adversarial-test-review
Skill2 starsChanged 4 months agoMITView on GitHub
Adversarial pre-merge review for implementation and tests. Use for code review, PR review, or safe-to-ship questions.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- agent-dag-plannerSkill
- agent-plan-implementerSkill
- airtight-feature-deliverySkill
- deep-bug-auditSkill
- mivia-agent-workflowsSkill
- test-coverage-auditSkill
- adversarial-test-reviewSkill
- agent-dag-plannerSkill
- agent-plan-implementerSkill
- airtight-feature-deliverySkill
- deep-bug-auditSkill
- mivia-agent-workflowsSkill
- test-coverage-auditSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Very specific: line 13
Read .ai/skills/adversarial-test-review/SKILL.md first.
- Very specific: line 15
Use mivia-agent-report/v1 from .ai/templates/agent-report-v1.md.
- Distinctive: line 20
Treat missing mutation proof as a coverage gap.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Adversarial Test Review
Read .ai/skills/adversarial-test-review/SKILL.md first. Follow AGENTS.md and .ai/rules/20-agent-quality.md.
Use mivia-agent-report/v1 from .ai/templates/agent-report-v1.md; do not define a Codex-specific report shape.
Codex-specific behavior:
- Lead with blocking findings.
- Treat missing mutation proof as a coverage gap.
- State unrun verifiers plainly.
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.

