From falsegreen-skill
Analyze test files for false-positive smells, meaning tests that pass even when the code breaks. Use when the user asks to review tests for false positives, weak assertions, mock misuse, test smells, or asks whether a test can actually fail. Covers Python (pytest, unittest), TypeScript, and JavaScript (Jest, Vitest, Mocha).
How this skill is triggered — by the user, by Claude, or both
Slash command
/falsegreen-skill:falsegreen-llmThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill is a thin entry point. The canonical protocol lives at the plugin
This skill is a thin entry point. The canonical protocol lives at the plugin root. Read these files before judging any test:
SKILL.md at the plugin root (relative to this file: ../../SKILL.md).
It defines Steps 0-7 and the six
judgments J1-J6.reference.md at the plugin root: the per-language pattern catalog with
look-alike exemptions. Consult it before flagging anything as HIGH.A test is useful only if it fails when the code breaks. Detect the language and framework, classify the test intent (spec, characterization, regression, behavior), then apply the six judgments: J1 does the assertion run, J2 is the expected value from an independent oracle, J3 is the real unit under test, J4 does the assertion verify enough, J5 is the test coupled to implementation internals, J6 does the test pass in isolation. For Python, also run the full structural catalog (families A-E, codes C1-C37). Flag only the first failing judgment per test.
reference.md before flagging.Use the CASE / SUMMARY format defined in the root SKILL.md Step 6:
CASE {number} ({J-code}) - {HIGH|LOW} - {language} - {intent}
Test / Finding / Evidence / Oracle (case 18 only) / Fix hint
Provides a checklist for code reviews covering functionality, security, performance, maintainability, tests, and quality. Use for pull requests, audits, team standards, and developer training.
npx claudepluginhub vinicq/falsegreen-skill --plugin falsegreen-skill