Skip to content
SkillModel-led1,259 tokens in use

The Fool

Stress-test a plan, architecture or decision with five structured critical-reasoning modes, then synthesize a stronger position.

12,471 stars on the repository MIT LicenseJeffallan/claude-skills · skills/the-fool
/plugin install fullstack-dev-skills@fullstack-dev-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing The Fool costs

43tokens idle
1,259tokens in use
10,243tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter15/15
  • Structure23/25
  • Examples3/15
  • Output10/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity36
  • Momentum40

The Fool plays devil’s advocate with method. It restates your position in its strongest form, asks which kind of challenge you want, then applies one of five reasoning modes: Socratic questioning, dialectic, pre-mortem, red team or evidence audit.

It presents the three to five strongest challenges, waits for your response, and finishes with a synthesis and an offer of a second pass in a different mode.

What You Get

  • A five-step flow: identify, select, challenge, engage, synthesize
  • Two-step mode selection through structured questions to the user
  • Five modes, each with an output template: assumption inventory, counter-argument, ranked failure narratives, attack vectors, evidence audit
  • Six reference files, one per mode plus a mode selection guide

Common Use Cases

  • Pre-mortem on an architecture before implementation starts
  • Challenging a vendor or technology choice
  • Red-teaming a design for abuse and perverse incentives
  • Checking whether the evidence behind a business proposal supports its conclusion

What Makes It Unique

Most review skills look at code. This one reviews the reasoning behind a decision. It requires a steelman before any challenge, caps the challenges at the strongest few, forbids strawmen and stacked minor objections, and always ends with a synthesis the user can act on.

Under The Hood

The skill loads SKILL.md and opens one reference file for the chosen mode. It asks you questions through the agent’s structured question tool to pick the mode, and it waits for your reply before it synthesizes. It runs no commands, calls no APIs, fetches no web pages and writes no files. The skill ships no scripts.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers