# Adversarial Decision Analysis

> Stress-tests competing options by searching for counterexamples and surfacing the strongest downside before recommending a choice. Use when evaluating decisions, tradeoffs, architecture options, vendor selection, hire/no-hire calls, research conclusions, or any recommendation that needs adversarial scrutiny before commitment.

- Skill: `justtyashh/adversarial-decision-analysis` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add justtyashh/adversarial-decision-analysis`
- Raw SKILL.md: https://api.skillmd.com/api/skills/justtyashh/adversarial-decision-analysis/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: JusttYashh (https://skillmd.com/u/justtyashh)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/justtyashh/adversarial-decision-analysis

---


# Adversarial Decision Analysis

## When to use

Use when the user is choosing between options and has not yet stress-tested the leading candidate.

## Procedure

1. State the decision to be made in one sentence.
2. Generate candidate options (at least two).
3. Weigh pros and cons for each option.
4. Search for counterexamples and disconfirming evidence against the leading option.
5. Surface the strongest downside of the leading option explicitly.
6. Recommend a choice only after unresolved risks are documented.

Do not recommend until step 5 is complete.

## Additional resources

- Evidence and session citations: [evidence.md](evidence.md)