Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
correct-git-commits-no-exceptions
Enforce mature commit hygiene and documentation standards for long-lived projects. Trigger this skill automatically in ANY project before ANY commit creation, whether prompted by human, agent, or another skill; always do this, to ensure changesets are clean, tests pass, commit messages are terse and insightful, and all committed content is timeless rather than dependent on circumstantial context to cohere or be useful. Targets senior/staff engineer standards - no cruft, no debug statements, no transient language, no obvious comments. Maintains README accuracy and prevents documentation bloat.
majiayu000/claude-skill-registry 163
-
analyzing-network-latency
Analyze network latency and optimize request patterns for faster communication. Use when diagnosing slow network performance or optimizing API calls. Trigger with phrases like "analyze network latency", "optimize API calls", or "reduce network delays".
majiayu000/claude-skill-registry 163
-
size_guard
Enforce line budgets and rotate or split large context files.
majiayu000/claude-skill-registry 163
-
tauri-ipc-developer
Specialized agent for implementing type-safe IPC communication between React frontend and Rust backend in Tauri v2 applications. Use when adding new Tauri commands, implementing bidirectional events, debugging IPC serialization issues, or optimizing command performance.
majiayu000/claude-skill-registry 163
-
maintain-docs
Update and maintain documentation to reflect current implementation after code changes, refactoring, or new features. Remove temporal language, verify accuracy against code, and keep docs current. Use when updating docs, syncing documentation, removing outdated info, or after implementing features.
majiayu000/claude-skill-registry 163
-
sandbox-architect
Analyze codebases to generate optimal Claude Code Sandbox configurations. Use this skill when users need to set up sandbox security settings for their projects. This skill should be triggered when users ask about sandbox configuration, security settings, or when setting up Claude Code for a new project. It analyzes the codebase stack (Node.js, Python, Rust, Go, PHP, etc.), detects dependencies, and generates appropriate sandbox and permission settings through an interactive Q&A process.
majiayu000/claude-skill-registry 163
-
async-programming
Concurrent operations with asyncio and Tokio, focusing on race condition prevention, resource safety, and performance
majiayu000/claude-skill-registry 163
-
polyglot-c-py
Guidance for creating polyglot files that are valid in both Python and C. This skill applies when tasked with writing code that must be parseable and executable by both the Python interpreter and C compiler. Covers polyglot syntax techniques, testing strategies, and critical cleanup requirements.
majiayu000/claude-skill-registry 163
-
code-structure
Extract file structure (functions, classes, exports) efficiently without reading entire files, using ast-grep, go doc, ctags, or other language-specific tools to get outlines and signatures
majiayu000/claude-skill-registry 163
-
understanding-context-entropy
Decide how to codify knowledge for reuse. Use when evaluating whether a pattern, solution, or insight should be formalized—and in what form (types, code structure, CLAUDE.md, README, skill, or code comments).
majiayu000/claude-skill-registry 163
-
make-issue-spec
majiayu000/claude-skill-registry 163
-
review-resource
Review and validate a resource implementation follows all patterns. Use after creating a resource or when refactoring existing code. Triggers on "review resource", "validate resource", "check implementation", "refactor resource".
majiayu000/claude-skill-registry 163
-
token-docs
Generates design token documentation with visual swatches and code examples. Use when documenting token values, creating token reference guides, or building searchable design system documentation.
majiayu000/claude-skill-registry 163
-
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI.
majiayu000/claude-skill-registry 163
-
vkc-visa-assessment-engine
Design and implement the Viet K-Connect visa assessment engine (DB-driven ruleset JSON schema + versioning + effective dates). No hardcoded rules in code. Use for building /api/visa/assess and admin ruleset management.
majiayu000/claude-skill-registry 163
-
dev-context
Context architecture skill for aligning work. Use when starting new features, making architectural decisions, or setting up implementation work. Generates interconnected ADR/Design/Spec/Plan scaffolding that agents can navigate and humans can enrich.
majiayu000/claude-skill-registry 163
-
smoke-suite-debugging
Use this when smoke tests fail (binary/web assets, Playwright setup, server lifecycle, ports, env vars).
majiayu000/claude-skill-registry 163
-
logging-observability
Guidelines for structured logging, distributed tracing, and debugging patterns across languages. Covers logging best practices, observability, security considerations, and performance analysis.
majiayu000/claude-skill-registry 163
-
js-ts-best-practices
JavaScript and TypeScript best practices covering naming conventions, control flow, state management, TypeScript patterns (avoid any/enum, prefer type over interface), safety (input validation, assertions, error handling), performance optimization (reduce branching/looping, memoization, defer await, cache property access, storage API caching), and documentation (JSDoc, comment markers). Use when writing JS/TS functions, refactoring code for performance, reviewing code quality, fixing type errors, optimizing loops or conditionals, adding validation, or improving error messages.
majiayu000/claude-skill-registry 163
-
output-dev-workflow-function
Create workflow.ts files for Output SDK workflows. Use when defining workflow functions, orchestrating steps, or fixing workflow structure issues.
majiayu000/claude-skill-registry 163
-
hf-model-inference
Guidance for deploying HuggingFace models as inference APIs/services. This skill applies when tasks involve downloading pre-trained models from HuggingFace Hub, creating REST APIs for model inference, building Flask/FastAPI services around ML models, or setting up sentiment analysis, text classification, or other NLP inference endpoints.
majiayu000/claude-skill-registry 163
-
query-optimization-agent
Analyzes and optimizes database queries for performance and efficiency
majiayu000/claude-skill-registry 163
-
clippy-custom
Use when developing custom Clippy lints, implementing lint passes, and contributing to Clippy for Rust code standards.
majiayu000/claude-skill-registry 163
-
power-bi
Master Power BI development including DAX formulas, Power Query M, data modeling, and report optimization
majiayu000/claude-skill-registry 163