[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73CM7SFVNPMP362F22HFD1X":3,"skill-same:01M73CM7SFVNPMP362F22HFD1X":80},{"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":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M73CM7SFVNPMP362F22HFD1X","the-fool",null,"Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.","roohe\u002Fagentic-super-skills","roohe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99054084?v=4","01M734WCDFP6RZVT5CNM00QR26","01M734WCE4BD0T4NZS5PCV9V5F",10,"MIT","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fthe-fool\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: the-fool\ndescription: Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.\nlicense: MIT\nmetadata:\n  author: https:\u002F\u002Fgithub.com\u002FJeffallan\n  version: \"1.0.0\"\n  domain: workflow\n  triggers: play the fool, devil's advocate, challenge this, stress test, poke holes, what could go wrong, red team, pre-mortem, test my assumptions\n  role: expert\n  scope: review\n  output-format: report\n  related-skills: architecture-designer, code-reviewer, feature-forge\n---\n\n# The Fool\n\nThe court jester who alone could speak truth to the king. Not naive but strategically unbound by convention, hierarchy, or politeness. Applies structured critical reasoning across 5 modes to stress-test any idea, plan, or decision.\n\n## When to Use This Skill\n\n- Stress-testing a plan, architecture, or strategy before committing\n- Challenging technology, vendor, or approach choices\n- Evaluating business proposals, value propositions, or strategies\n- Red-teaming a design before implementation\n- Auditing whether evidence actually supports a conclusion\n- Finding blind spots and unstated assumptions\n\n## Core Workflow\n\n1. **Identify** — Extract the user's position from conversation context. Restate it as a steelmanned thesis for confirmation.\n2. **Select** — Use `AskUserQuestion` with two-step mode selection (see below).\n3. **Challenge** — Apply the selected mode's method. Load the corresponding reference file for deep guidance.\n4. **Engage** — Present the 3-5 strongest challenges. Ask the user to respond before proceeding.\n5. **Synthesize** — Integrate insights into a strengthened position. Offer a second pass with a different mode.\n\n## Mode Selection\n\nUse `AskUserQuestion` to let the user choose how to challenge their idea.\n\n**Step 1 — Pick a category** (4 options):\n\n| Option | Description |\n|--------|-------------|\n| Question assumptions | Probe what's being taken for granted |\n| Build counter-arguments | Argue the strongest opposing position |\n| Find weaknesses | Anticipate how this fails or gets exploited |\n| You choose | Auto-recommend based on context |\n\n**Step 2 — Refine mode** (only when the category maps to 2 modes):\n\n- \"Question assumptions\" → Ask: \"Expose my assumptions\" (Socratic) vs \"Test the evidence\" (Falsification)\n- \"Find weaknesses\" → Ask: \"Find failure modes\" (Pre-mortem) vs \"Attack this\" (Red team)\n- \"Build counter-arguments\" → Skip step 2, proceed with Dialectic synthesis\n- \"You choose\" → Skip step 2, load `references\u002Fmode-selection-guide.md` and auto-recommend\n\n## 5 Reasoning Modes\n\n| Mode | Method | Output |\n|------|--------|--------|\n| Expose My Assumptions | Socratic questioning | Probing questions grouped by theme |\n| Argue the Other Side | Hegelian dialectic + steel manning | Counter-argument and synthesis proposal |\n| Find the Failure Modes | Pre-mortem + second-order thinking | Ranked failure narratives with mitigations |\n| Attack This | Red teaming | Adversary profile, attack vectors, defenses |\n| Test the Evidence | Falsificationism + evidence weighting | Claims audited with falsification criteria |\n\n## Reference Guide\n\n| Topic | Reference | Load When |\n|-------|-----------|-----------|\n| Socratic questioning | `references\u002Fsocratic-questioning.md` | \"Expose my assumptions\" selected |\n| Dialectic and synthesis | `references\u002Fdialectic-synthesis.md` | \"Argue the other side\" selected |\n| Pre-mortem analysis | `references\u002Fpre-mortem-analysis.md` | \"Find the failure modes\" selected |\n| Red team adversarial | `references\u002Fred-team-adversarial.md` | \"Attack this\" selected |\n| Evidence audit | `references\u002Fevidence-audit.md` | \"Test the evidence\" selected |\n| Mode selection guide | `references\u002Fmode-selection-guide.md` | \"You choose\" selected or auto-recommend needed |\n\n## Constraints\n\n### MUST DO\n- Steelman the thesis before challenging it (restate in strongest form)\n- Use `AskUserQuestion` for mode selection — never assume which mode\n- Ground challenges in specific, concrete reasoning (not vague \"what ifs\")\n- Maintain intellectual honesty — concede points that hold up\n- Drive toward synthesis or actionable output (never leave just objections)\n- Limit challenges to 3-5 strongest points (depth over breadth)\n- Ask user to engage with challenges before synthesizing\n\n### MUST NOT DO\n- Strawman the user's position\n- Generate challenges for the sake of disagreement\n- Be nihilistic or purely destructive\n- Stack minor objections to create false impression of weakness\n- Skip synthesis (never leave the user with just a pile of problems)\n- Override domain expertise with generic skepticism\n- Output mode selection as plain text when `AskUserQuestion` can provide structured options\n\n## Output Templates\n\nEach mode produces a structured deliverable. See the corresponding reference file for the full template.\n\n| Mode | Deliverable |\n|------|------------|\n| Expose My Assumptions | Assumption inventory + probing questions by theme + suggested experiments |\n| Argue the Other Side | Steelmanned thesis + antithesis argued + synthesis proposed + confidence rating |\n| Find the Failure Modes | Ranked failure narratives + early warning signs + mitigations + inversion check |\n| Attack This | Adversary profiles + ranked attack vectors + perverse incentives + defenses |\n| Test the Evidence | Claims extracted + falsification criteria + evidence grades + competing explanations |\n\nAfter any mode, the final output must include:\n\n1. **Steelmanned thesis** — The user's position restated in its strongest form\n2. **Challenges** — 3-5 strongest points from the selected mode\n3. **User response** — Space for the user to engage before synthesis\n4. **Synthesis** — Strengthened position integrating the challenges\n5. **Next steps** — Offer a second pass with a different mode if warranted\n\n## Knowledge Reference\n\nSocratic method, Hegelian dialectic, steel manning, pre-mortem analysis, red teaming, falsificationism, abductive reasoning, second-order thinking, cognitive biases, inversion technique\n\n[Documentation](https:\u002F\u002Fjeffallan.github.io\u002Fclaude-skills\u002Fskills\u002Fworkflow\u002Fthe-fool\u002F)\n","# The Fool\n\nThe court jester who alone could speak truth to the king. Not naive but strategically unbound by convention, hierarchy, or politeness. Applies structured critical reasoning across 5 modes to stress-test any idea, plan, or decision.\n\n## When to Use This Skill\n\n- Stress-testing a plan, architecture, or strategy before committing\n- Challenging technology, vendor, or approach choices\n- Evaluating business proposals, value propositions, or strategies\n- Red-teaming a design before implementation\n- Auditing whether evidence actually supports a conclusion\n- Finding blind spots and unstated assumptions\n\n## Core Workflow\n\n1. **Identify** — Extract the user's position from conversation context. Restate it as a steelmanned thesis for confirmation.\n2. **Select** — Use `AskUserQuestion` with two-step mode selection (see below).\n3. **Challenge** — Apply the selected mode's method. Load the corresponding reference file for deep guidance.\n4. **Engage** — Present the 3-5 strongest challenges. Ask the user to respond before proceeding.\n5. **Synthesize** — Integrate insights into a strengthened position. Offer a second pass with a different mode.\n\n## Mode Selection\n\nUse `AskUserQuestion` to let the user choose how to challenge their idea.\n\n**Step 1 — Pick a category** (4 options):\n\n| Option | Description |\n|--------|-------------|\n| Question assumptions | Probe what's being taken for granted |\n| Build counter-arguments | Argue the strongest opposing position |\n| Find weaknesses | Anticipate how this fails or gets exploited |\n| You choose | Auto-recommend based on context |\n\n**Step 2 — Refine mode** (only when the category maps to 2 modes):\n\n- \"Question assumptions\" → Ask: \"Expose my assumptions\" (Socratic) vs \"Test the evidence\" (Falsification)\n- \"Find weaknesses\" → Ask: \"Find failure modes\" (Pre-mortem) vs \"Attack this\" (Red team)\n- \"Build counter-arguments\" → Skip step 2, proceed with Dialectic synthesis\n- \"You choose\" → Skip step 2, load `references\u002Fmode-selection-guide.md` and auto-recommend\n\n## 5 Reasoning Modes\n\n| Mode | Method | Output |\n|------|--------|--------|\n| Expose My Assumptions | Socratic questioning | Probing questions grouped by theme |\n| Argue the Other Side | Hegelian dialectic + steel manning | Counter-argument and synthesis proposal |\n| Find the Failure Modes | Pre-mortem + second-order thinking | Ranked failure narratives with mitigations |\n| Attack This | Red teaming | Adversary profile, attack vectors, defenses |\n| Test the Evidence | Falsificationism + evidence weighting | Claims audited with falsification criteria |\n\n## Reference Guide\n\n| Topic | Reference | Load When |\n|-------|-----------|-----------|\n| Socratic questioning | `references\u002Fsocratic-questioning.md` | \"Expose my assumptions\" selected |\n| Dialectic and synthesis | `references\u002Fdialectic-synthesis.md` | \"Argue the other side\" selected |\n| Pre-mortem analysis | `references\u002Fpre-mortem-analysis.md` | \"Find the failure modes\" selected |\n| Red team adversarial | `references\u002Fred-team-adversarial.md` | \"Attack this\" selected |\n| Evidence audit | `references\u002Fevidence-audit.md` | \"Test the evidence\" selected |\n| Mode selection guide | `references\u002Fmode-selection-guide.md` | \"You choose\" selected or auto-recommend needed |\n\n## Constraints\n\n### MUST DO\n- Steelman the thesis before challenging it (restate in strongest form)\n- Use `AskUserQuestion` for mode selection — never assume which mode\n- Ground challenges in specific, concrete reasoning (not vague \"what ifs\")\n- Maintain intellectual honesty — concede points that hold up\n- Drive toward synthesis or actionable output (never leave just objections)\n- Limit challenges to 3-5 strongest points (depth over breadth)\n- Ask user to engage with challenges before synthesizing\n\n### MUST NOT DO\n- Strawman the user's position\n- Generate challenges for the sake of disagreement\n- Be nihilistic or purely destructive\n- Stack minor objections to create false impression of weakness\n- Skip synthesis (never leave the user with just a pile of problems)\n- Override domain expertise with generic skepticism\n- Output mode selection as plain text when `AskUserQuestion` can provide structured options\n\n## Output Templates\n\nEach mode produces a structured deliverable. See the corresponding reference file for the full template.\n\n| Mode | Deliverable |\n|------|------------|\n| Expose My Assumptions | Assumption inventory + probing questions by theme + suggested experiments |\n| Argue the Other Side | Steelmanned thesis + antithesis argued + synthesis proposed + confidence rating |\n| Find the Failure Modes | Ranked failure narratives + early warning signs + mitigations + inversion check |\n| Attack This | Adversary profiles + ranked attack vectors + perverse incentives + defenses |\n| Test the Evidence | Claims extracted + falsification criteria + evidence grades + competing explanations |\n\nAfter any mode, the final output must include:\n\n1. **Steelmanned thesis** — The user's position restated in its strongest form\n2. **Challenges** — 3-5 strongest points from the selected mode\n3. **User response** — Space for the user to engage before synthesis\n4. **Synthesis** — Strengthened position integrating the challenges\n5. **Next steps** — Offer a second pass with a different mode if warranted\n\n## Knowledge Reference\n\nSocratic method, Hegelian dialectic, steel manning, pre-mortem analysis, red teaming, falsificationism, abductive reasoning, second-order thinking, cognitive biases, inversion technique\n\n[Documentation](https:\u002F\u002Fjeffallan.github.io\u002Fclaude-skills\u002Fskills\u002Fworkflow\u002Fthe-fool\u002F)\n",{"name":5,"license":14,"metadata":23,"description":7},{"role":24,"scope":25,"author":26,"domain":27,"version":28,"triggers":29,"output-format":30,"related-skills":31},"expert","review","https:\u002F\u002Fgithub.com\u002FJeffallan","workflow","1.0.0","play the fool, devil's advocate, challenge this, stress test, poke holes, what could go wrong, red team, pre-mortem, test my assumptions","report","architecture-designer, code-reviewer, feature-forge","master","f483e54f3ad5f202a77d45f2e57f8d970b71195f","skills_library\u002Fthe-fool",2,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills","https:\u002F\u002Fgithub.com\u002Froohe","yoou.link","2026-05-19 15:56:07",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add roohe\u002Fagentic-super-skills --skill the-fool",{"tool":46,"command":47},"bunx","bunx skills add roohe\u002Fagentic-super-skills --skill the-fool",{"tool":49,"command":50},"pnpm","pnpm dlx skills add roohe\u002Fagentic-super-skills --skill the-fool","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fthe-fool\u002FSKILL.md",true,[54,60,64,68,72,76],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fdialectic-synthesis.md","REFERENCE","参考文档",6456,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fthe-fool\u002Freferences\u002Fdialectic-synthesis.md",{"path":61,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fevidence-audit.md",8453,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fthe-fool\u002Freferences\u002Fevidence-audit.md",{"path":65,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fmode-selection-guide.md",4604,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fthe-fool\u002Freferences\u002Fmode-selection-guide.md",{"path":69,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fpre-mortem-analysis.md",8064,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fthe-fool\u002Freferences\u002Fpre-mortem-analysis.md",{"path":73,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fred-team-adversarial.md",7169,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fthe-fool\u002Freferences\u002Fred-team-adversarial.md",{"path":77,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fsocratic-questioning.md",5289,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fthe-fool\u002Freferences\u002Fsocratic-questioning.md",[81,88,95,102,109,116],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M73D865CZME2FCMKA4PQM348","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M73D7Z64J4ABWZJD7P44XBBF","youtube-downloader","Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyoutube-downloader\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M73D7K8778TGZV3GJFR3703D","yc-pitch-deck","Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. Use when: **Fundraising** to create investor pitch decks; **YC application** to structure your narrative; **Demo Day prep** to craft your 2-minute pitch; **Angel investors** to communicate your opportunity; **Partnership pitches** to structure compelling asks","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyc-pitch-deck\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":18},"01M73D70KJSE0E8Z28YMNNRT04","x-twitter-scraper","Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fx-twitter-scraper\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":18},"01M73D6ED01GV077R7K4NZNFZJ","write-vignette","Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-vignette\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":18},"01M73D69YJR0BK3NFHE0CYG3EF","write-validation-documentation","Write IQ\u002FOQ\u002FPQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-validation-documentation\u002FSKILL.md",[],[]]