All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 415,766 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.
A single-company research interface for South Korean DART filings and United States EDGAR filings. It provides one object through which users can request company records, analysis, credit, prices, quantitative data, market context, industry information, and reports.
Translates an image (or a set of image references — screenshots, mockups, Figma URLs, live websites) into two mirrored design-system artifacts: docs/design.md (YAML tokens + prose, following Google's open design.md format, for the coding agent) and docs/design.html (a self-contained, token-driven style guide rendering…
Use when creating, reviewing, or styling charts, graphs, dashboards, sparklines, or any data visualization. Applies to Recharts, ECharts, Chart.js, matplotlib, Plotly, seaborn, D3.js, and SVG. Enforces Tufte principles (data-ink ratio, direct labeling, range-frame axes) plus modern screen-first standards…
Secure access to Google Drive, Docs, Sheets, Slides, and Calendar through MCP. Runs locally from the @piotr-agier/google-drive-mcp npm package. Needs 1 environment variable to run.
★not rated 219▲
+2 todayA
tokens not measured
originalMIT
Dev coordinator - worktree lifecycle and dispatch to plan/impl/review skills. Use when user wants to create/remove worktrees, kick off dev tasks, commit worktree changes, or hand off reviewed changes.
Drive a self-hosted Guaardvark from your coding agent: local image, video, music-video and Film Crew generation, voice and music, upscaling, LoRA training, Hugging Face model onboarding, agent swarms, local knowledge, code intelligence and supervised outreach, on your own GPU.
★not rated 219▲
+13
changed 3d agoA
tokens not measured
originalMIT
Autonomous, looping, multi-altitude security vulnerability hunt for a codebase — the RAPTOR 'Karpathy auto-research' generate -> adversarially-judge -> verify loop that finds far more bugs than a single-pass scan.
Step one of vibe coding — turn scattered reading and half-formed ideas into a design you can defend. Three markdown layers (sources → ideas → output) synced on the human's command on a visual canvas; the human adjudicates, the agent runs errands.
Persistent memory for AI coding agents. Teaches agents how to use OMEGA's MCP tools for storing decisions, querying context, coordinating multi-agent workflows, and resuming tasks across sessions.
A product-requirements-document writer that gathers information through questions, researches competitors, and produces a structured PRD. A PRD is a document describing what a product should do and why.
A workflow guide for helping Chinese undergraduate students create a graduation thesis, from setting up a workspace through writing, revision, images, and Word export.
Construct a new app page from scratch using this repo's component system. Use when the user says "build a new page for X", "create a settings page", "add a dashboard for Y", "scaffold an app screen", or otherwise wants a Next.js page assembled from the project's elements/components/patterns. Produces a route under…
A skill for building and maintaining a personal knowledge-base wiki with a large language model. It can organize imported material and answer questions from the wiki.
Use when working with sunpeak, or when the user asks to "build an MCP App", "build a ChatGPT App", "add a UI to an MCP tool", "create an interactive resource for Claude Connector or ChatGPT", "build a React UI for an MCP server", or needs guidance on MCP App resources, tool-to-UI data flow, simulation files, host…
Guided workflow for authorized penetration testing, vulnerability validation, security reporting, CTF/local sandbox reverse engineering, and user-directed vulnerability research. Use when Codex is asked to run or plan a security assessment, triage a target or artifact, maintain pentest state, produce interim/final…
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Build something several people use together — a survey, a sign-up sheet, a booking form, a shared list, a form on a link — where the answers are kept in one place rather than on this machine. Use when the user asks for anything other people will fill in or read, and when they later say show it to someone, invite an…
Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent. Includes a background client for task progress, follow-up prompts, conversation recovery, cancellation, and visible failures.
★not rated 217▲
+9 3d agoA45 tokens
originalApache-2.0
Decompose complex tasks into detailed, actionable todos with rich descriptions. Each todo is specific, achievable, and small enough to execute independently.
★not rated 216 2mo agoA
tokens not measured
GPL-3.0
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: