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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

A well-structured, actionable skill body with a clear sequenced workflow and clean one-level-deep progressive disclosure. The only weakness is mild verbosity from persona flavor text and parenthetical scholar attributions that the skill itself discourages.

Suggestions

Trim the persona preamble ("The court jester who alone could speak truth to the king...") to one line or move it to a reference file — it costs tokens without aiding execution.

Drop the parenthetical author attributions (e.g., "(Gary Klein)", "(Karl Popper)", "(Annie Duke)"); the skill explicitly warns against name-dropping frameworks, so listing them in the header undercuts that instruction.

Consider moving the dense expertise inventory in the opening paragraph into references/mode-selection-guide.md, keeping SKILL.md focused on the workflow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the opening persona flavor ("The court jester who alone could speak truth to the king...") and parenthetical name attributions ("(Gary Klein)", "(Karl Popper)", "(Annie Duke)") are tokens that do not earn their place, especially given the skill's own rule against name-dropping.	2 / 3
Actionability	Highly actionable for an instruction-only skill: exact AskUserQuestion option tables, a mode→reference-file mapping table, and a fully worked monolith-to-microservices example showing each step's concrete output.	3 / 3
Workflow Clarity	A clearly sequenced 5-step process (Identify → Select → Challenge → Engage → Synthesize) with explicit validation checkpoints — steelman confirmation, user engagement before synthesis — and recovery guidance for MEDIUM/LOW confidence.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview pointing to seven one-level-deep reference files via an explicit mode→reference mapping table; all referenced files exist in ./references/, and there is no deeper nesting.	3 / 3
	Total	11 / 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.

A highly specific, well-triggered description that clearly states both what the skill does and when to use it, with explicit negative scope that sharply reduces conflict risk. No changes needed.

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, or find blind spots" — matching the top anchor; voice is imperative ("Use when...") consistent with the good examples, so no first/second-person penalty applies.	3 / 3
Completeness	Explicitly answers both what ("only challenges and critiques") and when ("Use when challenging ideas, plans, decisions, or proposals") with an explicit trigger clause, plus a negative-scope clause.	3 / 3
Trigger Term Quality	Strong coverage of natural phrases a user would actually say — "challenge", "devil's advocate", "pre-mortem", "red team", "stress test assumptions", "blind spots" — well beyond a single keyword.	3 / 3
Distinctiveness Conflict Risk	A clear niche (challenge/critique only) reinforced by "Do NOT use for building plans, making decisions, or generating solutions" makes it unlikely to trigger for the wrong skill.	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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tech-leads-club/agent-skills
Commit: 9026164

Reviewed: 4 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.