the-fool

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.

Quality

76%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/the-fool/SKILL.md

Quality

Content

62%

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

This is a well-structured instruction-only skill with a clear multi-step workflow, good branching logic for mode selection, and strong constraints. Its main weaknesses are moderate redundancy across multiple tables describing the same 5 modes, lack of concrete examples showing what good challenge output looks like, and missing bundle reference files that the skill depends on for detailed guidance.

Suggestions

Add at least one concrete example showing a complete challenge cycle (thesis → challenges → synthesis) for one mode, so Claude has a clear model of expected output quality and format.

Consolidate the repeated mode information — the 5 Reasoning Modes table, Reference Guide table, and Output Templates table could be merged into a single comprehensive table to reduce redundancy.

Remove the 'Knowledge Reference' section at the bottom — Claude already knows these concepts, and the line adds no actionable guidance.

Provide the referenced bundle files (e.g., references/socratic-questioning.md) or note their absence, since the skill's actionability depends heavily on content that isn't present.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably well-structured but includes some redundancy — the mode information is repeated across the mode selection section, the 5 Reasoning Modes table, the reference guide table, and the output templates table. The knowledge reference list at the bottom adds little value since Claude already knows these concepts. However, it avoids explaining what these reasoning methods are in the body, deferring to reference files.	2 / 3
Actionability	The workflow is clearly described with specific steps and the mode selection process is concrete with structured options. However, there are no executable code examples or concrete challenge examples showing what a good output looks like in practice. The output templates section just lists deliverable names without showing actual example content, deferring entirely to reference files that aren't provided.	2 / 3
Workflow Clarity	The 5-step core workflow is clearly sequenced with explicit checkpoints: steelman before challenging, use AskUserQuestion for mode selection, present 3-5 challenges, wait for user engagement before synthesizing, then offer a second pass. The two-step mode selection process is well-documented with clear branching logic. The constraints section reinforces the workflow with explicit MUST DO/MUST NOT DO guardrails.	3 / 3
Progressive Disclosure	The skill references 6 separate reference files with clear load conditions, which is good progressive disclosure design. However, no bundle files were provided, meaning the referenced files don't actually exist in the evaluated bundle. The SKILL.md itself also contains some content that could be consolidated (mode info repeated in multiple tables), and the output templates section is too thin without the reference files to back it up.	2 / 3
	Total	9 / 12 Passed

Description

89%

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 a strong description with excellent trigger term coverage and clear 'Use when' guidance. Its main weakness is that it leans more toward describing when to invoke the skill than detailing the specific concrete actions or outputs it produces (e.g., does it generate a structured report, a list of risks, counterarguments?). Overall it would perform well in skill selection among a large set of skills.

Suggestions

Add more specific output actions to improve specificity, e.g., 'Generates structured counterarguments, identifies hidden assumptions, produces risk assessments and failure mode analyses.'

Dimension	Reasoning	Score
Specificity	The description names several specific techniques (devil's advocate, pre-mortem, red team, audit evidence and assumptions) but doesn't describe concrete output actions—it focuses more on when to use it than what specific deliverables or steps it produces.	2 / 3
Completeness	The description explicitly answers both 'when' ('Use when challenging ideas, plans, decisions, or proposals') and 'what' ('structured critical reasoning', 'play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions'). It opens with a clear 'Use when...' clause.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'devil's advocate', 'pre-mortem', 'red team', 'audit', 'challenge', 'assumptions', 'critical reasoning'. These are terms users would naturally use when seeking this kind of analysis.	3 / 3
Distinctiveness Conflict Risk	This skill occupies a clear niche around structured critical analysis and adversarial reasoning. Terms like 'devil's advocate', 'pre-mortem', and 'red team' are highly distinctive and unlikely to conflict with other skills.	3 / 3
	Total	11 / 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: Jeffallan/claude-skills
Commit: e8be415

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.