Total 50,520 skills, Code Quality has 2287 skills
Showing 12 of 2287 skills
Ultra-lightweight channel for refactor processes - used when changes are obviously too small to justify the full scan → design → apply three-stage workflow. AI directly identifies 1-3 low-risk optimization points, confirms with the user once, modifies in-place using classic methods, and validates itself by running tests. No scan checklist, no design documentation, no multi-step HUMAN verification required. Trigger scenarios: When the user says "quick refactor", "small refactor", "simply optimize XX function", "modify directly", "skip all those steps", and the scope of changes is clearly limited to a single function/single component, with tests available for self-validation.
Organize reusable programming patterns / library usages / technical skills that answer "To do this kind of thing, the correct approach is this" into a prescriptive reference library, which can be retrieved and reused as needed during feature-design and issue-analyze phases. Three types: pattern (design patterns, programming idioms), library (usage and pitfalls of a certain library/framework), technique (specific operation skills / command recipes). Trigger scenarios: When the user says "record a trick", "this usage is worth recording", "tricks", "record library usage", or when a skill worth archiving is discovered during feature-design / issue-analyze phases and actively pushed. Refer to `codestable/reference/system-overview.md` for how to distinguish it from learning / decisions / explore.
Phase 2 of the feature workflow —— Write code according to the implementation sequence in {slug}-design.md, and submit a completion report in a unified format for user review after finishing. Prerequisites: {slug}-design.md has been approved (standard design includes test design, or fastforward design includes acceptance criteria), and {slug}-checklist.yaml exists in the same directory. Trigger scenarios: User says "The plan is confirmed, start implementation", "Write code according to the plan", "Start working". If you encounter situations not covered by the plan during implementation (new concepts, out-of-scope files, need for patch branches), proactively stop and go back to discuss the plan instead of pushing forward blindly.
Ultra-lightweight channel for refactor processes - used when changes are clearly too small to go through the full scan → design → apply three-stage workflow. AI directly identifies 1-3 low-risk optimization points, confirms with the user once, modifies in-place using classic methods, and validates itself by running tests. No scan checklist, no design documentation, no multi-step human verification required. Trigger scenarios: User says "quick refactor", "small refactor", "simply optimize XX function", "modify directly", "skip the extra steps", and the scope of changes is clearly localized to a single function / single component with test coverage for self-validation.
Reviews code for quality, security, tests, and project standards (PEP 8, type hints, VERSION, Docker, funcoes.md). Use when reviewing pull requests, code changes, or when the user asks for a code review or quality check.
Code review and audit system with specialized sub-skills covering SOLID principles, security, performance, architecture, error handling, testing, code smells, design patterns, and framework best practices. Generates severity-scored findings with copy-pasteable fix prompts. Strictly read-only — never modifies user code. Use when user says "review", "audit", "code review", "check my code", "security scan", "code smells", "SOLID check".
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
Code review using the reviewer agent
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.
Review a PR or branch diff using the knowledge graph for full structural context. Outputs a structured review with blast-radius analysis.
Use when diagnosing unexpected behavior, failed workflows, bugs, browser or Node.js runtime issues, logs, traces, or when preparing a root-cause hypothesis. 诊断异常、定位 bug、判断修复方向时使用：先建立证据表，区分运行时事实和代码推断，避免多层猜测；证据不足时添加 copy-friendly 浏览器日志或本地 Node.js JSONL 日志。
Full debugging workflow — reproduce the bug with a failing test, perform root cause analysis, then implement a minimal fix.