the-fool

Use when challenging ideas, plans, decisions, or proposals. Invoke to play devil's advocate, run a pre-mortem, red team, stress test assumptions, audit evidence quality, or find blind spots before committing. Do NOT use for building plans, making decisions, or generating solutions — this skill only challenges and critiques. For a multi-agent panel that challenges and then commits to a verdict, use the-jury.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured process skill with a clear five-step workflow, explicit user-confirmation checkpoints, and excellent progressive disclosure into verified reference files. The only blemish is a small amount of persona/expertise flavor text that could be trimmed for token efficiency.

Suggestions

Trim the persona paragraph ('The court jester who alone could speak truth to the king...') to a single sentence — it establishes tone but spends tokens Claude doesn't need.

Replace the expertise name-drop list ('Gary Klein', 'Karl Popper', 'Kozyrkov', 'Annie Duke') with the framework names alone, or move the full attribution list into a reference file.

Dimension	Reasoning	Score
Conciseness	The body is largely lean — tables, terse constraint lists, a mapped workflow — but the persona flavor text ('The court jester who alone could speak truth to the king') and the name-dropping expertise paragraph ('Gary Klein... Karl Popper... Kozyrkov... Annie Duke') are minor over-explanation Claude does not need. This fits anchor 4 ('minor instances of over-explanation that could be trimmed') better than 5.	4 / 5
Actionability	For an instruction-only skill the guidance is fully executable: exact AskUserQuestion option tables in step 2, a mode-to-reference mapping table in step 3, numbered synthesis requirements with a confidence rubric in step 5, and a complete worked example showing actual outputs. The constraints section pins the behavior unambiguously.	5 / 5
Workflow Clarity	Five clearly sequenced steps with explicit validation checkpoints: confirm the steelman restatement with the user, structured mode selection, user must respond to each challenge before synthesis proceeds, and a confidence assessment with a concrete follow-up experiment when MEDIUM/LOW. No destructive or batch operations apply.	5 / 5
Progressive Disclosure	SKILL.md is a genuine overview: method detail is delegated to seven real reference files (all present in references/), each well-signaled via the mode mapping table, exactly one level deep, with no buried or nested references.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an exemplary skill description: concrete actions, explicit when-to-use triggers with natural phrasing, clear negative boundaries, and explicit disambiguation from a related skill. Voice is appropriately third-person/imperative.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'play devil's advocate, run a pre-mortem, red team, stress test assumptions, audit evidence quality, or find blind spots' — with comprehensive coverage and no gaps, matching the top anchor rather than the 'minor gaps' anchor at 4.	5 / 5
Completeness	It explicitly answers 'what' (the enumerated challenge actions) and 'when' ('Use when challenging ideas, plans, decisions, or proposals'), and additionally provides negative boundary guidance. Both questions are answered with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrasings are comprehensively covered with synonyms: 'challenging ideas, plans, decisions', 'devil's advocate', 'pre-mortem', 'red team', 'stress test assumptions', 'find blind spots'. These are exactly what a user would say when they need this skill.	5 / 5
Distinctiveness Conflict Risk	An explicit 'Do NOT use for building plans, making decisions, or generating solutions' clause plus redirection to a sibling skill ('use the-jury') gives it a clear niche with minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(decision-making)/the-fool/SKILL.md
Commit: 120b676

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.