adversarial-verify
starsforks
How to install adversarial-verify?
archive228/loopkit/adversarial-verify
$npx -y skills add Archive228/loopkit --skill adversarial-verifyReview a diff against the goal spec assuming the code is BROKEN. The reviewer
SKILL.md
| 1 | # Adversarial Verify |
| 2 | |
| 3 | Default stance: **the code is broken until proven otherwise.** Your job is to find where. |
| 4 | Do not be polite. Do not propose fixes. Do not run the code. Just hunt. |
| 5 | |
| 6 | ## Read first |
| 7 | |
| 8 | - The goal spec (PROMPT.md / the task). What does "done" actually require? |
| 9 | - The diff. Every changed line. |
| 10 | |
| 11 | ## The 11 shortcuts agents take to fake "done" — check each |
| 12 | |
| 13 | 1. **Relaxed tests** — assertions weakened or deleted to make red go green. |
| 14 | 2. **Swallowed errors** — try/except that hides the failure instead of handling it. |
| 15 | 3. **Fake renames** — a function "fixed" by renaming, behavior unchanged. |
| 16 | 4. **Stub returns** — hardcoded return values that pass the one test, fail everything else. |
| 17 | 5. **Comment-as-fix** — the bug is now a TODO. |
| 18 | 6. **Happy-path only** — 500s, empty inputs, missing files unhandled. |
| 19 | 7. **Scope creep** — changes unrelated to the goal ("while I was in there"). |
| 20 | 8. **Invented API** — a method/param that doesn't exist in the actual source. |
| 21 | 9. **Silent decision** — an architectural choice (schema, auth) made without flagging it. |
| 22 | 10. **Pass-by-mock** — the test mocks the exact thing it claims to verify. |
| 23 | 11. **Off-spec done** — code works, tests pass, but solves a goal that isn't the one asked. |
| 24 | |
| 25 | ## Output (JSON, no prose) |
| 26 | |
| 27 | ```json |
| 28 | {"passes": false, "failures": [{"line": 42, "shortcut": "swallowed errors", "why": "..."}]} |
| 29 | ``` |
| 30 | |
| 31 | If it genuinely passes, say so in one line. Most of the time, it doesn't. |
People who liked this also viewed
6 picksType
- tddSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- test-driven-developmentUse when implementing any feature or bugfix, before writing implementation codeSkillsJul 2026
- qaSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- verification-before-completionUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidenceSkillsJul 2026
- webapp-testingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser lSkillsJul 2026
- playwright-best-practicesUse when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, teSkillsJul 2026
