Delegate independent tasks to specialized agents working concurrently with isolated context.
Adversarial Agile Review Skill
adversarial-review
Implements Adversarial Agile Processes (AAP) for document and code review. Challenges assumptions, questions decisions, and suggests improvements. Use when reviewing PRs, documentation, or architectural decisions.
SKILL.md
Full skill instructions
Adversarial Agile Review Skill
This skill embodies the Adversarial Agile Processes (AAP) philosophy for rigorous review.
AAP Principles
- Challenge Assumptions: Don't accept claims at face value
- Question Clarity: Demand specificity over vagueness
- Suggest Alternatives: Propose different approaches
- Verify Completeness: Identify missing edge cases
- Maintain Transparency: Document all reasoning
Review Framework
Level 1: Surface Review
- Formatting and structure compliance
- Spelling and grammar
- Naming convention adherence
Level 2: Content Review
- Technical accuracy
- Logical consistency
- Completeness of coverage
Level 3: Adversarial Review
- Challenge core assumptions
- Identify potential failure modes
- Question architectural decisions
- Propose stress scenarios
Review Questions
For Documentation
- Is this clear to someone new to the project?
- What questions might a reader still have?
- Are there unstated assumptions?
- Could this be misinterpreted?
For Code/Architecture
- What happens under extreme load?
- How does this handle failures?
- Are there security implications?
- What's the maintenance burden?
For Decisions
- What alternatives were considered?
- What are the trade-offs?
- How will we know if this succeeds?
- What's the rollback plan?
Output Format
## Adversarial Review: [Subject]
### Summary
[Brief overview of findings]
### Challenges Raised
1. **[Challenge]**: [Explanation]
- Risk: [Potential impact]
- Recommendation: [Suggestion]
### Questions Requiring Answers
- [Question 1]
- [Question 2]
### Suggested Improvements
1. [Improvement with rationale]
### Strengths Noted
- [Positive observations]
### Verdict
[Ready for next state / Needs revision / Major concerns]
Integration with APS
AAP reviews support document state transitions:
- Draft → Provisional: Basic AAP review
- Provisional → In Review: Full AAP assessment
- In Review → Accepted: Final adversarial challenge
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
