Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
agent-browser
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video
majiayu000/claude-skill-registry 163
-
test-harness
Tests the AI Harness Discord bot after code changes.
majiayu000/claude-skill-registry 163
-
code-review
Structured code review covering style, readability, and security concerns with actionable feedback. Use when reviewing pull requests or merge requests to identify issues and suggest improvements.
majiayu000/claude-skill-registry 163
-
turbo-sdk
Complete Arweave Turbo ecosystem including client SDKs, core upload infrastructure, payment service backend, and CLI tools for permanent decentralized storage
majiayu000/claude-skill-registry 163
-
clerk-reference-architecture
Reference architecture patterns for Clerk authentication.
Use when designing application architecture, planning auth flows,
or implementing enterprise-grade authentication.
Trigger with phrases like "clerk architecture", "clerk design",
"clerk system design", "clerk integration patterns".
majiayu000/claude-skill-registry 163
-
V3 CLI Modernization
CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.
majiayu000/claude-skill-registry 163
-
workflow-feature-shipper
Use when you need to ship a single PR-sized feature end-to-end (plan -> implement -> verify) with artifacts. Ship core product features quickly in a Next.js codebase: turn a feature idea into an executable plan, implement in PR-sized slices, and keep artifacts under runs/ (or OpenSpec changes/ when available). Supports plan-only mode for early scoping. For prototype UI work, include a demo-ready wow moment (animation/micro-interaction) by default unless user opts out.
majiayu000/claude-skill-registry 163
-
exploiting-kerberos-delegation
majiayu000/claude-skill-registry 163
-
azure-mgmt-fabric-py
Azure Fabric Management SDK for Python. Use for managing Microsoft Fabric capacities and resources.
majiayu000/claude-skill-registry 163
-
bundle-barrel-imports
Import directly from source files instead of barrel files. Apply when using libraries like lucide-react, @mui/material, or @radix-ui/react-* to reduce bundle size and improve dev boot time.
majiayu000/claude-skill-registry 163
-
excalidraw-slides
Generate Excalidraw-style whiteboard slide prompts for YouTube videos (Hormozi aesthetic).
majiayu000/claude-skill-registry 163
-
pause-subs
Temporarily disable the skill bus. Quick toggle to stop all subscriptions from firing without removing them.
majiayu000/claude-skill-registry 163
-
onepassword-cli-coder
This skill guides integrating 1Password CLI (op) for secret management in development workflows. Use when loading secrets for infrastructure, deployments, or local development.
majiayu000/claude-skill-registry 163
-
lp-launch-qa
Pre-launch quality assurance gate for startup loop (S9B). Validates conversion flows, SEO technical readiness, performance budget, and legal compliance before a site goes live.
majiayu000/claude-skill-registry 163
-
ontology-mapper
Map materials science terms, crystal structures, and sample descriptions to ontology classes and properties. Supports any ontology registered in ontology_registry.json. Use when translating natural-language material descriptions to ontology terms, annotating simulation inputs with ontology metadata, or mapping crystal parameters (space group, Bravais lattice, lattice constants) to standardized ontology representations.
majiayu000/claude-skill-registry 163
-
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
majiayu000/claude-skill-registry 163
-
synthesize
Merge, deduplicate, rank, and format research findings from multiple channels into a coherent report. Use after research agents return their results.
majiayu000/claude-skill-registry 163
-
flowio
Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.
majiayu000/claude-skill-registry 163
-
supabase-postgres-best-practices
Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.
majiayu000/claude-skill-registry 163
-
documenting-components
Create documentation for specific components or areas of a codebase. Analyzes targeted code sections and produces structured documentation useful to both humans and AI agents. Use when (1) documenting an undocumented component or module, (2) building initial docs for a new area, (3) an agent discovers documentation gaps during codebase exploration, or (4) onboarding documentation is needed for a complex subsystem. Always targets a specific component — never documents the entire codebase at once.
majiayu000/claude-skill-registry 163
-
motherduck-query
Execute DuckDB SQL queries against MotherDuck databases. Use when running analytics, aggregations, transformations, or any SQL operation. Covers query best practices, CTEs, window functions, QUALIFY, and performance optimization.
majiayu000/claude-skill-registry 163
-
time-ripple-analyzer
This prompt instructs the AI to act as a time travel consultant who evaluates a user-defined historical era and a specific past alteration affecting a key figure or invention, then outlines multiple plausible ripple effects across history, technology, society, and the traveler’s origin timeline. The result is a structured, accessible analysis that connects causal chains, paradoxes, and ethical considerations using both scientific reasoning and speculative imagination, concluding with open-ended questions to encourage further exploration of alternate timelines.
majiayu000/claude-skill-registry 163
-
read-doc
Leverage the llmdoc documentation system to quickly understand the project architecture, code details, and key concepts without reading source code directly.
majiayu000/claude-skill-registry 163
-
Azure DevOps Automation
CI/CD pipelines, infrastructure as code, and deployment automation for Azure workloads
majiayu000/claude-skill-registry 163