Debugging
Find and fix bugs, error analysis
review-changes
by Cygnusfear
Code review of current git changes, compare to related plan if exists, identify bad engineering, over-engineering, or suboptimal solutions. Use when user asks to review changes, check git diff, validate implementation quality, or assess code changes.
codex-collab
by miracloon
【WHEN】当用户命令中明确包含"codex协作"、"codex协同"、"与codex合作"等指令时启用； 【WHEN】当用户要求使用 codex MCP 工具进行代码分析、原型生成、review 等协作开发场景时启用。 【WHEN NOT】不用于单独的代码实现任务、不用于纯文档编写、不用于不涉及 codex 的常规开发流程。
Performance Benchmarker
by anorbert-cmyk
Performance Engineer focusing on real-user impact, Core Web Vitals, and backend latency benchmarks.
terminal-colors
by jasonsie
Standardized bash terminal color formatting for agent output. Use when creating or updating agent prompts that need colored terminal output for progress indicators, success/error messages, file paths, or structured logging. Provides consistent color palette and usage patterns across all agents.
update-claude-md
by carsten-j
You are updating this project's CLAUDE.md to reflect meta learnings (conventions, philosophy, gotchas) and significant recent changes to the codebase.
git-commit-helper
by cuba6112
Adherence to Conventional Commits and efficient Git history management using types, scopes, and advanced commit tools like fixup/amend. Triggers: git-commit, conventional-commits, breaking-change, fixup, git-amend, rebase.
code-review
by queso
Reviews all unmerged code in the current branch for readability, security, correctness, types, and test quality. Produces a summary of issues to fix before merging.
semver
by stuckinforloop
Semantic versioning guidelines for software releases. Use when assigning version numbers, deciding between major/minor/patch bumps, managing unstable (0.x.x) software versions, evaluating breaking changes, or reviewing changelogs and release notes for correct semver compliance.
domain-web
by lywa1998
"Use when building web services. Keywords: web server, HTTP, REST API, GraphQL, WebSocket, axum, actix, warp, rocket, tower, hyper, reqwest, middleware, router, handler, extractor, state management, authentication, authorization, JWT, session, cookie, CORS, rate limiting, web 开发, HTTP 服务, API 设计, 中间件, 路由"
test-driven-development
by hwatkins
Use when implementing any feature or bugfix, before writing implementation code
raise-bug
by bryan-zxc
Investigate, diagnose, and file a bug ticket with full context for debugging and resolution. Use this skill whenever you encounter unexpected behaviour, errors, crashes, or anything that used to work but is now broken. Triggers on any mention of bug, error, crash, regression, broken behaviour, unexpected result, or "this shouldn't happen".
triaging-bugs
by danbars
Use when a bug report is ambiguous or incomplete and you need a consistent way to assess severity, impact, reproducibility, and the next investigative step.
elixir-liveview
by hwatkins
Phoenix LiveView patterns for real-time web applications. Covers lifecycle, streams, events, PubSub, forms, and performance optimization. Use when building or debugging LiveView features.
ask-me-questions
by Pranav-Karra-3301
Interactive questioning skill to help users understand vibecoded or AI-generated codebases they've lost track of. Use when: (1) User is confused about how something works in their codebase (2) User doesn't understand code that was generated with too much AI autonomy (3) User wants to find gaps, errors, or misunderstandings in implementation (4) User says things like "I don't understand this", "how does X work", "what does this do" (5) User wants to audit their understanding of AI-generated code (6) User mentions "vibecoding", "lost track", "don't know what the agent built" Triggers: "confused", "don't understand", "how does this work", "explain", "audit my understanding", "vibecoded", "what did the agent do"
cx-status
by m19803261706
CX 工作流 — 进度查看。从本地配置读取当前活跃功能和任务状态， 展示完成进度、当前任务详情、最近修复记录。 触发词：进度、状态、做到哪了、还剩什么、怎样了、当前任务。 自动触发当用户询问工作流进度相关问题。
electron-desktop-builds
by gamerforgood469-art
Expert helper for planning, configuring and troubleshooting Electron desktop builds. Use when packaging or distributing a desktop app with Electron, when an electron-builder or electron-forge build fails, when there are errors related to Electron versions, Node versions, native modules, code signing, installer configuration (NSIS), cross-platform builds (Windows/macOS/Linux), asar packaging, preload scripts, or app icons. Covers Node.js, React, and Expo projects. Do NOT use for pure web frontend without Electron.
config
by Fibrous-Finance
View and modify fibx CLI configuration, such as setting custom RPC URLs to avoid rate limits.
goldy
by SacredTexts
"Global planning/orchestration skill. Use for: (1) Gold Standard plan creation and phased execution, (2) stack-aware decisions across TanStack/React/Neon/Drizzle/WorkOS/Radix/shadcn and other stacks, (3) session memory and deterministic resume capsules, (4) long-running /goldy-loop phase automation with checkpoints and resume chaining, (5) UI/UX module reuse from ui-ux-pro-max when design output is needed, (6) browser-based bug investigation and smoke testing via auto-detected backend (Chrome Extension for Claude Code, Playwright for Codex). Trigger for planning, roadmap, phase, architecture, implementation sequencing, or when user asks for /goldy or /goldy-loop behavior. Also auto-invokes on any coding work that lacks a pre-existing plan: fix, bug, implement, build, add, create, refactor, migrate, update, upgrade, feature, endpoint, component, test, debug, deploy, optimize, integrate, change, modify, remove, delete."
ears-requirements
by bromanko
Generate EARS (Easy Approach to Requirements Syntax) specifications from plan files, design documents, user stories, or existing codebases. Use this skill whenever the user wants to write software requirements, create specifications, extract requirements from code, convert informal requirements to structured format, prepare requirements for verification/testing, or mentions "EARS", "requirements syntax", "shall statements", "system requirements", or "specifications". Also trigger when the user asks to make requirements testable, reduce ambiguity in specs, or prepare verification criteria from a plan or codebase.
survivorship-bias
by jefrnc
Use when constructing a backtest universe, computing index/sector returns, ranking strategies, or comparing performance across time. Catches the silent inflation that comes from using today's universe (or today's ticker resolution, or today's index membership) for a historical backtest. Especially severe in small caps and FPI-heavy universes where delisting rates exceed 30% over five-year windows.
claudeception
by DanTo228
Claudeception is a continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /claudeception command to review session learnings, (2) "save this as a skill" or "extract a skill from this", (3) "what did we learn?", (4) After any task involving non-obvious debugging, workarounds, or trial-and-error discovery. Creates new Claude Code skills when valuable, reusable knowledge is identified.
skill-auditor
by tomwangowa
Audit Claude Code skills for quality, security, and best practices. Use when reviewing SKILL.md files, ensuring skill quality standards, or before sharing skills with team.
general-frontend-security
by lenneTech
Framework-agnostic frontend security guide based on OWASP Secure Coding Practices. Covers XSS prevention, CSRF protection, Content Security Policy (CSP), secure cookie configuration, client-side authentication patterns, input validation, secure storage, and security headers. Activates for security audits, vulnerability reviews, or browser security questions in any web application. NOT for backend/NestJS security (use generating-nest-servers). NOT for Nuxt-specific implementation (use developing-lt-frontend).
user-proxy
by metyatech
Use when reviewing an agent's plan, work output, or completion claim on behalf of the user. Evaluates against established rules, known error patterns, and quality standards. Do not use for direct implementation work.