code-review
Code review assistance with linting, style checking, and best practices
发现 测试与安全 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Code review assistance with linting, style checking, and best practices
Aggregate-only summarizer for K18 QC artifacts; produces summary outputs and appends manifest rows when format is confirmed.
Diff-aware guardrail checker for Fear-of-Falling (FOF) changes; fails closed on raw data edits, Kxx intro/req_cols mismatches, and output discipline risks.
Global project rules, identity, platform constraints, PM authority, and mandatory design system for the Wakti AI app.
Turn experiment reports and development notes into summaries and reusable skills. Adapts behavior based on project domain (research, unsloth, cuda) by reading registry.json. Triggers on or requests for lessons...
Plan experiments or development tasks using past knowledge. Adapts behavior based on project domain (research, unsloth, cuda) by reading registry.json. Triggers on or questions like "What should we try next?"
Verify code is ready for production - build, tests, security, and configuration checks
Generate daily summary of git activity across all repositories
Generate folder-scoped README documentation for codebase exploration
React/Next.js performance optimization guidelines from Vercel Engineering. Use when reviewing performance, optimizing bundles, or fixing waterfalls.
Verify documentation quality - checks README.md, CLAUDE.md, and other docs for completeness and accuracy
Verify code has no TODOs, stub implementations, or dead code before merge
Configure Claude Code with symlinks to knowledge base agents and skills
Clean up after PR merge - switch to default branch, delete feature branch, pull latest
Designs modern, clean iOS screens and components for Expo React Native apps following Apple HIG with safe areas, Dynamic Type, dark mode, accessibility, Liquid Glass materials, and App Store readiness.
Invokes 300+ AI models via OpenRouter API for text completion, image generation, and model discovery. Use when delegating tasks to external models (GPT-5.2, Gemini 3, Llama, Mistral, etc.). Triggers on "use Ope...
Creates or updates README.md files following GitHub best practices with badges, visual hierarchy, and comprehensive documentation. Use when asked to "create a README", "generate documentation", "write a README...
Generate logos for GitHub repositories via OpenRouter using Gemini with programmatic transparency conversion. Works with pixel art, vector designs, and complex multi-colored styles. Use when asked to "generate...
Orchestrate multiple Codex CLI workflows using done-signal files, optional locks, and simple dependencies.
Thorough, adversarial security review of API endpoints, UI flows that call those endpoints, and any database-interacting code. Use when the user asks for a security review, permission/authorization audit, red-t...
Create or update CRM to RMX syncing integrations. Use when adding a new synced entity, mapping, EF Core model/migration, or CrmSyncingInboxService logic for CRM to RMX (and optional RMX to CRM live sync/outbox)...
Create or update a task context dump document by scanning existing content and appending only new, non-duplicative progress. Use only when the user explicitly requests a context dump, handoff note, or progress...
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Create a new React component following project best practices
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。