- Skills
- 146
- 仓库
- 2
- 职业覆盖
- 0
- 场景覆盖
- 0
- Stars
- ★ 0
Aydina 的 Skills 146
token-optimization
Use zero-install context minimization first, with optional local optimization tooling when available.
testing-strategy
Testing philosophy and strategy. Use this when deciding what to test, naming tests, or identifying corner cases.
testing-patterns
Test implementation patterns. Use this when writing tests — table-driven tests, mocking, fixtures, assertions, and parallel execution.
testing-integration
Integration and E2E testing design. Use this when writing integration tests, E2E tests, or deciding what belongs in each test layer.
test-review
Test review for missing coverage, weak assertions, flaky tests, isolation, fixtures, and regression risk.
test-impact-selection
Select the minimal useful tests to run based on changed files, impacted components, and repository conventions.
severity-classification
Classify review findings into blocking, non-blocking, or note with consistent merge-risk rules.
security-review
Security review for auth, authorization, secrets, injection, crypto, dependency misuse, and unsafe data exposure.
risk-classification
Classify PR risk and select which specialist reviewers should run based on changed files, diff shape, and risk hints.
resilience-review
Resilience review for timeouts, retries, idempotency, circuit breakers, fallbacks, and failure isolation.
regression-risk-review
Regression-risk review for behavior changes likely to break existing users, flows, integrations, or production data.
prompt-gate
Optimizes user prompts before implementation. Use when the user asks to improve, prepare, validate, reduce ambiguity, minimize token usage, or avoid iteration loops before sending a task to an AI coding agent.
pr-diff-analysis
Analyze pull request diffs efficiently and route files to the right review specialists without loading the whole repository.
pr-context-collection
Collect minimal PR context needed by orchestrators and specialists without reading full files or the whole repo.
performance-review
Performance review for expensive loops, N+1 calls, memory pressure, latency, caching, and unnecessary IO.
observability-review
Observability review for logs, metrics, tracing, correlation IDs, error context, dashboards, and alertability.
minimal-fix-review
Review whether a patch fixes only the intended issue with minimal blast radius and no unrelated changes.
logic-review
Logic review for correctness, edge cases, state transitions, error handling, concurrency, and business invariants.