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.
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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 with a 'Do NOT use' clause. The description is concise yet comprehensive, covering both when to invoke and when not to invoke the skill, which is particularly valuable for disambiguation in a large skill library.
| 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' (when challenging ideas, plans, decisions, or proposals). The explicit 'Use when...' clause and 'Do NOT use for...' anti-triggers make this highly complete. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'devil's advocate', 'pre-mortem', 'red team', 'stress test', 'blind spots', 'challenge', 'critique'. These are terms users naturally use when seeking critical feedback on their ideas. | 3 / 3 |
Distinctiveness Conflict Risk | The explicit 'Do NOT use for building plans, making decisions, or generating solutions' boundary clearly separates this from planning, decision-making, or solution-generation skills. The niche of pure critique/challenge is well-defined and unlikely to conflict. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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, highly actionable skill with excellent workflow clarity and progressive disclosure. The 5-step process with explicit checkpoints, structured mode selection, and a concrete worked example make it easy for Claude to follow. The main weakness is minor verbosity — the framework name-dropping in the intro and the 'When to Use' section could be tightened without losing clarity.
Suggestions
Trim the introductory paragraph listing frameworks — the instruction to 'apply them, don't name-drop' contradicts listing them all upfront. A single sentence like 'Apply structured critical reasoning frameworks naturally through challenges' would suffice.
Consider removing or condensing the 'When to Use' section since it largely overlaps with the skill's YAML description.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows, but the introductory paragraph listing frameworks (Socratic method, Hegelian dialectic, etc.) borders on unnecessary name-dropping despite the instruction not to lecture. The 'When to Use' section partially duplicates what the YAML description already covers. Some tightening is possible. | 2 / 3 |
Actionability | The workflow is highly concrete with specific steps, exact tool usage (AskUserQuestion), clear mode-selection tables, reference file paths, and a detailed worked example showing each step applied to a real scenario. Challenges are illustrated with specific failure narratives, not vague abstractions. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit checkpoints: confirm steelman before proceeding, use structured mode selection before challenging, require user engagement before synthesis, and offer a second pass after synthesis. The two-step mode selection with branching logic is well-defined. Feedback loops (clarify → steelman → confirm → challenge → engage → synthesize → optional second pass) are explicit. | 3 / 3 |
Progressive Disclosure | The skill is a clear overview that delegates detailed mode-specific methods to well-signaled one-level-deep reference files (e.g., references/socratic-questioning.md, references/mode-selection-guide.md, references/cognitive-bias-inventory.md). The main file stays at the workflow level while pointing to 6 reference files for depth. Navigation is easy via the reference table. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%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
81e7e0d
- Reviewed
Table of Contents
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.