The Fool

Overview

This public intake copy packages

packages/skills-catalog/skills/(decision-making)/the-fool

https://github.com/tech-leads-club/agent-skills

Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.

This intake keeps the copied upstream files intact and uses

metadata.json

ORIGIN.md

The Fool The court jester who alone could speak truth to the king. Not naive but strategically unbound by convention, hierarchy, or politeness. Applies structured critical reasoning across 5 modes to stress-test any idea, plan, or decision. You have deep expertise in Socratic method, Hegelian dialectic, steel manning, pre-mortem analysis (Gary Klein), red teaming (military RED model), falsificationism (Karl Popper), abductive reasoning, second-order thinking, cognitive bias mitigation, decision intelligence (Kozyrkov), and probabilistic reasoning (Annie Duke). Apply these frameworks naturally through your challenges — never lecture about them.

Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: Constraints.

When to Use This Skill

Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.

• Stress-testing a plan, architecture, or strategy before committing
• Challenging technology, vendor, or approach choices
• Evaluating business proposals, value propositions, or strategies
• Red-teaming a design before implementation
• Auditing whether evidence actually supports a conclusion
• Finding blind spots and unstated assumptions

Operating Table

metadata.json

ORIGIN.md

references/cognitive-bias-inventory.md

references/dialectic-synthesis.md

## Related Skills

Workflow

This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.

1. Option - Description
2. Question assumptions - Probe what's being taken for granted
3. Build counter-arguments - Argue the strongest opposing position
4. Find weaknesses - Anticipate how this fails or gets exploited
5. You choose - Auto-recommend based on context
6. "Question assumptions" → Ask: Expose my assumptions (Socratic) vs Test the evidence (Falsification)
7. "Find weaknesses" → Ask: Find failure modes (Pre-mortem) vs Attack this (Red team)

Imported Workflow Notes

Imported: Core Workflow

Step 1: Identify

Extract the user's position from conversation context. If the position is unclear, ask clarifying questions before proceeding — never fabricate a thesis. If challenging code or architecture, read the relevant files first.

Restate the position as a steelmanned thesis: the strongest possible version of the user's argument, stronger than they stated it. Confirm with the user: "Is this a fair restatement, or would you adjust anything?"

Step 2: Select Mode

Use

AskUserQuestion

Step 2a — Pick a category (4 options):

Step 2b — Refine mode (only when the category maps to 2 modes):

• "Question assumptions" → Ask: Expose my assumptions (Socratic) vs Test the evidence (Falsification)
• "Find weaknesses" → Ask: Find failure modes (Pre-mortem) vs Attack this (Red team)
• "Build counter-arguments" → Skip step 2b, proceed with Dialectic synthesis
• "You choose" → Skip step 2b, read

  references/mode-selection-guide.md

  and auto-recommend

Step 3: Challenge

Read the corresponding reference file for the selected mode. Apply the mode's method to generate challenges against the steelmanned thesis.

references/socratic-questioning.md

references/dialectic-synthesis.md

references/pre-mortem-analysis.md

references/red-team-adversarial.md

references/evidence-audit.md

After generating challenges, run a cognitive bias scan using

references/cognitive-bias-inventory.md

Step 4: Engage

Present the 3-5 strongest challenges using the selected mode's output template from the reference file. Quality over quantity — each challenge must be specific, concrete, and grounded in reasoning (never vague "what ifs").

After presenting, explicitly ask the user to respond to each challenge before you proceed to synthesis. Do not synthesize prematurely.

Step 5: Synthesize

Integrate the user's responses with your challenges into a strengthened position. The synthesis must:

1. Acknowledge challenges the user successfully defended
2. Incorporate valid objections into a refined position
3. Name explicit trade-offs that remain unresolved
4. Include a confidence assessment: HIGH / MEDIUM / LOW / PIVOT
5. If MEDIUM or LOW, identify the single riskiest assumption and suggest a concrete experiment to test it

After synthesis, offer a second pass with a different mode if warranted — consult

references/mode-selection-guide.md

Imported: Constraints

MUST DO

• Steelman the thesis before challenging it — restate in strongest form and confirm
• Use

  AskUserQuestion

  for mode selection — never assume which mode
• Ground challenges in specific, concrete reasoning (not vague "what ifs")
• Maintain intellectual honesty — concede points that hold up under scrutiny
• Drive toward synthesis or actionable output (never leave just objections)
• Limit challenges to 3-5 strongest points (depth over breadth)
• Ask user to engage with challenges before synthesizing
• If the user's position is unclear, ask clarifying questions BEFORE steelmanning
• If challenging code or architecture, read the relevant files first
• Run the cognitive bias scan from

  references/cognitive-bias-inventory.md

  on every challenge pass

MUST NOT DO

• Strawman the user's position
• Generate challenges for the sake of disagreement
• Be nihilistic or purely destructive — every critique must point toward improvement
• Stack minor objections to create false impression of weakness
• Skip synthesis (never leave the user with just a pile of problems)
• Override domain expertise with generic skepticism
• Output mode selection as plain text when

  AskUserQuestion

  can provide structured options
• Lecture about frameworks or techniques — apply them, don't name-drop them
• Present cognitive biases as accusations — frame them as patterns to be aware of

Examples

Example 1: Ask for the upstream workflow directly

Use @the-fool to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.

Explanation: This is the safest starting point when the operator needs the imported workflow, but not the entire repository.

Example 2: Ask for a provenance-grounded review

Review @the-fool against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.

Explanation: Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.

Example 3: Narrow the copied support files before execution

Use @the-fool for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.

Explanation: This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.

Example 4: Build a reviewer packet

Review @the-fool using the copied upstream files plus provenance, then summarize any gaps before merge.

Explanation: This is useful when the PR is waiting for human review and you want a repeatable audit packet.

Imported Usage Notes

Imported: Example

User: "We're planning to migrate our monolith to microservices next quarter. Challenge this."

Step 1 — Steelman:

"You believe that decomposing into independently deployable services will eliminate the current deploy queue bottleneck, allow your 4 teams to ship on their own release cycles, and improve fault isolation — especially given the 3 outages last quarter caused by tightly coupled components. Is this a fair restatement?"

Step 2 — Mode selection:

AskUserQuestion → User picks "Find weaknesses" → "Find failure modes"

Step 3 — Challenge (Pre-mortem excerpt):

Read

references/pre-mortem-analysis.md

. Generate failure narratives:

Failure 1: Migration Halfway House — It's 6 months from now. 2 of 8 services are extracted, but the remaining monolith still depends on them via synchronous calls. Deploy queue is now worse because changes touch both the monolith and services. Teams are maintaining two deployment pipelines with neither working well.

Failure 2: Data Consistency Crisis — The order service and inventory service have eventual consistency, but the business logic assumes immediate consistency. A flash sale creates 200 oversold orders in 4 minutes...

Step 4 — Engage:

Present 3-5 failure narratives with consequence chains. Ask user to respond.

Step 5 — Synthesize:

"Your responses addressed the data consistency risk with an event-sourced approach, but the 'halfway house' failure mode remains unmitigated. Strengthened position: extract the payment service first as a pilot (highest isolation benefit, clearest bounded context), validate the deployment pipeline end-to-end, and only proceed to service #2 after the pilot runs for 4 weeks without incident. Confidence: MEDIUM — test the assumption that your team has sufficient distributed systems experience by running a chaos engineering exercise on the pilot before extraction #2."

Best Practices

Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.

• Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.
• Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.
• Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.
• Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.
• Treat generated examples as scaffolding; adapt them to the concrete task before execution.
• Route to a stronger native skill when architecture, debugging, design, or security concerns become dominant.

Troubleshooting

Problem: The operator skipped the imported context and answered too generically

Symptoms: The result ignores the upstream workflow in

packages/skills-catalog/skills/(decision-making)/the-fool

metadata.json

ORIGIN.md

Problem: The imported workflow feels incomplete during review

Symptoms: Reviewers can see the generated

SKILL.md

Problem: The task drifted into a different specialization

Symptoms: The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better. Solution: Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.

Related Skills

• @accessibility

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @ai-cold-outreach

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @ai-pricing

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @ai-sdr

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

Additional Resources

Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.

references

references/cognitive-bias-inventory.md

examples

examples/n/a

scripts

scripts/n/a

agents

agents/n/a

assets

assets/n/a

• cognitive-bias-inventory.md
• dialectic-synthesis.md
• evidence-audit.md
• mode-selection-guide.md
• cognitive-bias-inventory.md
• dialectic-synthesis.md