AI Skills
Installable SKILL.md packages that extend AI coding agents with reliable workflows and domain-specific judgment — ranked by installs, sourced from skills.sh.

testability-obstacle
Add minimal production seams to test C#/.NET code with ambient dependencies like DateTime, File I/O, and Random.

expo-react-native-performance
42 performance optimization rules for Expo React Native apps, organized by impact.

word
|-

postgresql-best-practices
PostgreSQL schema design, query optimization, and database administration best practices

iso-13485-certification
Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work instructions, (4) preparing Medical Device Files, (5) understanding ISO 13485 requirements, or (6) identifying missing documentation for medical device certification. Also use when users mention medical device regulations, QMS certification, FDA QMSR, EU MDR, or need help with quality system documentation.

r3f-loaders
Load and reuse 3D assets in React Three Fiber with caching, cloning, and error handling.

developer-keyword-research
Mine actual developer search demand from logs and tickets to build a ranked keyword map for technical content.

requesting-code-review
完成任务、实现重要功能或合并前使用,用于验证工作成果是否符合要求

openspec-implementation
Systematically implement approved specifications by executing tasks sequentially with testing and validation.

pi-history-ingest
>

ccf-paper-to-exemplar
Distill academic papers into reusable writing exemplar cards with source attribution preserved.

law-of-common-region
Apply visual boundaries and containers to group elements clearly, regardless of spacing.

compose-state-holder-ui-split
Use when a Jetpack Compose screen-level composable takes a ViewModel/component/controller, collects state or effects, handles navigation/snackbars, or wires callbacks while also rendering layout.

llm-security
Security guidelines for LLM applications based on OWASP Top 10 for LLM 2025.

game-assets
Create pixel art sprites, animated characters, and visual entities for browser games without external image files.

handoff
Write compact session handoff artifacts with exact evidence paths for context handoff without choosing continuation.

ccf-submission-checker
Verify CCF paper submissions against venue rules, templates, page limits, anonymity, and artifact readiness.

conference-cfp-submission
Turn talk ideas into winning conference proposals, or plan a CFP submission calendar across multiple events.

content-creator
Create SEO-optimized marketing content with consistent brand voice. Includes brand voice analyzer, SEO optimizer, content frameworks, and social media templates. Use when writing blog posts, creating social media content, analyzing brand voice, optimizing SEO, planning content calendars, or when user mentions content creation, brand voice, SEO optimization, social media marketing, or content strategy.

agents-md
Create or update repository AGENTS.md for scoped, evidence-backed agent guidance.

sf-debug
Analyze Salesforce debug logs to diagnose governor limits, stack traces, and performance issues with structured root-cause reporting.

implement
Execute changes and repairs with per-lane evidence and factual checks.

version-bump
Automated semantic versioning and release workflow for Claude Code plugins with multi-manifest sync and GitHub integration.

electron-development
Electron development guidelines for building cross-platform desktop applications with JavaScript/TypeScript

developer-tutorial
Write or audit tutorials that teach developers a skill through hands-on building, with checkpoints and fading guidance.

ccf-pipeline-orchestrator
Coordinate CCF research stages, gates, and project workflow with explicit task planning and artifact tracking.

technical-specification
>

paperclip-ai-orchestration
Open-source platform for orchestrating autonomous AI-agent companies with org charts, budgets, and governance.

using-git-worktrees
当需要开始与当前工作区隔离的功能开发,或在执行实现计划之前使用——通过原生工具或 git worktree 回退机制确保隔离工作区存在

continual-learning
Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to a subagent.