Loading...
Loading...
Found 143 Skills
Implement the fix for a GitHub issue from its RCA artifact (created by piv-investigate-issue) — drift-check the plan, branch, implement, add regression tests, and validate. Use after the investigation artifact exists and you're ready to fix the issue.
Use when writing or reviewing tests for Python behavior, contracts, async lifecycles, or reliability paths. Also use when tests are flaky, coupled to implementation details, missing regression coverage, slow to run, or when unclear what tests a change needs.
Apply when asked to probe, stress, fuzz, or chaos-test a running product, feature, or PR for defects nobody has reported, or to go hunting for bugs against a live surface. Two passes: a probe pass over a closed category taxonomy, and a promotion gate that keeps only findings a real caller can reach. Promoted findings leave a committed regression test behind. The rest are dismissed with a reason, carried as an explicit gap, or escalated when the call is not the agent's to make.
Safe deployment of Polymarket trading bot with regression tests and active trade protection
Hypothesis-driven autonomous debugging with real command validation
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only.
Percy integration. Manage data, records, and automate workflows. Use when the user wants to interact with Percy data.
Find the root cause of a bug before fixing it. Use when a bug, test failure, or unexpected behavior appears, before proposing any fix.
Bug-to-test pipeline: reproduce the bug as a failing test first, then fix. The regression test lives forever.
Diagnosticar bugs, regressões, falhas intermitentes e problemas de performance por reprodução, minimização, hipótese falsificável e instrumentação até a causa no nível do mecanismo. Use quando o usuário pedir diagnóstico ou relatar algo quebrado, incluindo falhas intermitentes e degradação de performance; não implementar correção quando o pedido for somente diagnóstico; não use para otimizar algo que já funciona corretamente sem sintoma, use `$specsfy-specialist-performance-engineering` para isso.
Standardize requirement/feature changes in an existing codebase (especially Chrome extensions) by turning "改需求/需求变更/调整交互/改功能/重构流程" into a repeatable loop: clarify acceptance criteria, confirm current behavior from code, assess impact/risk, design the new logic, implement with small diffs, run a fixed regression checklist, and update docs/decision log. Use when the user feels the change process is chaotic, when edits tend to sprawl across files, or when changes touch manifest/service worker/OAuth/storage/UI and need reliable verification + rollback planning.
Systematic web application QA testing with structured issue taxonomy, health scoring, and regression tracking. Use this skill when the user asks for QA testing, systematic testing, smoke testing, regression testing, web app testing, browser testing, or says "QA this", "test the app", "smoke test", "run QA", "systematic test", "check the site", "regression test", "full QA", "/qa-systematic". Supports full, quick, and regression modes.