SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags

ros-skill
Control and monitor ROS/ROS2 robots over rosbridge (WebSocket) with CLI commands for topics, services, nodes, params, and actions.

kanwas
CLI helpers for synchronizing a Kanwas workspace with local files: pull, push, and bulk-import markdown notes into a repo-friendly structure.

claude-ai-music-skills
Interactive setup and management for the bitwize-music plugin configuration (creates, edits, shows, validates, or resets ~/.bitwize-music/config.yaml).

medgeclaw
Detects and configures CJK fonts for matplotlib/plotly so Chinese/Japanese/Korean text renders correctly in visualizations.

ai-factory
Set up agent project context: analyze tech stack, install or generate skills, and configure MCP servers with mandatory security scanning for external skills.

gobby
Create a concise Discovery Brief that frames a task, lists constraints, states testable hypotheses, and surfaces open questions for downstream research and plan

biblioteca
Operational diagnostics for WhatsApp: inspect message delivery, webhook deliveries/retries, triage API errors, and run phone-number health checks.

claude-skill-registry
Guidance for designing, running, and analyzing test suites for agents: test isolation, execution patterns, and coverage-based enforcement.

scrollclaw
Persona research and UGC script pipeline: mine real customer language, map to format blueprints, and produce A-roll/B-roll tagged scripts ready for approval.

narrator-ai-cli-skill
CLI client to create AI-narrated videos: writing, clip generation, composing and visual templates with 90+ narration styles, 146 BGM tracks and 63 dubbing voice

first-tree
Operations skill for managing Context Tree syncs: detect drift, open proposed fixes, and route reviewer workflows via gardener and breeze.

bilitickerskill
Orchestrates the local biliTickerBuy project to search for Bilibili member-sale events and prepare or execute automated ticket purchase workflows (search, login

vmprint
Practical guide and authoritative reference for authoring VMPrint JSON AST 1.1 documents — layouts, stories, tables, floats, scripting, and pagination rules.

api-relay-audit
An 11-step automated security audit for AI API relay/proxy services — detects prompt injection, context truncation, tool-call substitution, stream integrity iss

avenir-web
Run and improve Avenir-Web autonomous web tasks: choose run mode, validate and refine instructions, execute single or batch runs, and analyze outputs to propose

a-gusman-claude
A design system and catalog of 24 reusable UI modules and product patterns (components, modules, product scaffolds) to consult before specifying or building fea

codex-image
Generate images via the Codex CLI using OAuth (no API key). Handles argument parsing, save paths, and error messages for gpt-image-2 generation.

stellar-dev-skill
Guidance and patterns for integrating zero-knowledge proofs and privacy-preserving primitives into Stellar/Soroban smart contracts.

asynkron-skills
Resilient .NET test runner that detects hangs, isolates flaky/crashing tests, tracks history, and helps identify culprits in unstable test suites.

babysitter
Select and balance project portfolios using constraint-based mathematical optimization to maximize value under budget, resource, and strategic constraints.

skills
Human-guided, defensive exploratory data analysis for scientific datasets: capture context first, propose one step, run disposable scripts, and keep an append-o

proma
Execute a written implementation plan in safe, review-checked batches: load, review, run tasks in small batches with verification and checkpoints for feedback.

marvin-template
Begin a MARVIN session with context loading, state review, and a concise daily briefing listing top priorities and alerts.

skills
Fetch real-time X/Twitter attention signals for Base-chain tokens: leaderboards, spikes, and token deep-dives (pay-per-call via x402).

悟道真英雄 (wudao-hero)
Create a personalized A-share trading persona that grows with your trade history: analyze screenshots, ingest chat posts, track watchlists and regrets, and enfo

litellm-skills
Guides adding and testing a new model on a LiteLLM proxy: pick provider, supply credentials, POST to /model/new and verify routing with a test call.

zylos-core
Schedule and dispatch one-time, recurring and interval tasks to an agent runtime via the C4 comm-bridge for autonomous execution.

zylos-core
Channel skill that connects a CLI REPL to a Claude-like backend via a Unix socket, routing user input to the agent and delivering responses back to the REPL.

grapefruit
CLI skill to control the IGF (Grapefruit) dynamic instrumentation server for mobile security testing: enumerate Frida devices, inspect apps, run hooks, access f

bitterbot-desktop
Agent-oriented social network client: post dream insights, read feeds, comment, and engage with agent communities (Moltbook API integration).