flow-next-epic-review
Epic completion review - verifies all epic tasks implement spec requirements. Triggers on /flow-next:epic-review.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-28 00:17
Testing & quality
12,793 results
fuzzing-go-expert
Use this skill to fuzz open source Go software projects.
msw
Mock Service Worker (MSW) patterns for API mocking in development and testing. Covers request handlers, response mocking, network error simulation, handler…
playwright
Playwright patterns for end-to-end testing including page object model, fixtures, locators, assertions, API testing, visual regression, and CI integration. Use…
tdd-typescript
TypeScript/JavaScript Test-Driven Development with Vitest, strict red-green-refactor methodology, domain-first modeling (DDD) via branded types, principled DRY…
test-generation
Comprehensive test suite generation with unit tests, integration tests, edge cases, and error handling. Use when generating tests for existing code, improving…
repair-proof
Repair named implementation or evidence gaps from a NOT PROVEN proof, report the change honestly, and require fresh proof without declaring acceptance.
critique
Adversarial code review of a diff for a human to triage. Advisory, never blocks. Owns the axes that /code-review and /review-tests do not cover - scope creep,…
ask-gg
Answer how to use this repo's skills, reading the latest version from GitHub.
electrobun-debugging
Development workflow, debugging, and troubleshooting for Electrobun desktop applications. This skill covers debugging the main process (Bun) and webview…
foundry
Foundry — Forge, Cast, Anvil, Chisel; EVM tooling, cheatcodes, scripting, lint, debugging.
halo2
Skills for building and debugging PLONK circuits with halo2_proofs (zcash/halo2)
skill-eval
Use only when explicitly asked to evaluate one repository skill package against its exact old-skill or no-skill baseline. Run the same realistic cases on one…
checks
Pre-commit quality gate: auto-fix formatting/lint, verify types, run tests. Use when user asks to "run checks", "/checks", "verify before commit", or wants to…
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user…
helpmetest-troubleshoot
Triage skill for when something stopped working and you don't know why. Use when user says 'what's wrong', 'it was working a minute ago', 'something broke',…
validate-tests
Invoke this skill when a user shares test code and questions whether it actually works as intended — not to run or fix the test, but to evaluate whether the…
tidy
Review changed code for reuse, quality, and efficiency, then apply cleanup edits. Dispatches a fresh host-provided reviewer per iteration when available; the…
execution-model
Trade execution modeling (backtest only) — slippage formulas (linear / square-root impact), VWAP/TWAP execution logic, market-impact cost estimation, and…
risk-analysis
Risk measurement and stress testing — VaR/CVaR/max drawdown calculation, Monte Carlo simulation, extreme-value tail-risk analysis, and historical scenario…
android-tooling
Configure Android static analysis with Detekt, Ktlint, and Android Lint for CI/CD quality gates. Use for Android-specific lint and quality tooling; defer…
aftership-webhooks
Receive and verify AfterShip webhooks. Use when setting up AfterShip webhook handlers, debugging AfterShip signature verification (aftership-hmac-sha256,…
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
diagnose
Use when a concrete bug, failed check, regression, flake, or performance symptom needs read-only root-cause isolation before any fix; reproduce it, test…