feature-refinement-flow
Run a structured 20-question refinement flow before implementation for feature requests.
cy-final-verify
Enforces fresh verification evidence before any completion, fix, or passing claim, and before commits or PR creation. Use when an agent is about to report success, hand off work, or commit code. Do not use for early planning, brainstorming, or tasks that have not yet reached a concrete verification step.
cy-review-round
Performs a comprehensive code review of a PRD implementation and generates a review round directory with issue files compatible with cy-fix-reviews. Use when reviewing implemented PRD tasks, creating a manual review round without an external provider, or performing a quality audit of code changes. Do not use for fetching reviews from external providers, fixing existing review issues, executing PRD tasks, or editing source code.
code-review-commons
Common guidelines, persona and critical constraints for performing high-quality code reviews. Use this skill when performing a /code-review or /pr-code-review command.
self-verification
Verification patterns to confirm task completion before submitting. Read this before calling submit().
claude-config-advisor
审查或设计 Claude Code 项目配置。用于用户提到 `.claude`、`CLAUDE.md`、Claude 配置文件、项目级 Claude 自定义配置、配置结构是否合理、该创建哪些配置文件，或希望从零规划 Claude 配置时使用。默认先审查或诊断，再给方案；只有用户明确要求时，才进一步输出推荐结构或样例文件。
claudian-installer-updater
更新私有 skill 仓库中的 claudian-installer 资源文件。适用于用户提到“更新 Claudian 安装器”“同步 Claudian releases”“检查 claudian-installer 是否有新版本”“刷新 claudian-installer assets”时使用。会读取 claudian-installer/SKILL.md 中记录的基线版本，查询 GitHub releases；若发现新版本，则下载并替换 main.js、manifest.json、styles.css，并把新版本写回 SKILL.md。
skill-optimizer
优化和重构现有 skill。用于检查目标 skill 的触发描述、SKILL.md 工作流、确认门槛、渐进式披露，以及 references/scripts/assets 的组织方式。当用户提到“优化 skill”“检查 skill 质量”“改进某个 skill”“重构技能说明”，或直接说明要优化哪些方面时使用。默认先审查、再出计划、等待用户确认后再修改目标 skill。
eslint-plugin-custom-rule
USE THIS when asked to create a new eslint plugin rule for the eslint-plugin-cds package
playwright-testing
Write end-to-end browser tests using Playwright.
vibe-security
Audits codebases for common security vulnerabilities that AI coding assistants introduce in "vibe-coded" applications. Checks for exposed API keys, broken access control (Supabase RLS, Firebase rules), missing auth validation, client-side trust issues, insecure payment flows, and more. Use this skill whenever the user asks about security, wants a code review, mentions "vibe coding", or when you're writing or reviewing code that handles authentication, payments, database access, API keys, secrets, or user data — even if they don't explicitly mention security. Also trigger when the user says things like "is this safe?", "check my code", "audit this", "review for vulnerabilities", or "can someone hack this?".
code-review
Review code quality, patterns, and best practices
security-audit
Security review checklist for code and infrastructure
code-style
iOS platform rules, Swift conventions, dependency injection patterns, and code quality standards for ADAMANT iOS. Use when writing or reviewing code.
testing-validation
Testing and validation requirements for ADAMANT iOS. Use when writing tests, validating changes, or ensuring code quality before commits.
e2e-test-builder
Create Playwright E2E tests using Page Object Model pattern with database isolation
agent-linter
Agent ve skill dosyalarinin yapisal dogrulamasi. Frontmatter kontrol, naming convention, zorunlu bolum kontrolu, tutarlilik denetimi. Yeni agent/skill eklendiginde veya mevcut dosyalar duzenlediginde otomatik calistirilir.
deep-interview
Mathematically rigorous Socratic interview system that drives ambiguity below 20% before any code is written. One question per message, weighted ambiguity scoring, brownfield-aware, outputs a complete PRD. Replaces discovery-interview with a stricter protocol.
eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
fp-check
Systematic false positive verification for security findings. Provides structured methodology to confirm or dismiss scanner results, manual audit findings, and automated alerts. Adapted from Trail of Bits. Use when triaging security scan results or verifying audit findings.
hook-developer
Complete Claude Code hooks reference - input/output schemas, registration, testing patterns