Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
dev-handoff
This skill should be used when the user asks to 'pause work', 'hand off session', 'save progress', 'create handoff', or when context is running low and work needs to continue in a new session.
majiayu000/claude-skill-registry 163
-
kbase-query
Skills for querying the KBase/BERDL Datalake via the MCP REST API. Use this when users want to explore KBase databases, list tables, get schemas, sample data, or run SQL queries against the KBase data lake. Triggers on mentions of KBase, BERDL, or requests to query biological/microbiome data stored in KBase.
majiayu000/claude-skill-registry 163
-
skill-updater
Updates skills during project work according to their contracts. Adds references, improves explanations, and refines examples while respecting skill boundaries. Use when discovering patterns, encountering edge cases, or finding better ways to explain skill concepts. Works with skills that have Skill Contracts defined by skill-contract-generator.
majiayu000/claude-skill-registry 163
-
vibe-to-agentic-framework
The conceptual framework behind the presentation — what "Vibe Coding to Agentic Engineering" means, why the journey is structured the way it is, and how every slide fits the narrative arc
majiayu000/claude-skill-registry 163
-
git
(ePost) Use when user says "commit", "push", "create a PR", "ship it", "done", "merge", or "open a pull request" — runs the appropriate git workflow (commit, push, or PR creation)
majiayu000/claude-skill-registry 163
-
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
majiayu000/claude-skill-registry 163
-
submittal-tracker
Track construction submittals through the review process. Manage approvals, revisions, and compliance.
majiayu000/claude-skill-registry 163
-
complete-responses
Provide complete, thorough responses Use when enforcing code quality standards. Quality category skill.
majiayu000/claude-skill-registry 163
-
sonoscli
Control Sonos speakers (discover/status/play/volume/group).
majiayu000/claude-skill-registry 163
-
medusa
Medusa rules and best practices. These rules should be used when building applications with Medusa.
majiayu000/claude-skill-registry 163
-
git-worktree
Git worktreeを使用して、複数のブランチで作業を同時並行で実行します。
majiayu000/claude-skill-registry 163
-
skill-trainer-creator
Meta-skill for Epsilon Prime evolution. Analyzes existing knowledge bases and user requirements to design and train new specialized skills or update existing ones.
majiayu000/claude-skill-registry 163
-
nextjs-best-practices
Next.js App Router principles. Server Components, data fetching, routing patterns.
majiayu000/claude-skill-registry 163
-
test-process-adapter
Generate mockk-based unit tests for Zeebe process out-adapters covering `startProcess`, `sendMessage`, and `sendSignal` methods. Use when the user asks to "write tests for a process adapter", "test the outbound Zeebe adapter", or "generate unit tests for a process adapter".
majiayu000/claude-skill-registry 163
-
microservices-patterns
Master microservices architecture patterns including service boundaries, inter-service communication, data management, and resilience patterns for building distributed systems.
majiayu000/claude-skill-registry 163
-
linkedin-engagement
LinkedIn Content-Erstellung, Engagement und Monitoring für B2B/Manufacturing. Regionale Anpassung (US/EU/Asien), Artikel mit Teasern, Bildgenerierung via Gemini, Kommentar-Monitoring.
majiayu000/claude-skill-registry 163
-
claude-advanced-tool-use
Advanced tool use patterns including tool search, programmatic calling, and production orchestration. Use when scaling to 10,000+ tools, optimizing token usage, or implementing production tool systems.
majiayu000/claude-skill-registry 163
-
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
majiayu000/claude-skill-registry 163
-
bmad-testarch-nfr
Assess NFRs like performance security and reliability. Use when the user says "lets assess NFRs" or "I want to evaluate non-functional requirements"
majiayu000/claude-skill-registry 163
-
rust-tracing
Structured logging with tracing and tracing-subscriber
majiayu000/claude-skill-registry 163
-
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration
majiayu000/claude-skill-registry 163
-
ReasoningBank with AgentDB
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
majiayu000/claude-skill-registry 163
-
api-design
Use this skill when designing APIs, choosing between REST/GraphQL/gRPC, writing OpenAPI specs, implementing pagination, versioning endpoints, or structuring request/response schemas. Triggers on API design, endpoint naming, HTTP methods, status codes, rate limiting, authentication schemes, HATEOAS, query parameters, and any task requiring API architecture decisions.
majiayu000/claude-skill-registry 163
-
brevo-automation
Automate Brevo (formerly Sendinblue) email marketing operations through Composio's Brevo toolkit via Rube MCP.
majiayu000/claude-skill-registry 163