System 2, loss aversion |\n| **Torvalds** | Engineering minimalism | Ollama (local) | \"Will this actually work? Is it unnecessarily complex?\" |\n\nIf a provider is unavailable, fall back to Claude for that persona but explicitly note the fallback in output.\n\n---\n\n## Protocol\n\n### Step 0 — Problem Restate Gate\n\n**Before any analysis**, every persona must reframe the question in one sentence.\n\n> Rule: if ≥3 personas restate the question differently from how it was asked, the original question was the problem. Resolve the question ambiguity before proceeding.\n\n### Step 1 — Extract the real decision\n\nReduce to:\n- What exactly are we deciding?\n- What constraints are non-negotiable?\n- What does success look like in 6 months?\n- What is the cost of reversing this decision?\n\n### Step 2 — Form Architect position first (anti-anchoring)\n\nBefore reading other voices, write:\n1. Initial position (1 sentence)\n2. Three strongest reasons\n3. Main risk in preferred path\n\nThis prevents synthesis from simply mirroring external voices.\n\n### Step 3 — Launch personas in parallel\n\nEach persona gets only:\n- The restated decision question\n- Minimal necessary context (no full conversation history)\n- Their role prompt\n\n**Persona prompt template:**\n```\nYou are [PERSONA NAME] on a six-voice decision council.\n\nYour intellectual tradition: [tradition]\nYour primary lens: [lens]\n\nQuestion: [restated decision]\n\nContext (only what's needed):\n[compact context — code snippet, constraint, metric — max 200 words]\n\nRespond with exactly this structure:\n1. Restate — rephrase the question in your own words (1 sentence)\n2. Position — your recommendation (1-2 sentences)\n3. Reasoning — 3 bullets, each ≤ 25 words\n4. Strongest objection to your own position — 1 sentence\n5. What the other voices will miss — 1 sentence\n\nUnder 250 words total. No hedging. No \"it depends\" without specifying what it depends on.\n```\n\n### Step 4 — Dissent Quota Check\n\nAfter collecting all positions:\n\n> **Rule**: If ≥4 of 6 personas agree on the same recommendation, force 2 personas (chosen by least-confident alignment) to steelman the opposing view before synthesis.\n\nThis prevents groupthink from producing false consensus.\n\n### Step 5 — Round 2 (full mode only)\n\nShow each persona the other five positions (anonymized — no names, just positions).\nEach updates or defends their view in ≤ 100 words.\n\n### Step 6 — Synthesize\n\nRules for synthesis:\n- Do not dismiss any external view without explaining why\n- If an external voice changed the Architect's recommendation, say so explicitly\n- Lead with **Unresolved Questions** before the verdict\n- The strongest dissent must appear even if rejected\n\n---\n\n## Output Format\n\n```markdown\n## Council of Minds: [decision title]\n\n### Problem Restate Gate\n- Original question: [as asked]\n- Restated by council: [if different, flag it]\n\n---\n\n### Positions\n\n**The Architect** (Claude) — [1-sentence position]\n> [key reasoning, 1 line]\n\n**Socrates** (Gemini) — [1-sentence position]\n> [key reasoning, 1 line]\n\n**Feynman** (DeepSeek) — [1-sentence position]\n> [key reasoning, 1 line]\n\n**The Pragmatist** (Groq) — [1-sentence position]\n> [key reasoning, 1 line]\n\n**Kahneman** (OpenAI) — [1-sentence position]\n> [key reasoning, 1 line]\n\n**Torvalds** (Ollama) — [1-sentence position]\n> [key reasoning, 1 line]\n\n---\n\n### Synthesis\n\n**Where they align:** [what ≥4 agree on]\n\n**Strongest dissent:** [the most important disagreement — do not soften it]\n\n**Dissent quota triggered:** yes \u002F no — [if yes, who steelmanned what]\n\n**Unresolved questions:**\n- [question the council couldn't answer]\n- [what you'd need to know to decide with confidence]\n\n**Recommended next steps:** [concrete, not \"do more research\"]\n\n### Verdict\n**Recommendation:** [the synthesized path — commit to one]\n**Confidence:** [low \u002F medium \u002F high + why]\n**Reversibility:** [how hard to undo if wrong]\n```\n\n---\n\n## Quick Mode (3 personas)\n\nUse: Architect + Socrates + Torvalds\n\nBest for: tactical decisions, scope calls, technology choices\n\nOne round only. No Round 2. No dissent quota.\n\nOutput: same format but 3 positions only.\n\n## Duo Mode (2 personas)\n\nPick the two most opposing intellectual traditions for the question type:\n\n| Decision type | Best duo |\n|--------------|---------|\n| Technical architecture | Architect vs Torvalds |\n| Strategic direction | Feynman vs Kahneman |\n| Ship vs hold | Pragmatist vs Architect |\n| Question a premise | Socrates vs anyone |\n\nOne round. No restate gate (too short). Verdict required.\n\n---\n\n## Anti-Patterns\n\n```\n❌ Feeding the full conversation history to all personas (kills independence)\n❌ Hiding disagreement in the verdict to sound decisive\n❌ Using council for tasks with an objectively correct answer\n❌ Accepting ≥4-way agreement without triggering dissent quota\n❌ \"It depends\" without specifying the dependency\n❌ Council when the real blocker is missing information, not conflicting values\n```\n\n## Related Skills\n\n- `council` — 4-voice version, lighter\n- `multi-agent-debate` — Du et al. 2023 algorithm, multi-round consensus\n- `santa-method` — adversarial verification of a specific claim\n- `first-principles-thinker` — single voice, Feynman-style deconstruction\n","# \u002Fcouncil-of-minds\n\nSix intellectual personas deliberate your hardest decisions across multiple AI providers.\nOne command. Structured disagreement. No fake consensus.\n\n## Modes\n\n```\n\u002Fcouncil-of-minds \"question\"           → full (6 personas, 2 rounds)\n\u002Fcouncil-of-minds --quick \"question\"   → quick (3 personas, 1 round)\n\u002Fcouncil-of-minds --duo \"question\"     → duo (2 opposing voices, 1 round)\n```\n\n## When to Use\n\n- Decision has ≥2 credible paths and no obvious winner\n- You want structured disagreement, not a polished \"yes\"\n- You suspect your own anchoring bias\n- High stakes: architecture, strategy, go\u002Fno-go, hiring, product direction\n\n## When NOT to Use\n\n- Single correct answer (use tools or research instead)\n- Pure implementation task (use `\u002Fplan`)\n- Code review (use `\u002Fcode-review`)\n- Factual lookup (just ask directly)\n\n---\n\n## The Six Personas\n\nEach persona is routed to a different provider to ensure genuinely different reasoning.\n\n| Persona | Intellectual Tradition | Provider | Lens |\n|---------|----------------------|----------|------|\n| **The Architect** | Systems thinking, long-term | Claude | Correctness, maintainability, 5-year consequence |\n| **Socrates** | Socratic questioning | Gemini | Destroys premises, finds the hidden assumption |\n| **Feynman** | First-principles empiricism | DeepSeek | \"What does evidence actually say? Rebuild from scratch.\" |\n| **The Pragmatist** | Execution realism | Groq | Shipping speed, operational reality, resource constraints |\n| **Kahneman** | Behavioral economics | OpenAI | Cognitive bias traps, System 1 vs System 2, loss aversion |\n| **Torvalds** | Engineering minimalism | Ollama (local) | \"Will this actually work? Is it unnecessarily complex?\" |\n\nIf a provider is unavailable, fall back to Claude for that persona but explicitly note the fallback in output.\n\n---\n\n## Protocol\n\n### Step 0 — Problem Restate Gate\n\n**Before any analysis**, every persona must reframe the question in one sentence.\n\n> Rule: if ≥3 personas restate the question differently from how it was asked, the original question was the problem. Resolve the question ambiguity before proceeding.\n\n### Step 1 — Extract the real decision\n\nReduce to:\n- What exactly are we deciding?\n- What constraints are non-negotiable?\n- What does success look like in 6 months?\n- What is the cost of reversing this decision?\n\n### Step 2 — Form Architect position first (anti-anchoring)\n\nBefore reading other voices, write:\n1. Initial position (1 sentence)\n2. Three strongest reasons\n3. Main risk in preferred path\n\nThis prevents synthesis from simply mirroring external voices.\n\n### Step 3 — Launch personas in parallel\n\nEach persona gets only:\n- The restated decision question\n- Minimal necessary context (no full conversation history)\n- Their role prompt\n\n**Persona prompt template:**\n```\nYou are [PERSONA NAME] on a six-voice decision council.\n\nYour intellectual tradition: [tradition]\nYour primary lens: [lens]\n\nQuestion: [restated decision]\n\nContext (only what's needed):\n[compact context — code snippet, constraint, metric — max 200 words]\n\nRespond with exactly this structure:\n1. Restate — rephrase the question in your own words (1 sentence)\n2. Position — your recommendation (1-2 sentences)\n3. Reasoning — 3 bullets, each ≤ 25 words\n4. Strongest objection to your own position — 1 sentence\n5. What the other voices will miss — 1 sentence\n\nUnder 250 words total. No hedging. No \"it depends\" without specifying what it depends on.\n```\n\n### Step 4 — Dissent Quota Check\n\nAfter collecting all positions:\n\n> **Rule**: If ≥4 of 6 personas agree on the same recommendation, force 2 personas (chosen by least-confident alignment) to steelman the opposing view before synthesis.\n\nThis prevents groupthink from producing false consensus.\n\n### Step 5 — Round 2 (full mode only)\n\nShow each persona the other five positions (anonymized — no names, just positions).\nEach updates or defends their view in ≤ 100 words.\n\n### Step 6 — Synthesize\n\nRules for synthesis:\n- Do not dismiss any external view without explaining why\n- If an external voice changed the Architect's recommendation, say so explicitly\n- Lead with **Unresolved Questions** before the verdict\n- The strongest dissent must appear even if rejected\n\n---\n\n## Output Format\n\n```markdown\n## Council of Minds: [decision title]\n\n### Problem Restate Gate\n- Original question: [as asked]\n- Restated by council: [if different, flag it]\n\n---\n\n### Positions\n\n**The Architect** (Claude) — [1-sentence position]\n> [key reasoning, 1 line]\n\n**Socrates** (Gemini) — [1-sentence position]\n> [key reasoning, 1 line]\n\n**Feynman** (DeepSeek) — [1-sentence position]\n> [key reasoning, 1 line]\n\n**The Pragmatist** (Groq) — [1-sentence position]\n> [key reasoning, 1 line]\n\n**Kahneman** (OpenAI) — [1-sentence position]\n> [key reasoning, 1 line]\n\n**Torvalds** (Ollama) — [1-sentence position]\n> [key reasoning, 1 line]\n\n---\n\n### Synthesis\n\n**Where they align:** [what ≥4 agree on]\n\n**Strongest dissent:** [the most important disagreement — do not soften it]\n\n**Dissent quota triggered:** yes \u002F no — [if yes, who steelmanned what]\n\n**Unresolved questions:**\n- [question the council couldn't answer]\n- [what you'd need to know to decide with confidence]\n\n**Recommended next steps:** [concrete, not \"do more research\"]\n\n### Verdict\n**Recommendation:** [the synthesized path — commit to one]\n**Confidence:** [low \u002F medium \u002F high + why]\n**Reversibility:** [how hard to undo if wrong]\n```\n\n---\n\n## Quick Mode (3 personas)\n\nUse: Architect + Socrates + Torvalds\n\nBest for: tactical decisions, scope calls, technology choices\n\nOne round only. No Round 2. No dissent quota.\n\nOutput: same format but 3 positions only.\n\n## Duo Mode (2 personas)\n\nPick the two most opposing intellectual traditions for the question type:\n\n| Decision type | Best duo |\n|--------------|---------|\n| Technical architecture | Architect vs Torvalds |\n| Strategic direction | Feynman vs Kahneman |\n| Ship vs hold | Pragmatist vs Architect |\n| Question a premise | Socrates vs anyone |\n\nOne round. No restate gate (too short). Verdict required.\n\n---\n\n## Anti-Patterns\n\n```\n❌ Feeding the full conversation history to all personas (kills independence)\n❌ Hiding disagreement in the verdict to sound decisive\n❌ Using council for tasks with an objectively correct answer\n❌ Accepting ≥4-way agreement without triggering dissent quota\n❌ \"It depends\" without specifying the dependency\n❌ Council when the real blocker is missing information, not conflicting values\n```\n\n## Related Skills\n\n- `council` — 4-voice version, lighter\n- `multi-agent-debate` — Du et al. 2023 algorithm, multi-round consensus\n- `santa-method` — adversarial verification of a specific claim\n- `first-principles-thinker` — single voice, Feynman-style deconstruction\n",{"name":5,"modes":24,"origin":28,"license":15,"version":29,"triggers":30,"description":7},{"duo":25,"full":26,"quick":27},"2 opposing personas, 1 round (~45s)","6 personas, 2 rounds (~4 min)","3 personas, 1 round (~90s)","yana-ai — inspired by 0xNyk\u002Fcouncil-of-high-intelligence (CC0)","1.0.0",[31,32,33,34],"\u002Fcouncil-of-minds","council of minds","convene the council","multi-mind deliberation","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa",".claude\u002Fskills\u002Fcouncil-of-minds",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":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill council-of-minds",{"tool":51,"command":52},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill council-of-minds",{"tool":54,"command":55},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill council-of-minds","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcouncil-of-minds\u002FSKILL.md",true,[],[60,67,75,83,91,99],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":95,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]