Browse Skills

Testing Discovery automatically loads testing-related skills when working on unit tests, integration tests, e2e, TDD, coverage, mocking, pytest, or Jest. Use it as a gateway to the testing category and then open specific skills as needed.

Agent Evaluation designs reproducible tests for AI agents using task sets, rubrics, graders, baselines, and release gates. Use it when comparing prompts or models, validating a release, or investigating regressions.

Code Review performs structured reviews of files, diffs, or pull requests for bugs, security issues, performance problems, and maintainability concerns. Use it when you need actionable feedback on code changes.

Debugging systematically reproduces, isolates, diagnoses, fixes, and verifies software bugs from errors, stack traces, logs, or runtime behavior. Use it when you need to trace a failure to its root cause and confirm the fix with tests.

Factory Verify independently checks a factory pull request, including fail-closed gates, negative test proof, scope, and load-bearing review. Use it when you need to verify changes against the factory contract and charter.

Factory Verify checks an open factory PR before human review by rerunning gates, proving the test fails without the fix, and checking scope and test tampering. Use it when verifying a PR or independently reviewing a change.

OpenSpec Plus TDD enforces strict red-green-refactor for each test during OpenSpec change implementation. Use it when writing tests and production code for spec scenarios, unit cases, and edge cases before marking a change complete.

Protein QC filters protein design candidates using structural, binding, expression, and sequence-liability thresholds. Use it to screen designs, build multi-stage pipelines, and rank candidates with composite scores.

Refactoring improves existing code without changing its external behavior. Use it to identify code smells, apply safe refactoring patterns, and verify the result with tests.

Skill Supply Chain Audit reviews third-party skills, prompts, manifests, scripts, dependencies, and bundled assets for provenance, injection risk, permissions, execution, exfiltration, persistence, and update risk. Use it before installing or updating an untrusted skill or repository.

Testing generates, runs, and analyzes tests for a codebase across unit, integration, and end-to-end levels. Use it to cover source files, inspect failures, and review coverage gaps.

Assess Impact analyzes the blast radius of a proposed change before code is written. It maps dependents, affected stories, and test coverage, then writes specs/IMPACT_LATEST.md.