Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
local-setup
Interactive setup workflow for running the Magnet MCP server locally (project-specific, magnet-app directory only). Use when user says "local setup", "run locally", "test locally", "configure MCP", or "set up local development".
majiayu000/claude-skill-registry 163
-
build-pov-ray
Guidance for building POV-Ray (Persistence of Vision Raytracer) from source, particularly legacy versions like 2.2. This skill should be used when tasked with downloading, compiling, and installing POV-Ray from source archives. It covers handling legacy C code, compressed archive formats, build system navigation, and verification strategies for successful compilation.
majiayu000/claude-skill-registry 163
-
quantum-analysis
Deep code and system analysis using the Quantum Cognitive OS. Use when analyzing code, architectures, or complex systems that benefit from multi-dimensional reasoning.
majiayu000/claude-skill-registry 163
-
agent-graphql-architect
GraphQL schema architect designing efficient, scalable API graphs. Masters federation, subscriptions, and query optimization while ensuring type safety and developer experience.
majiayu000/claude-skill-registry 163
-
monitoring-apis
Build real-time API monitoring dashboards with metrics, alerts, and health checks.
Use when tracking API health and performance metrics.
Trigger with phrases like "monitor the API", "add API metrics", or "setup API monitoring".
majiayu000/claude-skill-registry 163
-
deleting-op-secrets
Deletes or archives secrets in 1Password using the op CLI. Use when the user needs to permanently remove items, archive deprecated credentials, or clean up unused secrets from 1Password vaults. Supports both permanent deletion and archiving for later recovery.
majiayu000/claude-skill-registry 163
-
oss
This skill should be used when the user asks to "create a pull request", "create PR", "open PR", "create an issue", "file an issue", "create a GitHub issue", "create a Claude Code issue", "report a bug in Claude Code", "create a Codex issue", "report a bug in Codex CLI", "create a discussion", "start a GitHub discussion", or mentions OSS contribution workflows.
majiayu000/claude-skill-registry 163
-
code-review-preferences
Use when reviewing code, PRs, or discussing code quality standards. Applies team coding standards and review methodology.
majiayu000/claude-skill-registry 163
-
add-resource
Add new learning resources (books, articles, courses, papers) to the appropriate resources.md file. Use when user mentions adding, saving, or tracking learning materials.
majiayu000/claude-skill-registry 163
-
custom-memory-heap-crash
Debugging crashes related to custom memory heap implementations, particularly release-only crashes involving static destruction order, use-after-free during program shutdown, and memory lifecycle issues between custom allocators and standard library internals. This skill should be used when debugging segfaults or memory corruption that only occur in release/optimized builds, involve custom memory allocators or heap managers, or manifest during static object destruction after main() returns.
majiayu000/claude-skill-registry 163
-
standup-formatter
Use when generating standup reports, daily updates, or team status summaries. Formats work activity into concise standup format.
majiayu000/claude-skill-registry 163
-
wp-playground
Use for WordPress Playground workflows: fast disposable WP instances in the browser or locally via @wp-playground/cli (server, run-blueprint, build-snapshot), auto-mounting plugins/themes, switching WP/PHP versions, blueprints, and debugging (Xdebug).
majiayu000/claude-skill-registry 163
-
development-standards
Development standards and best practices. Use when development standards guidance is required.
majiayu000/claude-skill-registry 163
-
gemini-claude-loop
Dual-AI engineering loop orchestrating Claude Code (planning/implementation) and Gemini (validation/review). Use when (1) complex feature development requiring validation, (2) high-quality code with security/performance concerns, (3) large-scale refactoring, (4) user requests gemini-claude loop or dual-AI review. Do NOT use for simple one-off fixes or prototypes.
majiayu000/claude-skill-registry 163
-
llm-basics
LLM architecture, tokenization, transformers, and inference optimization. Use for understanding and working with language models.
majiayu000/claude-skill-registry 163
-
implementing-code-splitting
Teaches code splitting with lazy() and Suspense in React 19 for reducing initial bundle size. Use when implementing lazy loading, route-based splitting, or optimizing performance.
majiayu000/claude-skill-registry 163
-
crdt
Loro CRDT state management with loro-mirror. Use when working on files in src/lib/crdt/.
majiayu000/claude-skill-registry 163
-
install-mkdocs-template
This skill creates a complete MkDocs Material project structure for intelligent textbooks. It sets up a Conda virtual environment named 'mkdocs', installs all dependencies, generates mkdocs.yml with all Material theme options, custom CSS for branding, the social_override plugin for custom social media cards, builds the site, and deploys to GitHub Pages. Use this skill when starting a new intelligent textbook project.
majiayu000/claude-skill-registry 163
-
synthese-multi-llm
Synthèse co-fabriquée par un conseil de 3 LLMs (Claude, Gemini, Codex). Ce skill devrait être utilisé quand l'utilisateur demande une synthèse robuste, traçable et vérifiée. Il orchestre trois modèles avec des rôles experts distincts (Extracteur, Critique, Architecte) pour produire une synthèse fidèle au texte source, avec contrôle des glissements sémantiques et trail d'audit complet.
majiayu000/claude-skill-registry 163
-
reviewing-changes
Performs comprehensive code reviews for Bitwarden iOS projects, verifying architecture compliance, style guidelines, compilation safety, test coverage, and security requirements. Use when reviewing pull requests, checking commits, analyzing code changes, verifying Bitwarden coding standards, evaluating unidirectional data flow pattern, checking services container dependency injection usage, reviewing security implementations, or assessing test coverage. Automatically invoked by CI pipeline or manually for interactive code reviews.
majiayu000/claude-skill-registry 163
-
swift-macos
Build macOS applications - AppKit, windows, menus, system integration, distribution
majiayu000/claude-skill-registry 163
-
temporal
Manage Temporal workflows: server lifecycle, worker processes, workflow execution, monitoring, and troubleshooting for Python SDK with temporal server start-dev.
majiayu000/claude-skill-registry 163
-
continuous-learning
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
majiayu000/claude-skill-registry 163
-
zustand-state
Zustand state management for React and vanilla JavaScript. Use when creating stores, using selectors, persisting state to localStorage, integrating devtools, or managing global state without Redux complexity. Triggers on zustand, create(), createStore, useStore, persist, devtools, immer middleware.
majiayu000/claude-skill-registry 163