Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
count-dataset-tokens
This skill provides guidance for counting tokens in datasets using specific tokenizers. It should be used when tasks involve tokenizing dataset content, filtering data by domain or category, and aggregating token counts. Common triggers include requests to count tokens in HuggingFace datasets, filter datasets by specific fields, or use particular tokenizers (e.g., Qwen, DeepSeek, GPT).
majiayu000/claude-skill-registry 163
-
example
这是一个示例 Skill，演示如何创建自定义 Skill。
majiayu000/claude-skill-registry 163
-
planning-with-files
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.
majiayu000/claude-skill-registry 163
-
failsafe-chassis-activation
Activate emergency failsafe chassis when primary systems fail.
majiayu000/claude-skill-registry 163
-
Story Sequencer
Plan and structure Instagram and Facebook Stories sequences for maximum engagement
majiayu000/claude-skill-registry 163
-
release-version
Guide for creating new Orient releases with proper versioning, changelogs, and Docker image tags
majiayu000/claude-skill-registry 163
-
antfu
Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.
majiayu000/claude-skill-registry 163
-
temporary-id-safe-output
Plan for adding temporary ID support to safe output jobs
majiayu000/claude-skill-registry 163
-
deploy-component
Deploys a component (frontend, backend, or landing) using SST. Use when deploying to AWS, pushing to dev or prod environments.
majiayu000/claude-skill-registry 163
-
init-local-tooling
Initialize and configure local development tooling for TypeScript, Rust, and Python projects including monorepos. Use when setting up linting (ESLint, Biome, clippy, ruff), formatting (Prettier, rustfmt, ruff), type checking (tsc, mypy), testing (Vitest, Jest, cargo test, pytest), Git hooks (lefthook for commit-msg, pre-commit, pre-push), GitHub Actions workflows, package publishing (npm, crates.io, PyPI), version management (Changesets), and automated releases. Covers both single-language projects and multi-language monorepos using Nx + pnpm workspaces.
majiayu000/claude-skill-registry 163
-
error-pattern-safety
Error Pattern Safety Guidelines for Agentic Engines
majiayu000/claude-skill-registry 163
-
python-docx
Create and manipulate Microsoft Word documents programmatically. Build reports, contracts, and documentation with full control over paragraphs, tables, headers, styles, and images.
majiayu000/claude-skill-registry 163
-
transaction-hooks
Patterns to follow for implementing transaction hooks with tracking. Use when implementing new features interacting with EVM contracts, signing transactions, permit... etc.
majiayu000/claude-skill-registry 163
-
bio-phylo-tree-io
Read, write, and convert phylogenetic tree files using Biopython Bio.Phylo. Use for parsing Newick, Nexus, PhyloXML, and NeXML tree formats, converting between formats, and handling multiple trees in a single file.
majiayu000/claude-skill-registry 163
-
standards-python
Apply Python tooling standards including uv package management, pytest testing, ruff/basedpyright code quality, one-line docstrings, and self-documenting code practices. Use this skill when working with Python backend code, managing dependencies, running tests, or ensuring code quality. Apply when installing packages, writing tests, formatting code, type checking, adding docstrings, organizing imports, or deciding whether to create new files vs. extending existing ones. Use for any Python development task requiring adherence to tooling standards and best practices.
majiayu000/claude-skill-registry 163
-
maestro
Use when you need to act as an Elite Software Architect (Maestro) to manage complex repositories. It enforces a "Why over How" philosophy, maintains a persistent project memory (Brain), and orchestrates specialized sub-skills through a Plan-Act-Verify lifecycle.
majiayu000/claude-skill-registry 163
-
linear-agent-api
Linear Agent API expertise - sessions, activities, signals, and best practices. Use when working with Linear agent integration, verifying dialogue population, or implementing two-way communication.
majiayu000/claude-skill-registry 163
-
Backend API
Design and implement RESTful API endpoints with proper HTTP methods, status codes, and consistent naming conventions. Use this skill when creating or modifying API routes, endpoints, or server-side request handlers. When working on files in src/pages/api/, files containing API route definitions, files implementing REST endpoints, files handling HTTP requests and responses, server middleware for API requests, API authentication and authorization logic, and files defining API versioning strategies. When designing URL structures for resources, implementing query parameter handling for filtering/sorting/pagination, setting up rate limiting for API endpoints, or configuring CORS and API security headers.
majiayu000/claude-skill-registry 163
-
cloud-architect
Expert cloud architect specializing in AWS/Azure/GCP multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization, and modern architectural patterns. Masters serverless, microservices, security, compliance, and disaster recovery. Use PROACTIVELY for cloud architecture, cost optimization, migration planning, or multi-cloud strategies.
majiayu000/claude-skill-registry 163
-
llm-evaluation
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
majiayu000/claude-skill-registry 163
-
User Interviews
Comprehensive guide to conducting effective user interviews for problem discovery, solution validation, and continuous learning
majiayu000/claude-skill-registry 163
-
version-control-rule
Applies to git related files, specifies to always use git for version control.
majiayu000/claude-skill-registry 163
-
configure-chatkit
This skill should be used when setting up OpenAI ChatKit in Next.js, adding domain allowlist to environment, building chat UI component, integrating with /api/chat endpoint, displaying history and tool calls visually, and integrating Better Auth session.
majiayu000/claude-skill-registry 163
-
47-evals-agent-performance
Create your agent-evals skill from official documentation before learning evaluation concepts. This skill-first approach ensures you build production-ready evaluation capabilities grounded in authoritative sources.
majiayu000/claude-skill-registry 163