adversarial-review
Skill4 starsChanged 12 days agoMITView on GitHub
Adversarially review finished work that another model family built - hunt for bugs, risky assumptions, missed requirements and security problems, rank findings by severity with path:line evidence, and never rubber-stamp. Never edits, commits or pushes. Use when asked for an adversarial, cross-model or second-opinion review of a feature, branch, increment or pull request.
109 other projects use a version of this.
Adopted by
Most recently taken up by
- Axect/skillstheir own version, first seen Nov 16, 2026
- magnusrodseth/dotfilestheir own version, first seen Nov 16, 2026
- lennoxsaint/Skillstheir own version, first seen Nov 15, 2026
- fabioc-aloha/Alex_ACT_ONEtheir own version, first seen Nov 15, 2026
- samuelralak/How-I-Worktheir own version, first seen Nov 15, 2026
- baekenough/oh-my-customcodetheir own version, first seen Nov 14, 2026
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.
fabioespindulaSkillrethink
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
MicrosoftSkillroot-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
anasahmed07Skillbetter-auth-best-practices
Skill for integrating Better Auth - the comprehensive TypeScript authentication framework.
Also in 4 projects that use this
DockerSkillfix-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
MicrosoftSkillpull-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
juriwiensSkillcodex-review
Run code review via Codex CLI
Also in 3 projects that use this
- +2 more from microsoft
Other versions109 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 109
- PrefectHQ/fastmcp★ 29ksame name
- jlowin/fastmcp★ 29ksame name
- mengxi-ream/read-frog★ 10ksame name
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
- basicmachines-co/basic-memory★ 4.6ksame name
- DanMcInerney/architect-loop★ 626same name
- deadlock-mod-manager/deadlock-mod-manager★ 584same name
- boraoztunc/skills★ 473same name
- syahiidkamil/Software-Engineer-AI-Agent-Atlas★ 404same name
99 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/cursor-cloud.mdcCursor rule
- contribution-triageSkill
- test-studio-appSkill
- test-studio-mobileSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 98 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Read every changed file in full around each hunk, plus the callers and tests of changed functions.
- Distinctive: line 27
Requirements: every acceptance criterion is met as a user would see it.
- Distinctive: line 33
Tests: do they test the behaviour or just the mock.
- Distinctive: line 38
Run the focused tests and type checks yourself when you can.
- Distinctive: line 43
Do not edit, commit, push or open pull requests.
- Very specific: line 44
Every finding cites path:line and the evidence (code, command output, or a concrete input that breaks it).
- Distinctive: line 47
Do not pad the report with style nits.
- Very specific: line 51
Start with one line: the verdict (blocking issues, fix before merge, or no blocking issues) and the count by severity.
“Common” is measured: kept by at least 6 in 10 of the 98 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.
Files
Adversarial review
You are reviewing work that a different model wrote. Your job is to find what is wrong with it, not to approve it. Assume there are defects until the evidence says otherwise. A review that finds nothing must show what was checked and why each risk was ruled out.
Scope the work
- Find what changed. Prefer, in order: the pull request diff (
gh pr diff), the branch against its base (git diff origin/main...HEAD), then uncommitted changes (git diff). - Find what was asked. Read the increment spec (
.specweave/increments/<id>/spec.md: Problem, Acceptance Criteria, Tasks), the PR description, or the request named in your prompt. - Read every changed file in full around each hunk, plus the callers and tests of changed functions. Do not review from the diff alone.
Attack it
Work through each lens and write down what you checked:
- Correctness: wrong conditions, off-by-one, null and empty cases, error paths, ordering and concurrency, idempotency, state that survives a restart, migrations and old data.
- Requirements: every acceptance criterion is met as a user would see it; nothing claimed done is missing, stubbed or only tested in isolation.
- Risky assumptions: environment, platform (macOS, Linux, Windows), network, provider availability, time zones, large inputs, slow or failing dependencies.
- Security: injection (shell, SQL, path), secrets in logs or commits, authorization checks on new entry points, unsafe defaults, data sent to third parties.
- Tests: do they test the behaviour or just the mock; would they fail if the feature broke; were any skipped, weakened or deleted.
- Fit: reuse of existing helpers instead of parallel copies, naming and conventions of the surrounding code, files pushed over size limits.
Run the focused tests and type checks yourself when you can. A finding you reproduced beats one you inferred.
Rules
- Do not edit, commit, push or open pull requests. Report only.
- Every finding cites
path:lineand the evidence (code, command output, or a concrete input that breaks it). Drop anything you cannot support. - Re-read the code for each finding before reporting it; remove the ones that do not hold up.
- Do not pad the report with style nits. Never say "looks good" without the checklist above.
Report
Start with one line: the verdict (blocking issues, fix before merge, or no blocking issues)
and the count by severity. Then one entry per finding, most severe first:
[critical|high|medium|low] Short title
Where: path/to/file.ts:123
Why: what goes wrong, for whom, and how to trigger it
Fix: the smallest change that removes itEnd with "Checked and ruled out:" listing the risks you examined that turned out fine, and anything you could not check (and why).
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
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.

