audit
13009Command Claude Code
Read and follow the instructions in agents/skills/audit.md. Also read and follow agents/frontend-design/design-all.md and any referenced files in agents/frontend-design/reference/ as needed.
All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 436,404 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Command Claude Code
Read and follow the instructions in agents/skills/audit.md. Also read and follow agents/frontend-design/design-all.md and any referenced files in agents/frontend-design/reference/ as needed.
kubevirt/kubevirt-tekton-tasks
Cursor rule Cursor
Always read the AGENTS.md project guide before starting any task.
Skill Claude CodeCodex
Use whenever a change can alter rendered output — components, styles, layout, SVG, canvas, scenes, cameras, lights, materials, animation — before claiming that something looks right, is visible, or renders correctly, and when diagnosing why something is invisible, black, clipped, misframed, or mis-lit.
kylemoschetto/vibe-md-templates
Command Claude Code
Transform a basic prompt idea into a comprehensive, structured prompt using the R.G.C.O.A. framework.
Plugin Claude Code
Bundles 8 agents · 309 tokens together
AI-generated documentation backend for code repositories.
Skill Claude CodeCodex
Use when the user explicitly asks to install, uninstall, or diagnose VibeGuard. Ordinary coding, review, build failures, and generic safety requests do not activate this skill.
wuchubuzai2018/expert-skills-hub
Skill Claude CodeCodex
A design tool for creating the image materials used on WeChat red-envelope covers. It produces cover images, decorative attachments, speech-bubble attachments, and cover-story materials designed for WeChat’s submission rules.
Galileo-Agent-Labs/eval-engineer
Skill Codex
Use when a user is unsure which Eval Engineer command to run for AI agents/RAG apps, needs onboarding/status for a .galileo workspace, or asks where to start.
Plugin Claude Code
Bundles 2 skills, 4 commands, 6 hooks, 1 MCP server · 356 tokens together
Automatic Claude Code -> Obsidian second brain: zero-config session capture, hybrid search, autonomous recall, daily/lessons/preferences.
MCP server Claude CodeCodexCursor +2
MCP server "verible" as configured in ssql2014/mcp4eda. Runs /Users/qlss/Documents/mcp4eda/verible-mcp/dist/index.js with node. Needs 1 environment variable to run.
Skill Claude CodeCodex
Author Ara 3D Studio tools — generators (make geometry) and modifiers (transform geometry) — as standalone C# scripts. Use when the user says "write a modifier", "create a generator", "make an Ara 3D tool", "new Studio script", asks how modifiers/generators/Eval/parameters/EvalContext work, or wants to add a mesh…
Skill Claude Code needs its repo
Scaffold a complete feature module with types, service, hooks, schema, and constants.
jiyuanduan001-oss/LLM_Amplifier_Sizing
Skill Claude CodeCodex
Hierarchical skill stack for analog IC design within AnalogAgent. Covers OTA/op-amp sizing from netlist + specs, with expert-level equation analysis, gm/ID-based sizing, simulation-driven iteration, and root-cause diagnosis.
Skill Claude CodeCodex
Use this skill when generating commit messages, pull request descriptions, release notes, changelogs, or code reviews in a repository where git-iris is available. Activates on requests like "commit this", "write a commit message", "draft a PR", "generate release notes", "write a changelog", or "review my changes" when…
Skill Claude Code
Hide implementation details behind interfaces - work at domain level (what), not implementation level (how).
richardkmichael/mcp-tailwindplus
MCP server Claude CodeCodexCursor +2
One of 3 in .mcp.json
MCP server "tailwindplus" as configured in richardkmichael/mcp-tailwindplus. Runs locally from the mcp-tailwindplus Python package. Needs 1 environment variable to run.
Command Claude Code
Use when the user asks to log in to Syncable, authenticate, switch projects or organizations, check current context, deploy a service, check deployment status, or manage platform settings.
Command Claude Code
Dynamic learning style optimization with real-time pedagogical adaptation.
Plugin Claude Code
Bundles 17 skills · 1,307 tokens together
A 5-phase development pipeline (requirement engineering, system architecture, task generation, verified implementation, code review) with an optional QA gate (plan-qa + execute-qa) for changes that have a running surface worth driving — independent of /review, run sequentially or in parallel at the developer's…
MCP server Claude CodeCodexCursor +2
MCP server "browser-mcp" as configured in browsermcp-com/mcp. Runs locally from the browser-mcp npm package.
Plugin Claude Code
Fast and token-friendly code reading for AI coding agents. Symbol-aware MCP tools that replace cat/grep with 85% fewer tokens, sub-millisecond search, and a raw fallback that preserves cat/grep parity byte-for-byte.
Plugin Claude Code
Bundles 1 skill · 226 tokens together
Persistent project workspaces for AI agents — task tracking, artifact storage, and semantic retrieval.
Skill Claude Code
A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.
Plugin Claude Code
Bundles 16 skills, 17 commands, 11 agents, 1 hook · 2,930 tokens together
Enables Product Managers and non-engineers to produce production-quality code through structured AI collaboration with Linear integration. Complete workflow from discovery through security review.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: