Total 43,574 skills, Code Quality has 2034 skills
Showing 12 of 2034 skills
Profile-driven performance optimization with behavior proofs. Use when: optimize, slow, bottleneck, hotspot, profile, p95, latency, throughput, or algorithmic improvements.
Multi-agent QA review team for code changes. This skill should be used when the user asks to "review my code", "run QA", "qa-team", "review this branch", "code review", "check my changes", or wants a comprehensive multi-perspective code review of the current branch's changes. Spawns parallel specialist agents (security, database, reliability, compatibility, data integrity, performance, frontend, copy) that independently review the diff and produce a converged report. Also includes two generalist reviewers for convergence validation.
OpenAI Codex Rust coding patterns distilled from the codex-rs workspace. Use this skill whenever writing, reviewing, or refactoring Rust code — especially for async agents, CLI tools, sandboxing, Ratatui TUIs, JSON-RPC protocols, tokio-based services, or any codebase that needs defensive panic discipline. Trigger even when the user does not explicitly mention Codex, because the patterns generalize to any production Rust workspace. Covers async cancellation, error enum design, process sandboxing, Cargo workspace architecture, wiremock-based fakes, insta snapshot testing, OpenTelemetry tracing, and Ratatui rendering.
Grill the diff. Specialists evaluate every finding internally — only high-value findings reach the user for discussion until reaching shared understanding.
Chinese Code Review Guidelines - Provide effective feedback in a way that aligns with domestic team culture while maintaining professionalism and rigor
Follow this sub-process when fixing bugs—turn the verbal description of "discovered a problem" into a closed loop of verification and repair, leaving three documents in the middle: issue report, root cause analysis, and repair record. This process adds a buffer between "seeing the problem" and "starting to modify code", avoiding several common pitfalls: the problem description in your mind disappears after modification, fixing only the surface without analyzing the root cause, uncontrollable expansion of repair scope that cannot be traced, and not knowing if the fix is correct without verification after modification. This skill only acts as a router, deciding which of report / analyze / fix to proceed with based on existing outputs. For simple problems that can be identified at a glance, a fast track will be taken, skipping the two middle steps and only keeping the fix-note.
Phase 2 of the issue process — Read the issue report + read the code, identify the true root cause and assess the repair risk, and finally provide the user with 2-3 repair plan options for them to decide. This phase is **not about starting to modify code** — after analysis, show the conclusion to the user first, and only proceed to Phase 3 after the user confirms the plan. The prerequisite dependency easysdd-issue-report has been completed. Trigger scenarios: The user says "analyze this bug", "find the root cause", "locate the issue", and the {slug}-report.md already exists in the issue directory.
Follow this sub-process for code optimization — handle tasks where 'behavior remains unchanged but structure changes' (structure / performance / readability). Shift single-module internal optimization from 'AI random refactoring' to 'first scan to generate a checklist, confirm each item with the user, execute step by step according to the method library, and obtain manual approval for each step'. Trigger scenarios: When the user mentions phrases like 'optimize / refactor / rewrite / split / poor performance / too long code' without any accompanying behavior changes. Do not handle new requirements (route to feature), bugs (route to issue), or cross-module architecture restructuring (route to architecture + decisions).
Fix the findings recorded in a crate issue file one at a time, with failing test first, minimal fix second, full crate verification third, and issue-file status updates after each successful fix. Use for Rust crate issue lists that already exist and need disciplined sequential repair.
Fix knip "Unused exports" violations. Handles all violation categories: test-only exports (extract to new file), dead barrel re-exports (remove from index.ts), and internally-only-used exports (un-export). Use when `npm run knip` reports unused exports.
Comprehensive review of local uncommitted changes using specialized agents with code improvement suggestions
Code review — both giving and receiving feedback. Verifying observed behavior over performative agreement. Use when reviewing a PR, requesting review on completed work, or processing review feedback you received.