Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
stl
Production-grade skill for the C++ Standard Template Library. Covers containers, algorithms, iterators, and utilities for efficient data manipulation.
majiayu000/claude-skill-registry 163
-
cursor-multi-repo
Manage work with multiple repositories in Cursor. Triggers on "cursor multi repo",
"cursor multiple projects", "cursor monorepo", "cursor workspace". Use when working with cursor multi repo functionality. Trigger with phrases like "cursor multi repo", "cursor repo", "cursor".
majiayu000/claude-skill-registry 163
-
kotlin-timber-logger
Add Timber logging statements to Kotlin Android files. Analyzes code logic to insert debug, info, warning, and error logs at function entry/exit, conditionals, try-catch blocks, and state changes. Only accepts Kotlin files (.kt). Use via /timber command.
majiayu000/claude-skill-registry 163
-
67-model-merging-optimization
majiayu000/claude-skill-registry 163
-
supabase-extract-jwt
Extract and decode Supabase-related JWTs from client-side code, cookies, and local storage patterns.
majiayu000/claude-skill-registry 163
-
safe-project-organizer
Comprehensive project cleanup and organization skill combining safe reorganization, root directory cleanup, and legacy tech removal. Features multi-stage validation, dry-run previews, and explicit user confirmation.
majiayu000/claude-skill-registry 163
-
off-page-seo
站外 SEO 分析和策略专家。分析外链质量和数量、竞争对手外链策略、品牌提及、社交信号等。提供 9 种外链建设策略(客座博客、断链建设、摩天大楼技术、HARO、行业目录、品牌提及、图片外链、社交信号、外链跟踪)。包含外链质量评估标准、跟踪管理系统和可执行的行动计划。
majiayu000/claude-skill-registry 163
-
quality-reflective-questions
Provides reflective questioning framework to challenge assumptions about work completeness,
catching incomplete implementations before they're marked "done". Use before claiming features
complete, before moving ADRs to completed status, during self-review, or when declaring work
finished. Triggers on "is this really done", "self-review my work", "challenge my assumptions",
"verify completeness", or proactively before marking tasks complete. Works with any type of
implementation work. Enforces critical thinking about integration, testing, and execution proof.
majiayu000/claude-skill-registry 163
-
using-browser-mode
Set up Vitest browser mode with Playwright or WebDriverIO providers, use page and userEvent APIs, test components. Use when testing browser-specific code or UI components.
majiayu000/claude-skill-registry 163
-
project-guide
claude-plugin 프로젝트 개발 가이드라인, 레퍼런스 패턴, 프로젝트 구조 조회. Use when Claude needs to (1) Look up development principles (P1-P4, DRY, KISS, YAGNI, SOLID), (2) Find reference patterns for Hooks/Agents/Commands creation, (3) Understand project structure and file locations, (4) Learn how to create Skills/Hooks/Agents/Commands, or (5) Delegate to claude-code-guide for official Claude Code documentation
majiayu000/claude-skill-registry 163
-
memory-bank-thecardgoat-tcg-engines
majiayu000/claude-skill-registry 163
-
features-documentation
Use when user-facing features change. Ensures features documentation is updated. Pauses work if documentation has drifted, triggering documentation-audit skill.
majiayu000/claude-skill-registry 163
-
api-mock-generator
Api Mock Generator - Auto-activating skill for API Development.
Triggers on: api mock generator, api mock generator
Part of the API Development skill category.
majiayu000/claude-skill-registry 163
-
ip-evaluator
梳理IP网络信息并进行多维度评估打分。适用于评估小说、剧本等IP的改编价值、分析市场潜力和创新属性
majiayu000/claude-skill-registry 163
-
channel-lister
Slack チャンネル一覧を取得する。「Slackチャンネル一覧」「チャンネルリスト」「Slackのチャンネル」「チャンネル見せて」「全チャンネル」「チャンネル確認」「どんなチャンネルがある」などで起動。公式Slack MCPの `slack_list_channels` を使用。
majiayu000/claude-skill-registry 163
-
modulization
Cadence-driven work moderation and recomposition system that discovers unfinished, fragmented, and drifting work across the codebase and collaboration surfaces, then recomposes it into coherent, schedulable units of work aligned with the roadmap and spec-driven development.
majiayu000/claude-skill-registry 163
-
nanobanana-skill
Generate or edit images using Google Gemini API via nanobanana. Use when the user asks to create, generate, edit images with nanobanana, or mentions image generation/editing tasks.
majiayu000/claude-skill-registry 163
-
wp-orchestrator
Master WordPress project orchestrator - coordinates all WordPress skills for complete site setup, audit, and optimization. Use for new project setup, site audits, or comprehensive reviews. Runs interview phases and manages todo lists.
majiayu000/claude-skill-registry 163
-
pattern-enforcement
Enforce architectural patterns with ESLint rules. Block infra imports, enforce object params, prevent server/client leaks.
majiayu000/claude-skill-registry 163
-
tmux-tui
Interact with TUI applications via tmux. Consider using tuistory skill instead for better synchronization (waitForText vs sleep). Use tmux-tui when you need visual debugging via tmux attach, or when Bun is unavailable.
majiayu000/claude-skill-registry 163
-
fetch-jira-issue
Use when user mentions a Jira issue key (e.g., PLAT-123) or needs context from Jira. Retrieves and formats issue details for PRISM agent workflows.
majiayu000/claude-skill-registry 163
-
principle-invest
评估用户故事质量的六维度框架(独立性、可协商、有价值、可估算、小粒度、可测试),系统化审查需求质量。当需要编写用户故事、评审需求文档、拆分史诗故事时使用。提供分级检查清单和低质量故事的改进建议。
majiayu000/claude-skill-registry 163
-
ray
Expert in Apache Ray distributed computing. Use when converting Python code to Ray workloads, debugging Ray applications, optimizing Ray performance, or working with Ray Core, Ray Data, Ray Train, Ray Serve, or Ray Tune. Automatically fetches relevant documentation from Ray, HuggingFace, PyTorch, and other ML/distributed frameworks based on code context.
majiayu000/claude-skill-registry 163
-
signal-scoring
Use to design composite intent scoring models with decay, weighting, and governance.
majiayu000/claude-skill-registry 163