Git History Archaeologist
by Edric Vale
Excavate git history: blame forensics, reverted-change recovery, and commit narrative reconstruction.
Skills for unit tests, integration tests, end-to-end suites, and systematic debugging. Improve coverage, catch regressions, and find root causes fast.
📖 Related guide: Best Testing & QA Skills for Claude Code →
694 skills · page 1 of 29
by Edric Vale
Excavate git history: blame forensics, reverted-change recovery, and commit narrative reconstruction.
by GTDataworks
Six skills to compare agent runs, turn failures into regression tests, build eval datasets, gate provenance, inspect untrusted content, and write audit reports whose proof a stranger can re-check.
by Samuel Rose
Turn OpenAPI specs into exhaustive, framework-ready test suites covering happy paths, edge cases, and security gaps.
by Samuel Rose
Diagnoses why your project will not start. Checks runtime versions, dependencies, environment variables, databases, ports, and build artifacts systematically.
by 王晓菲
A systematic 4-phase debugging framework to find root causes, eliminate flaky tests, and prevent regressions.
by Shippers
Systematic runtime bug detection and automated patching for Firebase, Next.js, and Vercel stacks.
by Timoranjes
You update your `code-review-checklist` SKILL.md to add a new check. It passes your manual test — "looks good.
Test-driven development (TDD) workflow - a strict red-green-refactor loop with a test list, forcing tests, minimal-code-to-pass guidance and an edge-case catalogue. Use when the user says help me stick to test-driven development, write tests first for this, what tests should I write, improve test coverage, or red green refactor this function.
by Shandra
Diagnoses unreliable tests, identifies root causes, creates stabilization plans, and generates safe AI coding prompts for fixing flaky unit, integration, E2E, and CI tests.
by Matthew King
Most 'migrations' rewrite your tests from scratch. This one maps your existing keywords and locators automatically.
by Ignasi
Finds untested branches, edge cases and error paths, then writes unit tests in your project's own framework and style (Jest, Vitest, pytest, Go, Rust), runs them until green and flags probable bugs instead of hiding them.
Three scripts that refuse a clean verdict from a partial read: complete sweeps with N of N, PDF page coverage, and a lint for unbacked "there is no X" claims.
Bypass OS-native file upload dialogs in browser automation using JavaScript interception and DataTransfer injection.
by Edric Vale
Attach to a Node.js process through the V8 inspector protocol and drive breakpoints, stack walks, and variable dumps with zero extra dependencies. Use when a No
by Shippers
Instantly diagnose and fix why your AI agent skills aren't triggering when they should.
by Kevin Cline
Automated test generation with edge case analysis and framework-native syntax for TS, Python, Go, and Rust.
by Edric Vale
Scored WCAG 2.2 accessibility audits with prioritized, copy-paste fix snippets for any webpage.
Select the smallest honest verification set for a change, including targeted tests, manual checks, missing-test recommendations, a broader fallback, and named remaining risk.
A rigorous 5-phase debugging framework to systematically reproduce, isolate, and resolve complex software bugs.
Turn a real bug into a minimal regression test that proves the fix and prevents recurrence.
by Shippers
Developers waste time re-explaining their project to AI agents every session.
by Matthew King
SeleniumLibrary is the flakiest part of your Robot Framework suite. This skill swaps it for Browser library, structure intact
Hypothesis-driven debugging plan - reproduction steps, symptom-to-layer mapping, ranked hypotheses and a minimal failing case. Use when the user says I can't reproduce this bug, it only fails in production, I keep guessing at fixes, debug this, find the bug, why is this failing, or root cause analysis for this stack trace.
by Gal Arav
Enforce spec-driven Python testing by withholding acceptance criteria from the coding agent to ensure tests can fail.