Agent skill
adversarial-review
Install this agent skill to your Project
npx add-skill https://github.com/ilude/claude-code-config/tree/main/skills/adversarial-review
SKILL.md
Adversarial Review Framework
Auto-activate when: User mentions red-team, adversarial review, find flaws, edge cases, blind spots, attack vectors, "what could go wrong", "poke holes in this", or asks to critique/challenge a plan or design.
Best for: Red-team attack on plans/systems to find flaws, edge cases, blind spots
Template (5 Phases)
{BASE_TARGET}
Phase 1: Challenge Assumptions
- What assumptions does this make?
- Which assumptions are most likely wrong?
- What happens if each assumption fails?
Phase 2: Edge Case Mining
- Boundary conditions (empty, null, max, negative)
- Timing issues (race conditions, ordering)
- Environment variations (OS, versions, permissions)
- Data quality issues (malformed, missing, duplicate)
Phase 3: Failure Mode Analysis
- List 5 ways this could fail
- For each: Likelihood (H/M/L), Impact (1-10), Mitigation
- Which failures are catastrophic?
Phase 4: Hidden Dependencies
- Undocumented state assumptions
- External service dependencies
- Implicit ordering requirements
- Configuration assumptions
Phase 5: Attack Vectors & Blind Spots
- What did we not consider?
- What expertise are we missing?
- Where could malicious input cause issues?
- What would break this in production?
Principles
Be adversarial. If you don't find issues, you weren't critical enough.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
python-testing
Python-specific testing practices with pytest, fixtures, mocking, async testing, coverage configuration, and uv execution rules. Activate when working with pytest files, conftest.py, test directories, pyproject.toml testing configuration, or Python test-related tasks.
archive-reprocessing
Flexible, version-tracked reprocessing system for archive transformations using design patterns (Strategy, Template Method, Observer). Activate when working with tools/scripts/lib/, reprocessing scripts, transform versions, archive transformations, metadata transformers, or incremental processing workflows.
structured-analysis
typescript-testing
TypeScript/JavaScript testing practices with Bun's test runner. Activate when working with bun test, .test.ts, .test.js, .spec.ts, .spec.js, testing TypeScript/JavaScript, bunfig.toml, testing configuration, or test-related tasks in Bun projects.
python-workflow
Python project workflow guidelines. Triggers: .py, pyproject.toml, uv, pip, pytest, Python. Covers package management, virtual environments, code style, type safety, testing, configuration, CQRS patterns, and Python-specific development tasks.
hanami-workflow
Hanami framework workflow guidelines. Activate when working with Hanami projects, Hanami CLI, or Hanami-specific patterns.
Didn't find tool you were looking for?