Back to catalog
Human reviewedOther

Skill dossier

the-fool

Source declaration

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.

The author's original description, preserved in English. It describes intent, not verified performance.

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.

references

Research summary

Human reviewed

Skill Atlas editorial review · editorial-preview-1.0.0

A critical-reasoning skill that steelmans the user's position, lets them choose among five challenge modes, and then presents the strongest objections before synthesizing a stronger position.

Review scope

Deterministic static analysis of collected SKILL.md and supporting text/code. Machine-assisted candidates and findings await human editorial review; no dynamic behavior or effect is assessed.

Observable capabilities

  • Restates the user's position as a steelmanned thesis for confirmation.
  • Uses AskUserQuestion for two-step mode selection.
  • Applies Socratic, dialectic, pre-mortem, red team or evidence-audit methods.
  • Presents 3-5 challenges and ends with a synthesis and next steps.

Limitations & scope

  • Relies on the AskUserQuestion tool being available for mode selection.
  • Output quality depends on how much context the user shares about the idea.
  • It challenges reasoning but does not independently verify facts.

Relevant for

  • Engineers and founders stress-testing a plan
  • Teams doing pre-mortems or design reviews
  • Anyone who wants structured devil's advocacy

What ships with the skill

The file inventory comes from the collected source at the recorded commit. Paths and sizes are structural observations, not a measure of quality.

files
7
Markdown files
7
scripts
0
references
6
Size
45.3 KB
Structural complexity
Low

File inventory

PathTypeBytes
skills/the-fool/references/dialectic-synthesis.mdReference6.3 KB
skills/the-fool/references/evidence-audit.mdReference8.3 KB
skills/the-fool/references/mode-selection-guide.mdReference4.5 KB
skills/the-fool/references/pre-mortem-analysis.mdReference7.9 KB
skills/the-fool/references/red-team-adversarial.mdReference7 KB
skills/the-fool/references/socratic-questioning.mdReference5.2 KB
skills/the-fool/SKILL.mdInstruction6.2 KB

SKILL.md frontmatter

{
  "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",
    "company": "https://synergetic.solutions",
    "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"
  }
}

A reading of the operating sequence

This workflow reconstructs the apparent sequence from source material. Unless controlled evaluation is explicitly recorded, it is provisional—not an observed trace.

  1. 01
    Input

    Identify the position

    Extract the user's position from context and restate it as a steelmanned thesis for confirmation.

  2. 02
    Action

    Apply the chosen mode

    Apply the selected mode's method and load the corresponding reference file.

  3. 03
    Decision

    Let the user respond

    Present the 3-5 strongest challenges and ask the user to respond before proceeding.

  4. 04
    Output

    Deliver the synthesis

    Final output includes the steelmanned thesis, challenges, user response, synthesis and next steps.

Potential risk surfaces

Static findings identify points to inspect before installation. They do not establish that a skill is safe, malicious, or effective.

Items warrant review

4 deterministic lexical finding(s) require review across the collected text. Findings can occur in documentation and do not prove execution or exploitability; binary-only files were not scanned.

Network accessObserved
File writesNot observed
Credential useNot observed
Medium

Network access is mentioned

4 occurrences

A URL or network client appears in this source line. Review destinations, data sent, and trust boundaries; static text cannot establish actual network activity. This rule matched 4 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Editorial security note

Low direct risk, but avoid pasting confidential plans or credentials into the conversation unless you are comfortable with them being discussed.

Where context can be spent

Discovery, activation, and resource layers have different meanings. Exact values appear only when the official token-counting method was run with a named model.

Exact token counts unavailable

All token values, including per-file inventory, are null until the pipeline performs an official exact count with an explicit model.

No token measurement was recorded with the required official method. This dossier does not substitute character counts, file sizes, or estimates.

Controlled evaluation

No controlled evaluation

This skill has only the evidence identified above. No task success, token efficiency, latency, or quality advantage is claimed.

Not tested

Use with the source in view

Install command
git clone https://github.com/Jeffallan/claude-skills.git cd claude-skills # Copy this skill directory into one of: # ~/.claude/skills/the-fool # .claude/skills/the-fool
  1. Open the pinned source at https://github.com/Jeffallan/claude-skills/blob/67c1961b180dc92cf08983344627109e983e8f51/skills/the-fool/SKILL.md.
  2. Review the license, prerequisites and all bundled reference files.
  3. Copy the skill directory into a personal or project-level Claude Code skills directory.
  4. Restart or refresh Claude Code so the skill can be discovered.
Verify installation

Confirm SKILL.md is discoverable at the destination, then ask Claude Code to use the-fool on a small task.

Prerequisites

  • Relies on the AskUserQuestion tool being available for mode selection.
  • Output quality depends on how much context the user shares about the idea.
  • It challenges reasoning but does not independently verify facts.

Example prompts

Representative task

Use the the-fool skill on my plan to migrate our monolith to microservices this quarter. Restate my position, let me pick the mode, and then run a pre-mortem on it.

Inspect before use

Read the the-fool skill at https://github.com/Jeffallan/claude-skills/blob/67c1961b180dc92cf08983344627109e983e8f51/skills/the-fool/SKILL.md. Explain its workflow, required tools, permissions and the main risks before I decide whether to install it.

A decision, with its limits attached

Strengths

  • Guards against pointless objections: steelman first, limit to 3-5 points, always synthesize.
  • Five distinct modes with a dedicated reference file for each.

Considerations

  • The interactive back-and-forth may be slow if you want a one-shot critique.
  • Mode choice shapes the result, so a poor selection can miss key risks.
Research conclusion

A disciplined review skill for decisions where structured challenge is worth the extra conversation.

Traceable by construction

The dossier is a time-bound reading of a public artifact, not an endorsement. Use the source link to inspect the exact upstream material.

Jeffallanclaude-skillsskills/the-fool
Source type
Community
Commit
67c1961b180dc92cf08983344627109e983e8f51
Collected
20 Nov 2026
Last checked
20 Nov 2026
Upstream license
MIT
Repository stars
12,464
Content basis

Deterministic lexical parsing, YAML frontmatter validation, file inventory, source-described workflow extraction, and heuristic provisional classification of the supplied files only. Generated by machine; no LLM, execution, dynamic testing, or human editorial approval.