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.

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

This is a strong, well-crafted skill with an exceptionally clear multi-step workflow, concrete examples, and good separation of concerns via reference files. Its main weaknesses are minor verbosity (the thematic framing and framework name-dropping in the preamble contradict its own 'don't lecture' constraint) and the inability to verify the referenced bundle files. The actionability is excellent — the microservices example walks through every step concretely.

Suggestions

Remove or significantly trim the second paragraph listing frameworks (Socratic method, Hegelian dialectic, etc.) — it contradicts the 'never lecture about them' constraint and wastes tokens on knowledge Claude already has.

Consider moving the full example to a separate references/example-walkthrough.md file to keep the main SKILL.md leaner while preserving the detailed demonstration.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and well-structured, but includes some unnecessary framing (the court jester metaphor, the list of frameworks in paragraph 2 that it then says to never lecture about). The constraints section has some redundancy with the workflow steps. Could be tightened by ~20%.	2 / 3
Actionability	Highly actionable with a clear 5-step workflow, specific mode selection tables, concrete example showing each step applied to a real scenario (microservices migration), explicit reference file paths for each mode, and structured output expectations (confidence assessment, experiment suggestions). Claude knows exactly what to do at each step.	3 / 3
Workflow Clarity	The 5-step workflow is clearly sequenced with explicit checkpoints: confirm steelman before proceeding, use AskUserQuestion for mode selection, ask user to respond before synthesizing, offer second pass after synthesis. The two-step mode selection with branching logic is well-defined. Feedback loops are present (clarify if unclear, engage before synthesizing, second pass if warranted).	3 / 3
Progressive Disclosure	The skill references 6 external files in the references/ directory for detailed mode instructions, mode selection guidance, and cognitive bias inventory — which is good progressive disclosure design. However, no bundle files were provided, meaning these references are unverifiable. The main SKILL.md itself is well-organized with clear sections, but the inline example is fairly long and could potentially be in a separate file.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 excellent skill description that clearly defines its purpose, provides rich trigger terms, and explicitly delineates its boundaries. The inclusion of a 'Do NOT use' clause is particularly effective for distinguishing this skill from planning or decision-making skills. The description is concise yet comprehensive, covering both positive triggers and negative boundaries.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'play devil's advocate, run a pre-mortem, red team, stress test assumptions, audit evidence quality, find blind spots.' Also explicitly states what it does NOT do, adding further specificity.	3 / 3
Completeness	Clearly answers both 'what' (challenges ideas, critiques, stress tests assumptions, audits evidence) and 'when' (explicit 'Use when challenging ideas, plans, decisions, or proposals'). Also includes a 'Do NOT use' clause which further clarifies scope.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'devil's advocate', 'pre-mortem', 'red team', 'stress test', 'blind spots', 'challenging ideas', 'critique'. These are terms users would naturally use when seeking critical analysis.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche — it only challenges and critiques, explicitly excluding plan-building, decision-making, and solution generation. The 'Do NOT use' clause significantly reduces conflict risk with planning or decision-making skills.	3 / 3
	Total	12 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: tech-leads-club/agent-skills
Commit: 5f9b25d

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.