agentleFS
htnabehtnabe/skills/adversarial-review/SKILL.md

adversarial-review

Skill0 starsChanged 2 months agoMITView on GitHub

Independent adversarial review skill for implemented features, behavior changes, and bug fixes. Use after implementation to challenge correctness, security, maintainability, readability, test coverage, and regression safety. Reviews the implementation without modifying code and produces actionable findings.

104 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use rethink, root-cause-analysis and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • fabioespindulaSkill

    rethink

    Reframe a plan, idea, or decision before the user commits to it. Use when the user asks to rethink, step back, pressure-test, gut-check, decide, right-size, simplify, think bigger about, or evaluate a concrete plan or decision in product, strategy, technical architecture, career, life, company direction, or personal priorities. This skill improves decision quality before action: clarify the real question, challenge assumptions, compare alternatives, calibrate ambition, classify the operating mode, surface risks, and recommend a next move. Do not use for broad future exploration without a concrete decision; that belongs to a think-big or research-style skill.

    Also in 3 projects that use this

  • MicrosoftSkill

    root-cause-analysis

    Use when a Regional Retail Manager asks I'm seeing unusual inventory movement at our Northwest stores. Can you help me understand what's happening?

    Also in 3 projects that use this

  • anasahmed07Skill

    better-auth-best-practices

    Skill for integrating Better Auth - the comprehensive TypeScript authentication framework.

    Also in 4 projects that use this

  • DockerSkill

    fix-issue

    Fix a single GitHub issue end-to-end: triage, research, write the fix, review, and create a PR. Use when asked to fix an issue: "fix issue 1234", "resolve #500", "create a PR for issue 200".

    Also in 3 projects that use this

  • MicrosoftSkill

    pull-request

    Write concise, focused pull request descriptions for Wassette — at most three sentences on the what and why, with an explicit note on any breaking public-API change and how users adapt. Use when opening or editing a Wassette pull request.

    Also in 3 projects that use this

  • juriwiensSkill

    codex-review

    Run code review via Codex CLI

    Also in 3 projects that use this

  • +2 more from microsoft

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 93 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill after implementation to independently challenge correctness, requirements coverage, security, maintainability, readability, …

    line 9
  2. Distinctive:

    Do not modify source code, tests, configuration, or documentation during review unless the caller explicitly requests review fixes.

    line 11
  3. Distinctive:

    Treat explicit user requirements as the primary oracle.

    line 15
  4. Distinctive:

    Do not assume correctness because the implementation is small, idiomatic, similar to existing code, or covered by passing tests.

    line 16
  5. Distinctive:

    Look for plausible failure scenarios, not theoretical concerns without meaningful impact.

    line 17
  6. Distinctive:

    Use this priority order when evidence conflicts:

    line 20
  7. Distinctive:

    Every substantive finding must include severity, location, problem, impact, concrete scenario, and a remediation direction.

    line 48
  8. Distinctive:

    PASS: no material defects identified.

    line 52

“Common” is measured: kept by at least 6 in 10 of the 93 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Adversarial Review

Use this skill after implementation to independently challenge correctness, requirements coverage, security, maintainability, readability, test quality, and regression safety. This is a review workflow, not an implementation workflow.

Do not modify source code, tests, configuration, or documentation during review unless the caller explicitly requests review fixes.

Review Principles

  • Treat explicit user requirements as the primary oracle.
  • Do not assume correctness because the implementation is small, idiomatic, similar to existing code, or covered by passing tests.
  • Look for plausible failure scenarios, not theoretical concerns without meaningful impact.
  • Report actionable defects and distinguish them from optional improvements.

Use this priority order when evidence conflicts:

  1. Explicit user requirements
  2. Acceptance criteria
  3. Current implementation and architecture
  4. Tests and CI behavior
  5. Repository conventions and instructions
  6. Existing documentation
  7. Historical assumptions

Workflow

1. Understand the Change

Establish the requested and changed behavior, changed files, assumptions, preserved behavior, and affected interfaces or contracts. Read relevant implementation, tests, configuration, documentation, and repository instructions.

2. Inspect the Diff and Trace Behavior

Review the complete final diff for unintended modifications, deleted behavior, changed defaults or interfaces, configuration and dependency changes, generated or missing files, and suspicious workarounds. Trace important paths from input through validation and transformation to state changes, failures, side effects, and returned results. Inspect callers and dependencies when relevant.

3. Challenge the Implementation

For each applicable review dimension, determine whether behavior is correct, requirements are fully covered, regressions are possible, tests prove observable behavior, security boundaries hold, errors are intentional, and design remains maintainable and readable. Use the detailed review criteria. Apply adversarial techniques when the change calls for them.

At minimum, consider correctness, regression safety, test quality, security, error handling, maintainability, readability, and scope. Consider performance, resources, dependencies, and configuration when relevant. Skip categories that do not apply.

4. Report Findings

Every substantive finding must include severity, location, problem, impact, concrete scenario, and a remediation direction. Order findings by severity, do not inflate severity, and do not invent findings. Use the reporting format.

Conclude with exactly one status:

  • PASS: no material defects identified.
  • CHANGES_REQUESTED: one or more material findings should be addressed.
  • HUMAN_REVIEW_REQUIRED: unresolved ambiguity, missing information, external dependencies, or requirement conflict prevents reliable review.

Review Boundaries

The review should inspect implementation, tests, relevant context, and the final diff; challenge assumptions; and report actionable risks independently. It should not implement fixes, refactor unrelated code, expand scope, impose personal style preferences, or approve merely because tests pass.

Completion Criteria

The review is complete when the requested behavior, relevant paths and tests, final diff, correctness, regression risks, applicable security concerns, maintainability, readability, edge cases, finding severity, and final status have all been considered. The report should be concise enough to act on and detailed enough to reproduce each substantive finding.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.