Poke Holes In My Plan Before I Commit
Unverified●30/40Claude Code◐PartialHas SKILL.md but declares no allowed-tools — Claude Code will ask for permission each time
Cursor◐PartialPlain prose you can paste in — but no Cursor rules file
Codex◐PartialPlain prose you can paste in — but no AGENTS.md
Gemini CLI◐PartialPlain prose you can paste in
Copilot◐PartialPlain prose you can paste in — but no Copilot instructions file
npx agentalley add the-foolWho is stuck, and on what
I'm about to make a big call and everyone around me just nods along. I need someone to tell me what I'm missing before I spend the money.
What it gives you
A written stress-test of your plan: the strongest arguments against it, the ways it could fail, the assumptions you didn't notice you were making, and a strengthened version to move forward with.
When NOT to use it
It will not make the decision for you or guarantee an outcome — it hands you the risks and counter-arguments to weigh yourself.
The whole source
Frontmatter — 4 properties
| name | the-fool |
|---|---|
| description | 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. |
| license | MIT |
| metadata | author: https://github.com/Jeffallan version: "1.0.0 domain: workflow triggers: play the fool, devil's advocate, challenge this, stress test, poke holes, what could go wrong, red team, pre-mortem, test my assumptions role: expert scope: review output-format: report related-skills: architecture-designer, code-reviewer, feature-forge |
| 1 | --- |
| 2 | name: the-fool |
| 3 | description: 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. |
| 4 | license: MIT |
| 5 | metadata: |
| 6 | author: https://github.com/Jeffallan |
| 7 | version: "1.0.0" |
| 8 | domain: workflow |
| 9 | triggers: play the fool, devil's advocate, challenge this, stress test, poke holes, what could go wrong, red team, pre-mortem, test my assumptions |
| 10 | role: expert |
| 11 | scope: review |
| 12 | output-format: report |
| 13 | related-skills: architecture-designer, code-reviewer, feature-forge |
| 14 | ---A5 — No allowed-tools declared — no way to tell what this skill may touch |
| 15 | |
| 16 | # The Fool |
| 17 | |
| 18 | The 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. |
| 19 | |
| 20 | ## When to Use This Skill |
| 21 | |
| 22 | - Stress-testing a plan, architecture, or strategy before committing |
| 23 | - Challenging technology, vendor, or approach choices |
| 24 | - Evaluating business proposals, value propositions, or strategies |
| 25 | - Red-teaming a design before implementation |
| 26 | - Auditing whether evidence actually supports a conclusion |
| 27 | - Finding blind spots and unstated assumptions |
| 28 | |
| 29 | ## Core Workflow |
| 30 | |
| 31 | 1. **Identify** — Extract the user's position from conversation context. Restate it as a steelmanned thesis for confirmation. |
| 32 | 2. **Select** — Use `AskUserQuestion` with two-step mode selection (see below). |
| 33 | 3. **Challenge** — Apply the selected mode's method. Load the corresponding reference file for deep guidance. |
| 34 | 4. **Engage** — Present the 3-5 strongest challenges. Ask the user to respond before proceeding. |
| 35 | 5. **Synthesize** — Integrate insights into a strengthened position. Offer a second pass with a different mode. |
| 36 | |
| 37 | ## Mode Selection |
| 38 | |
| 39 | Use `AskUserQuestion` to let the user choose how to challenge their idea. |
| 40 | |
| 41 | **Step 1 — Pick a category** (4 options): |
| 42 | |
| 43 | | Option | Description | |
| 44 | |--------|-------------| |
| 45 | | Question assumptions | Probe what's being taken for granted | |
| 46 | | Build counter-arguments | Argue the strongest opposing position | |
| 47 | | Find weaknesses | Anticipate how this fails or gets exploited | |
| 48 | | You choose | Auto-recommend based on context | |
| 49 | |
| 50 | **Step 2 — Refine mode** (only when the category maps to 2 modes): |
| 51 | |
| 52 | - "Question assumptions" → Ask: "Expose my assumptions" (Socratic) vs "Test the evidence" (Falsification) |
| 53 | - "Find weaknesses" → Ask: "Find failure modes" (Pre-mortem) vs "Attack this" (Red team) |
| 54 | - "Build counter-arguments" → Skip step 2, proceed with Dialectic synthesis |
| 55 | - "You choose" → Skip step 2, load `references/mode-selection-guide.md` and auto-recommend |
| 56 | |
| 57 | ## 5 Reasoning Modes |
| 58 | |
| 59 | | Mode | Method | Output | |
| 60 | |------|--------|--------| |
| 61 | | Expose My Assumptions | Socratic questioning | Probing questions grouped by theme | |
| 62 | | Argue the Other Side | Hegelian dialectic + steel manning | Counter-argument and synthesis proposal | |
| 63 | | Find the Failure Modes | Pre-mortem + second-order thinking | Ranked failure narratives with mitigations | |
| 64 | | Attack This | Red teaming | Adversary profile, attack vectors, defenses | |
| 65 | | Test the Evidence | Falsificationism + evidence weighting | Claims audited with falsification criteria | |
| 66 | |
| 67 | ## Reference Guide |
| 68 | |
| 69 | | Topic | Reference | Load When | |
| 70 | |-------|-----------|-----------| |
| 71 | | Socratic questioning | `references/socratic-questioning.md` | "Expose my assumptions" selected | |
| 72 | | Dialectic and synthesis | `references/dialectic-synthesis.md` | "Argue the other side" selected | |
| 73 | | Pre-mortem analysis | `references/pre-mortem-analysis.md` | "Find the failure modes" selected | |
| 74 | | Red team adversarial | `references/red-team-adversarial.md` | "Attack this" selected | |
| 75 | | Evidence audit | `references/evidence-audit.md` | "Test the evidence" selected | |
| 76 | | Mode selection guide | `references/mode-selection-guide.md` | "You choose" selected or auto-recommend needed | |
| 77 | |
| 78 | ## Constraints |
| 79 | |
| 80 | ### MUST DO |
| 81 | - Steelman the thesis before challenging it (restate in strongest form) |
| 82 | - Use `AskUserQuestion` for mode selection — never assume which mode |
| 83 | - Ground challenges in specific, concrete reasoning (not vague "what ifs") |
| 84 | - Maintain intellectual honesty — concede points that hold up |
| 85 | - Drive toward synthesis or actionable output (never leave just objections) |
| 86 | - Limit challenges to 3-5 strongest points (depth over breadth) |
| 87 | - Ask user to engage with challenges before synthesizing |
| 88 | |
| 89 | ### MUST NOT DO |
| 90 | - Strawman the user's position |
| 91 | - Generate challenges for the sake of disagreement |
| 92 | - Be nihilistic or purely destructive |
| 93 | - Stack minor objections to create false impression of weakness |
| 94 | - Skip synthesis (never leave the user with just a pile of problems) |
| 95 | - Override domain expertise with generic skepticism |
| 96 | - Output mode selection as plain text when `AskUserQuestion` can provide structured options |
| 97 | |
| 98 | ## Output Templates |
| 99 | |
| 100 | Each mode produces a structured deliverable. See the corresponding reference file for the full template. |
| 101 | |
| 102 | | Mode | Deliverable | |
| 103 | |------|------------| |
| 104 | | Expose My Assumptions | Assumption inventory + probing questions by theme + suggested experiments | |
| 105 | | Argue the Other Side | Steelmanned thesis + antithesis argued + synthesis proposed + confidence rating | |
| 106 | | Find the Failure Modes | Ranked failure narratives + early warning signs + mitigations + inversion check | |
| 107 | | Attack This | Adversary profiles + ranked attack vectors + perverse incentives + defenses | |
| 108 | | Test the Evidence | Claims extracted + falsification criteria + evidence grades + competing explanations | |
| 109 | |
| 110 | After any mode, the final output must include: |
| 111 | |
| 112 | 1. **Steelmanned thesis** — The user's position restated in its strongest form |
| 113 | 2. **Challenges** — 3-5 strongest points from the selected mode |
| 114 | 3. **User response** — Space for the user to engage before synthesis |
| 115 | 4. **Synthesis** — Strengthened position integrating the challenges |
| 116 | 5. **Next steps** — Offer a second pass with a different mode if warranted |
| 117 | |
| 118 | ## Knowledge Reference |
| 119 | |
| 120 | Socratic method, Hegelian dialectic, steel manning, pre-mortem analysis, red teaming, falsificationism, abductive reasoning, second-order thinking, cognitive biases, inversion technique |
| 121 | |
| 122 | [Documentation](https://jeffallan.github.io/claude-skills/skills/workflow/the-fool/) |
| 123 |
Reviews
Installed this one?Write the first review and take the Trailblazer badge.
Alternatives
Task Coordination StrategiesDecompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.◐◐◐◐◐●35/40Ebay Seller Tools·····●34/40Tough Decision Advisor: Every Angle ConsideredHand in a decision you're stuck on. Get back a clear breakdown of every angle — the trade-offs, the risks, the blind spot, and a recommended path.●····●32/40DHDNA Profiler — Cognitive Pattern ExtractionPaste any email, proposal, or note someone wrote, and get back a plain-language read on how they think, what drives their decisions, and how they communicate.●····●32/40