Agent skills

Skills you can use with AI coding agents, indexed from public GitHub repositories.

Latest Most Popular

character-management Maintain character consistency by cross-referencing canonical character files. Use when writing scenes with established characters, updating character information, or checking for contradictions. Prevents invented physical details, cars, homes, or backstory. Triggers include "character consistency", "check character", "update character file", "character canon", "character validation".
majiayu000/claude-skill-registry 163
activation-map Use to link segments and insights to GTM plays, owners, and measurement plans.
majiayu000/claude-skill-registry 163
clojure-hato Modern HTTP client for Clojure wrapping JDK 11+ java.net.http. Use when working with HTTP requests, REST APIs, async HTTP calls, WebSockets, or needing HTTP/2 support.
majiayu000/claude-skill-registry 163
sandbox-configurator Configure Claude Code sandbox security with file system and network isolation boundaries
majiayu000/claude-skill-registry 163
pattern-finder Find implementation examples and design patterns in the codebase. Use when user asks "how to implement X", "how does this project do X", "show me examples of X", "where is X implemented", or needs to follow existing code conventions.
majiayu000/claude-skill-registry 163
castella-a2a Connect to A2A protocol agents from Castella. Communicate with agents, display agent cards, send messages, handle responses, and stream results.
majiayu000/claude-skill-registry 163
serena-code-reading Token-efficient code reading protocol using Serena's progressive disclosure pattern (90-95% token savings). Provides mandatory workflow, tool reference, and common patterns for symbol-level code navigation.
majiayu000/claude-skill-registry 163
response-schema-generator Response Schema Generator - Auto-activating skill for API Development. Triggers on: response schema generator, response schema generator Part of the API Development skill category.
majiayu000/claude-skill-registry 163
using-lt-cli Expert for lenne.tech CLI (lt command). ALWAYS activate when user mentions "lt", "lt CLI", "lenne.tech CLI", fullstack workspace, local templates, or any lt command. Provides comprehensive reference for all lt CLI features including fullstack init, git workflows, server creation, and advanced options. Works alongside generating-nest-servers for NestJS development tasks.
majiayu000/claude-skill-registry 163
socket-io Builds real-time applications with Socket.IO including events, rooms, namespaces, and acknowledgements. Use when implementing real-time features, chat applications, live updates, or multiplayer functionality.
majiayu000/claude-skill-registry 163
prototype-planning Define what to build at what fidelity to learn what you need without over-investing. Use before starting any prototype.
majiayu000/claude-skill-registry 163
repo-explore Clone and explore external GitHub repositories to understand how libraries, frameworks, or dependencies work. Use when user provides a GitHub URL (github.com/owner/repo), asks "how does X library work", wants to look at source code for a dependency, asks about implementation details of an external package, or says "explore", "look at", or "check out" a repository. Automatically checks out the matching version tag when the repo is a dependency in the current project.
majiayu000/claude-skill-registry 163
swiftui-view-refactor Refactor and review SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view’s layout/ordering, handle view models safely (non-optional when possible), or standardize how dependencies and @Observable state are initialized and passed.
majiayu000/claude-skill-registry 163
knowledge-synthesis Synthesize knowledge from multiple sources into Zettelkasten notes for Logseq. Use when creating wiki pages, integrating academic research, or building interconnected knowledge with [[links]] and
majiayu000/claude-skill-registry 163
multi-source-investigation You must use this when investigating complex claims across diverse sources or fact-checking contradictory information.
majiayu000/claude-skill-registry 163
datasette-plugin-writer Guide for writing Datasette plugins. This skill should be used when users want to create or develop plugins for Datasette, including information about plugin hooks, the cookiecutter template, database APIs, request/response handling, and plugin configuration.
majiayu000/claude-skill-registry 163
create-haskell-bazel-target Create a target for haskell application.
majiayu000/claude-skill-registry 163
golang-senior-lead Expert Golang senior/lead developer dengan 20+ tahun pengalaman. Gunakan skill ini ketika bekerja dengan Go/Golang projects untuk membuat kode clean, maintainable, scalable, struktur folder production-grade, Docker containerization, debugging, mendeteksi celah crash/bug/race condition, code review standar senior engineer, testing strategies, performance optimization, dan library selection battle-tested. Trigger keywords include golang, go, docker, microservice, api, backend, clean code, refactor, debugging.
majiayu000/claude-skill-registry 163
templates-ryancnelson-deli-gator
majiayu000/claude-skill-registry 163
chronicle-context-retriever Search and retrieve context from past development sessions using Chronicle data. Works with MCP (fast, structured) or CLI commands (portable). Use when user asks about previous work, wants to recall past decisions, needs to understand codebase history, or wants to avoid repeating past approaches.
majiayu000/claude-skill-registry 163
workthrough Automatically document all development work and code modifications in a structured workthrough format. Use this skill after completing any development task, bug fix, feature implementation, or code refactoring to create comprehensive documentation.
majiayu000/claude-skill-registry 163
handler-source-control-gitlab GitLab source control handler centralizing Git CLI and GitLab API operations with protected branch safety
majiayu000/claude-skill-registry 163
eld-predict-impact ELD（Evidence-Loop Development）のPredict（予測）フェーズスキル。変更の影響を因果タイプで分類し、段階化戦略と停止条件を確定する。「賢く動く」よりも「壊さずに収束する」を優先。使用タイミング: (1) 実装前の影響分析、(2) 「影響予測して」「段階化計画を立てて」、 (3) Phase 2: Designで変更計画を策定する時、(4) 複雑な変更前のリスク評価
majiayu000/claude-skill-registry 163
authentication-clerk Specialized skill for implementing authentication and user management with Clerk. Use when working on sign-in/sign-up flows, user roles, or access control.
majiayu000/claude-skill-registry 163