All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 416,115 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.
Skill Codex
Create and edit lpm YAML configs for projects, duplicates, worktree metadata, services, actions, terminals, profiles, SSH projects, and shared config layers. Use when the user explicitly asks to configure lpm, add an lpm service/action/button/terminal, edit .lpm.yml, or manage lpm templates or global config. For…
Skill Claude CodeCodex
Search local videos by meaning, exact words, or a reference image, and annotate actions, events, interactions, and states in videos or LeRobot demonstrations. Use when the user mentions video search, finding a moment in a recording, exporting clips, video annotation, egocentric or robot demonstrations, or LeRobot…
Skill Claude CodeCodex
A skill to build and manage Home Assistant configurations. Use when using the Home Assistant Builder (hab) CLI to inspect, create, update, delete, operate, or troubleshoot Home Assistant resources; when a user mentions hab, Home Assistant CLI automation, Lovelace/dashboard edits, helpers, automations, scripts…
Skill Claude CodeCodex
Use when auditing a Gwxapkg unpacked WeChat Mini Program directory with LLM assistance; consumes .gwxapkg semantic artifacts, route maps, sensitivereport.json, and optional Burp raw requests to produce evidence-backed security findings.
olivomarco/github-copilot-token-optimization
Agent Claude Code
Token-conscious assistant. Terse output, scoped context, minimal tool calls. Use when cost or context budget matters.
Skill Codex
Use for graph-first AI coding sessions and repository analysis: session initialization, architecture maps, dependency or call-graph tracing, symbol and repository search, pull-request risk review, change-impact review, historical diffs, CompassQL, graph refreshes, GROUNDED agent-authored graph enhancements, continuous…
MCP server Claude CodeCodexCursor +2
An MCP server that provides access to Svelte 5 and SvelteKit documentation. Remote server at svelte-llm.stanislav.garden.
Cursor rule Cursor
../../CLAUDE.md.
Skill Claude CodeCodex
Generate RevealJS HTML presentations with reliable layout, professional typography, and effective visual communication. Use when creating slide decks, pitch presentations, technical talks, or any reveal.js output.
oliver-zehentleitner/keep-the-why
Cursor rule Cursor
In a project that uses Keep the Why (a .keep-the-why file at the workspace root, or a legacy keep-the-why:config block in AGENTS.md), load the keep-the-why skill first. Anywhere else, leave the skill alone.
Plugin Claude Code
Bundles 3 skills, 2 plugins · 36 tokens together
Shared Multi gateway, setup, status and reversible Claude startup integration.
davidYichengWei/agentic-engineering-framework
Skill Claude CodeCodex
A requirements-clarification workflow that defines the problem, goals, requirements, success measures, and non-goals before design begins.
MCP server Claude CodeCodexCursor +2
HyperTool MCP proxy server for routing requests between clients and multiple underlying MCP servers. Runs locally from the @toolprint/hypertool-mcp npm package.
tech-shrimp/agent-skills-examples
Skill Claude CodeCodex
A Chinese-language workflow for converting SRT subtitle files into Markdown notes. SRT is a subtitle format containing timed lines of text.
Skill Claude CodeCodex
Analyze GitHub and Discord signals to prioritize maintainer attention. Use when asked about priorities, what's hot, what needs attention, or project status.
severity1/claude-code-auto-memory
Plugin Claude Code
Bundles 2 skills, 4 commands, 1 agent, 4 hooks · 181 tokens together
Automatically maintains CLAUDE.md files as codebases evolve using hooks, agents, and skills.
Plugin Claude Code
Bundles 1 agent, 2 hooks, 1 plugin · 51 tokens together
A framework for governing UI automation agents built around Playwright, pytest, and the page object model (POM), a way to organize tests by web pages. It includes skills, rules, and self-improvement mechanisms.
MCP server Claude CodeCodexCursor +2
MCP server "rails-ai-context" as configured in crisnahine/rails-ai-context. Launched with https://github.com/crisnahine/rails-ai-context/releases/download/v5.9.1/rails-ai.
Skill Claude CodeCodex
Create or improve SOUL.md files for OpenClaw agents. Use when the user wants to design an agent personality, rewrite an existing soul, align SOUL.md with IDENTITY.md, or prepare a soul for publishing on souls.directory with optional frontmatter.
Plugin Claude Code
Bundles 1 skill · 68 tokens together
Surgical, non-interactive git hunk control for AI agents.
Cursor rule Cursor
Writing standards for AI-agent-facing documentation in skills and references.
Plugin Claude Code
Bundles 16 skills · 517 tokens together
Find application-specific vulnerabilities with whole-program static taint analysis and write rules and dependency models for future scans.
zubair-trabzada/dataforseo-claude
Skill Claude Code
Full SEO audit powered by the DataForSEO API. Orchestrates 5 specialist subagents (keywords, technical, competitors, content, backlinks) hitting DataForSEO Keywords Data, SERP, On-Page, Backlinks, and Labs endpoints in parallel, then produces a composite SEO Score (0-100) with prioritized action plan and audit JSON…
Skill Claude Code
Operating rules for the .okf/ knowledge bundle — filing new concepts, the board, the journal, the daily snapshot, closing work, source attribution, and the generated/verified attestation policy. Use before reading from or writing anything into .okf/.
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: