All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 419,045 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.
Plugin Claude Code
Bundles 5 skills, 1 hook · 567 tokens together
Searchable local index of Claude documentation. Provides the /docs command for instant access to API references, guides, and tutorials. Auto-discovery Skill reads docs automatically when you ask Claude-related questions. Docs auto-update via SessionStart hook.
Skill Claude CodeCodex
Alibaba Cloud Data Agent MCP skill (alibabacloud-data-agent-mcp-skill, data-agent MCP) for enterprise database/file analysis. Use when the user asks (in any language, including Chinese) to query/analyze DMS-managed databases, run SQL/data analysis, start quick-query (lite) or deep-analysis (pro/ultra) sessions…
MCP server Claude CodeCodexCursor +2
A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor. Runs locally from the task-master-ai npm package. Needs 9 environment variables to run.
Skill Claude CodeCodex
Claude Code adapter for ObsidianDataWeave workflows.
MCP server Claude CodeCodexCursor +2
Drive Chrome with filesystem commands (ls, cd, grep, click, type). One MCP tool, multi-agent. Runs locally from the @apireno/domshell npm package.
raphaelchristi/harness-evolver
Plugin Claude Code
Bundles 9 skills, 6 agents, 1 hook · 628 tokens together
LangSmith-native autonomous agent optimization — evolves LLM agent code using multi-agent proposers, LangSmith experiments, and git worktrees.
MCP server Claude CodeCodexCursor +2
A Model Context Protocol server for Sitecore. Runs locally from the @antonytm/mcp-sitecore-server npm package.
Plugin Claude Code
Bundles 1 skill · 214 tokens together
How to build, configure, run, and debug dbt projects on the duckrun adapter (DuckDB executes model SQL, delta-rs writes Delta tables) — local or on S3/GCS/ADLS/OneLake (Microsoft Fabric).
openscientist-io/openscientist
Skill Claude CodeCodex
Genomics and transcriptomics analysis strategies.
Skill Claude CodeCodex
Produce HTML output instead of markdown for any agent task. Four levels — Static Doc, Visual Artifact, Two-Way Interactive, Throwaway Tool. Based on Thariq Shihipar's "Unreasonable Effectiveness of HTML" framework. Triggers on "/html-it", "html-it", "html this", "render as html", "build me an html", "make an html…
Skill Claude Code needs its repo
A skill for searching OpenAlex, a free catalog of research papers, authors, institutions, journals, and research topics.
Skill Claude Code needs its repo
Architecture and coding rules for single-page applications using web components, BCE layering, lit-html templating, unidirectional Redux-style state management (reduction.js, standards-based), and standards-based client-side routing (Navigation API + URLPattern). Web standards and web platform first, minimal external…
auratech-lab/r3arxiv-react3-archive
Skill Codex
Plan, build, review, and debug React Three Fiber, Three.js, WebGL/WebGPU, shader, XR, asset-pipeline, physics, game, and creative 3D web app work using the R3ARXIV agent catalog plus absorbed R3F/Three.js skill patterns. Use when the task mentions @react-three/fiber, R3F, Drei, Three.js, WebGL, WebGPU, GLSL, shaders…
nopefallacy/vertical-video-editing-skills
Skill Claude CodeCodex
Turn an approved script, provided talking-head/voiceover media, and gathered assets into a polished, creator-grade vertical (9:16) short rendered with HyperFrames. Encodes a non-negotiable init→preview→lint→render→verify workflow; a reusable editorial house look (mixed serif/sans headlines, paper-stage and dark-grid…
zhouwei713/gpt-image-2-prompting-skill
Skill Claude CodeCodex
Write high-quality GPT-Image-2 prompts with strong structure, layout logic, and production-ready visual direction. Use this skill whenever the user asks for image prompts, wants better GPT-Image-2 prompting, wants to upgrade a weak image prompt, asks for prompt templates, wants series-style prompt systems, needs…
aithink001/Codex-Dream-Skin-Themes
Skill Codex
Install, customize, launch, hot-switch, pause, inspect, verify, package, repair, recover, update, or restore a real reversible skin for the official Codex Desktop app on macOS or Windows. Use when a user asks to apply a Codex Dream Skin, turn a local or CDN image into a Codex theme, manage saved themes or the macOS…
Plugin Claude Code
Bundles 1 skill · 273 tokens together
Source-cited Obsidian brain for the DataForSEO v3 API: 12 modules, 200+ endpoints, the task/live execution model, and per-call costs.
kangarooking/duan-yongping-skill
Skill Claude CodeCodex
A framework for deciding which companies and industries an investor understands well enough to judge their future cash flow.
Skill Claude CodeCodex
Create new OpenClaw agents OR dispatch coding agents to visible terminal sessions. Use when: (1) user asks to create/spin up/forge a new agent, (2) user asks to build/dispatch/delegate a coding task to an agent, (3) user says 'have an agent work on this', (4) user wants parallel coding agents on separate tasks.…
Skill Claude CodeCodex
Use when analyzing large files (>200 lines), more than 3 files at once, deep git/grep searches, web lookups, or adversarial reviews - delegates to the Antigravity CLI via agy-bridge MCP tools to save context.
MCP server Claude CodeCodexCursor +2
MCP server for Sonilo AI music generation API. Runs locally from the sonilo-mcp Python package. Needs 4 environment variables to run.
Command Claude Code
Produce full videos from script to render - resume projects or create new with AI voiceovers, music, and automated editing.
Plugin Claude Code
Bundles 15 skills · 1,021 tokens together
Agent skill stack for the American Economic Review, AER: Insights, and AEJ family. Covers topic selection, literature positioning with citation verification, modern causal identification (DiD / IV / RDD / SCM / Bartik), experimental pre-registration with power/MDE sizing, referee-anticipating robustness, body-section…
Skill Claude CodeCodex
Delegate the optimization of ONE design-DB slot to the rtl-subcircuit subagent via the task tool. Dispatch only delegates — analyzing the result afterwards is a separate design-db-inspect step.
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: