Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
librepl
librepl - Interactive REPL utilities. Repl class creates command-line interfaces with custom commands, state persistence, and terminal formatting. Supports dependency injection for testability. Use for building CLI tools, interactive debugging interfaces, and developer utilities.
majiayu000/claude-skill-registry 163
-
claude-code-starter
Analyze a project's tech stack and generate comprehensive Claude Code configuration files (.claude/ directory with CLAUDE.md, skills, agents, rules, and commands). Use when setting up Claude Code for a new or existing repository.
majiayu000/claude-skill-registry 163
-
bmad-bmb-rework-workflow
Rework a Workflow to a V6 Compliant Version
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-stream-delete
Delete a stream by ID (soft delete). Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
workflow-tdd-plan
TDD planning pipeline with multi-mode routing (plan/verify). Session discovery →
context gathering (spawn_agent) → test coverage analysis (spawn_agent) → conditional
conflict resolution → TDD task generation (spawn_agent) → structure validation →
interactive verification. Produces IMPL_PLAN.md with Red-Green-Refactor cycles,
task JSONs, TODO_LIST.md.
majiayu000/claude-skill-registry 163
-
search-memory
Search the hierarchical memory system for relevant memories. Searches across all tiers (working, episodic, semantic) and returns ranked results. Use for context retrieval and pattern matching. Keywords: memory, search, retrieve, recall, context, similarity.
majiayu000/claude-skill-registry 163
-
n8n-security-testing
Credential exposure detection, OAuth flow validation, API key management testing, and data sanitization verification for n8n workflows. Use when validating n8n workflow security.
majiayu000/claude-skill-registry 163
-
course-launch-sequence
Write a 10-email sequence specifically for launching a course — 3 value/warmup, 2 cart-open, 2 social proof/objection handling, 2 scarcity/deadline, 1 final call. Each email gets subject line, preview text, and full body copy. Use when user needs "launch emails", "course launch sequence", "enrollment emails", or "cart open/close emails".
majiayu000/claude-skill-registry 163
-
dark-mode-design-expert
Master dark mode UI design with atmospheric theming, WCAG accessibility, and cross-platform best practices. Specializes in weather/sky/ocean-inspired color systems that adapt to time of day and environmental conditions.
majiayu000/claude-skill-registry 163
-
evaluating-new-technology
Help users evaluate emerging technologies. Use when someone is assessing new tools, making build vs buy decisions, evaluating AI vendors, or deciding on technical architecture.
majiayu000/claude-skill-registry 163
-
work
This skill should be run only when the user explicitly invokes it. Orchestrates end-to-end task implementation — understands the task, assesses complexity, implements directly or via a team of subagents for complex work, and always finishes with a code-polish pass.
majiayu000/claude-skill-registry 163
-
geo-content-optimizer
This skill should be used when the user asks to "optimize for AI", "get cited by ChatGPT", "appear in AI answers", "GEO optimization", "generative engine optimization", "Google AI Overview optimization", "get mentioned by Perplexity AI", "appear in Gemini answers", "AI does not mention my brand", "make content AI-quotable", or "increase AI citation frequency". Optimizes content to increase citation frequency across AI systems: ChatGPT (Browse), Claude, Perplexity AI, Google AI Overviews, and Google Gemini. Adds quotable statements, structured Q&A, precise statistics with sources, expert attribution, and FAQ schema. Uses CORE-EEAT GEO-First items (C02, C09, O03, R01–R05, E01) as optimization targets. Produces a GEO score, rewritten content sections, and a citation-optimization checklist. For SEO-focused writing, see seo-content-writer. For entity and brand AI presence, see entity-optimizer.
majiayu000/claude-skill-registry 163
-
code-review-checklist
Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability
majiayu000/claude-skill-registry 163
-
chibi-pet-vinyl-emoji-set-version-1
This prompt instructs an image-generation workflow to create a cohesive pack of nine polished, 3D-rendered digital stickers depicting a chibi-style vinyl capsule toy version of a specific real pet based on an uploaded reference photo, preserving the pet’s exact identifying traits while translating them into a smooth collectible-toy aesthetic. The result is a modern, consistent 2025-style “pet emoji” sticker set on a clean background, with each sticker showing a different specified facial expression and maintaining uniform lighting, materials, and toy proportions for easy cropping and pack-wide visual cohesion.
majiayu000/claude-skill-registry 163
-
tdd-workflow-cacr92-wereply-4
majiayu000/claude-skill-registry 163
-
convex-cron-jobs
Scheduled function patterns for background tasks including interval scheduling, cron expressions, job monitoring, retry strategies, and best practices for long-running tasks
majiayu000/claude-skill-registry 163
-
ui-designer
UI/UX设计师角色技能。当需要进行页面结构设计、交互方案设计、用户体验分析、UI规范输出、组件样式定义，或需要将产品需求转化为可执行的UI设计说明时使用。关键词：UI设计、UX设计、交互设计、页面布局、组件规范、Design System、用户体验、信息架构。
majiayu000/claude-skill-registry 163
-
pressbeat
Order guaranteed press articles for your brand. Standard ($500, DR30+) or Premium ($2,000, DR50+) with 90-day money-back guarantee. Use when the user wants PR coverage, backlinks, press articles, or media mentions.
majiayu000/claude-skill-registry 163
-
script-kit-scripting
Script metadata and scriptlet bundle patterns for Script Kit. Use when writing scripts, test files, or scriptlet bundles. Covers global metadata, legacy comment-based metadata, and YAML frontmatter for bundles.
majiayu000/claude-skill-registry 163
-
fair-forge-lambda
Generate AWS Lambda deployment boilerplate for Fair-Forge modules. Use when deploying Fair-Forge metrics (BestOf, Toxicity, Bias), runners (test execution against AI systems), or generators (synthetic dataset creation) to AWS Lambda. Handles local wheel installation since fair-forge is not on PyPI.
majiayu000/claude-skill-registry 163
-
csrf-protection
Implements CSRF protection using synchronizer tokens, double-submit cookies, and SameSite attributes. Use when securing web forms, protecting state-changing endpoints, or implementing defense-in-depth authentication.
majiayu000/claude-skill-registry 163
-
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or have explicit authorization to test.
majiayu000/claude-skill-registry 163
-
moai-lang-kotlin
Kotlin 2.0+ development specialist covering Ktor, coroutines, Compose Multiplatform, and Kotlin-idiomatic patterns. Use when building Kotlin server apps, Android apps, or multiplatform projects.
majiayu000/claude-skill-registry 163
-
daily-planning
majiayu000/claude-skill-registry 163