Loading...
Loading...
Found 1,263 Skills
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.
Review code changes against STYLE_GUIDE.md before committing or creating PRs. Catches naming violations, import ordering issues, anti-pattern reintroduction, and convention drift. Run after /setup-ai or /generate-comprehensive-style-guide has created a style guide.
Detects common LLM coding agent artifacts by spawning 4 parallel subagents
Chinese Code Review Guidelines - Provide effective feedback in a way that aligns with domestic team culture while maintaining professionalism and rigor
Review a pull request — check diff, run tests, report findings
Modern PHP application development guidance for PHP 8.3+, Symfony, Composer, PHPUnit/Pest, PHPStan, Psalm, PSR standards, Doctrine, DTOs, value objects, dependency injection, migrations, middleware, and REST or GraphQL APIs. Use when Codex needs to build, refactor, test, statically analyze, or review PHP code and framework integrations.
Validate domain boundaries -- detect cross-context import violations and aggregate invariant issues
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Run a final code review on a pull request
Code style and quality rules for Megatron Bridge — ruff configuration, naming conventions, type hints, mypy rules, docstrings, copyright headers, logging, and the code review checklist.
Eight-axis judgment code review for the current diff — Correctness, Simplification, Tests, Documentation, Style, Intent, Design/API, Performance (+ Coherence on metadata changes). Five-phase pipeline scope → deterministic tool battery (npx/uvx-preferred, zero-install for the JS + Python majority) → 8 parallel LLM axis reviewers → Haiku validators on sub-80 findings (verbatim rubric, ≥80 threshold) → synthesis with no-silent-drop + Conventional Comments JSONL. Every report closes with "What I did NOT check" (security → /security-review, runtime perf, flaky detection). Opt-in flags `--verify-build`, `--mutation-test`, `--reconcile`, `--apply-safe`. Public-skill posture — zero auto-install, graceful skip on missing native tools.
Use before claiming work is complete, fixed, or tested; before committing or creating a PR — you must run verification commands and confirm the output before claiming success; always back up assertions with evidence