Loading...
Loading...
Found 137 Skills
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.
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
Bug diagnosis and fixing specialist - analyzes errors, identifies root causes, provides fixes, and writes regression tests
Automatically generates comprehensive test suites (unit, integration, E2E) based on code and past testing patterns. Use when user says "write tests", "test this", "add coverage", or after fixing bugs to create regression tests. Eliminates testing friction for ADHD users.
Troubleshoot and fix bugs systematically. Use when errors occur, tests fail, or unexpected behavior is observed. Covers root cause analysis and debugging strategies.
Coordinates code quality checks: ln-511 code quality, ln-512 tech debt cleanup, ln-513 agent review, ln-514 regression. Sequential pipeline, returns results to ln-500.
Bug-to-test pipeline: reproduce the bug as a failing test first, then fix. The regression test lives forever.
Use when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.
Drives a disciplined explore → plan → implement → verify loop for changing an AI agent's behavior with confidence — whether fixing a reported failure or introducing a new requirement, business rule, or policy. Grounds the diagnosis in MLflow traces, codifies the desired behavior as a regression test suite (`mlflow.genai.evaluate` assertions in `@mlflow.test` pytest tests), and iterates the agent — not the test — until green, resisting quick system-prompt patches when the real fix is upstream (missing tool, retrieval source, or capability). Use whenever the user wants to fix or change how an agent behaves — e.g. "fix this issue in my agent", "this answer is wrong", "the agent is hallucinating", "improve my agent based on this trace", "make the agent do X instead of Y", "I want the agent to lead with/prioritize/recommend X", "new business rule: the agent should X", "always/never do X", "change the agent's default behavior" — or shares a trace they want addressed.
Applies tests-first discipline (red/green/refactor) and adds regression tests for bugs. Use when implementing features, fixing bugs, or refactoring.
Audit and harden a repository test suite so tests carry their weight. Use when the user asks whether tests are useful, flaky, duplicated, slow, under-covering critical behavior, missing contract/regression coverage, or when a codebase needs a test strategy before major refactors, releases, security work, or production hardening.
Debugging méthodique en 4 phases (reproduce → isolate → fix → verify). Use when investigating a bug, regression, flaky test, or unexpected behavior.