Agent skills

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

Latest Most Popular

gh-address-comments Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
majiayu000/claude-skill-registry 163
Issue Analysis with Label Inference Analyze GitHub Issues and automatically infer appropriate labels from Miyabi's 57-label system across 11 categories. Use when creating or triaging Issues, or when label inference is needed.
majiayu000/claude-skill-registry 163
innozverse-repo-structure Navigate and understand the innozverse repository structure, file organization, naming conventions, and module boundaries. Use when creating new files, organizing code, or understanding where to add features.
majiayu000/claude-skill-registry 163
code-discovery-and-impact-analysis Discover project patterns and find all code usages before making changes. Use BEFORE renaming, refactoring, moving files, changing signatures, or adding features to ensure completeness and follow project conventions. Prevents incomplete refactors and assumption-based coding.
majiayu000/claude-skill-registry 163
zig-coding Enforces Zig coding conventions from the Zig Zero to Hero guide. Use when writing, reviewing, or refactoring Zig code. Applies naming conventions, error handling patterns, resource management, and module organization best practices.
majiayu000/claude-skill-registry 163
accessibility-checker Ensure WCAG2AA accessibility compliance. Use when creating forms, adding images, building navigation, creating interactive elements, or any user-facing HTML content.
majiayu000/claude-skill-registry 163
solana-security Audit Solana programs (Anchor or native Rust) for security vulnerabilities. Use when reviewing smart contract security, finding exploits, analyzing attack vectors, performing security assessments, or when explicitly asked to audit, review security, check for bugs, or find vulnerabilities in Solana programs.
majiayu000/claude-skill-registry 163
pull-request-conventions Use when creating or merging pull requests - provides branch naming, PR title format, and description requirements for consistent PR workflows
majiayu000/claude-skill-registry 163
secure-container-build Build secure container images with Wolfi runtime, non-root users, and multi-stage builds. Templates for Python/uv, Bun, Node.js/pnpm, Golang (static/CGO), and Rust (glibc/musl) with allocator optimization
majiayu000/claude-skill-registry 163
slash-command-builder Use when creating, improving, or troubleshooting Claude Code slash commands. Expert guidance on command structure, arguments, frontmatter, tool permissions, and best practices for building effective custom commands.
majiayu000/claude-skill-registry 163
backend-instance-creator Creates a permanent backend instance for Claude Imagine. Use this skill when the user wants to set up a new persistent backend server.
majiayu000/claude-skill-registry 163
vue-patterns
majiayu000/claude-skill-registry 163
Reviewing and Shipping Validate quality with multi-agent review, auto-fix issues, generate organized commits, and create PRs with rich context. Use after completing features to ensure quality gates pass and ship confidently.
majiayu000/claude-skill-registry 163
makefile-generator Generate Makefile build automation files with targets, dependencies, and common development tasks for various project types. Triggers on "create Makefile", "generate Makefile for", "build automation", "make targets for".
majiayu000/claude-skill-registry 163
community-program-matrix Planning framework for mapping community programming across personas, channels, and cadences.
majiayu000/claude-skill-registry 163
test-data-factory-builder Creates factories and builders for generating consistent, composable test data with realistic values and relationship handling. Use for "test factories", "test data builders", "fixture factories", or "test data generation".
majiayu000/claude-skill-registry 163
midnight-network Configure and operate Midnight Network infrastructure including proof servers, indexers, and network endpoints. Use when setting up development environment, troubleshooting connections, or configuring deployments. Triggers on network, proof server, indexer, or testnet questions.
majiayu000/claude-skill-registry 163
unknown-ansvver-your-github-io 谷歌技巧
majiayu000/claude-skill-registry 163
ben-heath Talk to Ben Heath Youtuber about their expertise. Ben Heath Youtuber provides authentic advice using their mental models, core beliefs, and real-world examples.
majiayu000/claude-skill-registry 163
research-project This skill should be used when initializing a new bioinformatics research project, checking project status, updating project phase, or getting research best practices guidance. Triggered by requests like "initialize project", "check status", "update phase", or "research best practices".
majiayu000/claude-skill-registry 163
finalize-commit Once we are confident our recent changes have captured the essence of the change we want to commit, finalize the commit.
majiayu000/claude-skill-registry 163
issue-resolution GitHub 이슈 해결 워크플로우. 분석 → 구현 → 검증 자동화.
majiayu000/claude-skill-registry 163
use-gunshi-cli Use the Gunshi library to create command-line interfaces in JavaScript/TypeScript.
majiayu000/claude-skill-registry 163
zensical-development Best practices for developing zensical/Material for MkDocs static sites. Covers installation, virtual environments, project structure, responsive images, CSS, media embedding, and verification. Use for ANY Material for MkDocs project development beyond basic text editing.
majiayu000/claude-skill-registry 163