the-fool

An agent skill by Jeffallan, from Jeffallan/claude-skills. Tags: brainstorming, evaluation, priority, research, strategy.

What it does

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.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add Jeffallan/claude-skills --skill the-fool

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/Jeffallan/claude-skills
cp -r claude-skills/skills/the-fool ~/.claude/skills/the-fool

Safety box score

Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a purely conversational reasoning workflow: it restates a user’s position, asks them to choose a critique mode, and produces structured challenges and synthesis. It does not ship scripts or automation, and the main concern is only prompt-instruction behavior inside the agent, not machine or data access.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, code evaluation, or native scripts are present; the skill is markdown-only.
Network access	0 (none)	The files only contain documentation and links; there is no code that fetches data or sends requests.
Filesystem reach	0 (none)	Nothing reads, writes, or deletes files on the host; it only references local markdown guides conceptually.
Secrets & credentials	0 (none)	The skill does not ask for tokens, passwords, .env files, or other credentials.
Privilege & persistence	0 (none)	There is no sudo, installation, service registration, or system-setting behavior.
Instruction hijack surface	0 (none)	The instructions are about structured critique and mode selection; there is no hidden text or directive to ignore higher-priority instructions.
Irreversible actions	0 (none)	It does not perform external actions like posting, deploying, purchasing, or deleting; it only generates analysis for the user.
Transparency	0 (none)	All shipped content is plain markdown and readable; there are no binaries, blobs, or generated-at-runtime code paths.

Before installing

Skim `SKILL.md` to confirm it is only a reasoning workflow and not an action runner.
Check that the repository contains only markdown reference files and no scripts or installers.
If you care about prompt behavior, verify the mode-selection and synthesis rules match how you want the agent to respond.

Rated 2026-10-20 by an automated review of 7 files from the skill's repository.

Source

Repository: Jeffallan/claude-skills (all skills from this repository)
Path: skills/the-fool/SKILL.md
Branch: main
Updated: 2026-09-19

let-fate-decide — Draws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated.
interpreting-culture-index — Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data.
marketing-council — When the user wants multiple expert perspectives on a marketing question — a simulated board of advisors staffed by legendary marketers (Seth Godin.
marketing-ideas — When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product.
feature-forge — Conducts structured requirements workshops to produce feature specifications, user stories, EARS-format functional requirements, acceptance criteria.
office-hours — YC Office Hours — two modes. (gstack)