Loading...
Loading...
Found 14 Skills
Review a spec or concrete code changes and report evidence-backed bugs, regressions, and risks.
Use when encountering a bug, crash, or test failure. Not for code review or new features.
Reviews staged git changes for code quality, maintainability, readability, and potential regressions. Verifies changes make sense in context, improve maintainability, enhance readability, and don't introduce side effects. Use when reviewing staged changes, examining git diffs, or when the user asks to review modifications before committing.
Test-driven development using Red-Green-Refactor for bug fixes, new features, and regression prevention. Writes a failing test first to prove a defect or define behavior, then implements minimal code to pass, then refactors. Use when fixing bugs, encountering failing behavior, adding new features, writing tests, or when the user mentions TDD, red-green-refactor, regression test, failing test, test first, or test-driven.
Test-Driven Development with Iron Laws enforcement. Use when writing any production code to ensure tests are written first. Includes testing-expert capabilities.
Review code for performance: complexity, database/query efficiency, I/O and network cost, memory and allocation behavior, concurrency contention, caching, and latency/throughput regressions. Cognitive-only atomic skill; output is a findings list.
Optimizes AI skills for activation, clarity, and cross-model reliability. Use when creating or editing skill packs, diagnosing weak skill uptake, reducing regressions, tuning instruction salience, improving examples, shrinking context cost, or setting benchmark/release gates for skills. Trigger terms: skill optimization, activation gap, benchmark skill, with/without skill delta, regression, context budget, prompt salience.
Test-Driven Development enforces the RED-GREEN-REFACTOR discipline on every code change an agent produces.
Systematic workflow for verifying bug fixes to ensure quality and prevent regres...
Verify fix commits address audit findings without new bugs
Evidence-based 4-phase root cause analysis: Reproduce, Isolate, Identify, Verify. Use when user reports a bug, tests are failing, code introduced regressions, or production issues need investigation. Use for "debug", "fix bug", "why is this failing", "root cause", or "tests broken". Do NOT use for feature requests, refactoring, or performance optimization without a specific bug symptom.
Test-Driven Development methodology enforcing RED-GREEN-REFACTOR cycle. Use for writing tests first, preventing regression, and ensuring code correctness. Based on obra/superpowers.