Loading...
Loading...
Found 1,079 Skills
Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.
Post-implementation reality check. Run after tests pass, before declaring done. Use when completing a feature, bug fix, refactor, or integration — or when asked to verify, sanity check, or confirm something actually works.
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas.
Review code for bugs, security issues, and best practices. Use when asked to review a PR, diff, or code snippet.
Code quality and deviation gate between /implement and /test. Reads the task document and changed files, validates coding standards, classifies deviations (minor/medium/major), and decides whether implementation is ready for testing. Runs automatically in the auto-chain between implement and test. Also invoke manually after any implementation to catch issues before wasting a test run.
Modern C++ best practices with C++17/20 features. Trigger: When writing C++ code with modern standards.
Clarity pre-deployment validation — syntax checking, deprecated keyword detection, sender check analysis, error propagation review, and test verification.
Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review, regression review, security review, or wants high-signal issues plus a prioritized fix path without editing files.
Turn plans, specs, diffs, and half-confident opinions into something that can survive contact with a real review.
Standards de codage universels, bonnes pratiques et patrons pour le développement TypeScript, JavaScript, React et Node.js.
LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".
Verify changes follow nearest-scoped AGENTS.md rules: group changed files by nested scope, auto-fix formatting, run lint/tests, and report violations. Use when the user wants scoped compliance checks for changed files.