All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 415,086 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.
Comprehensive best practices for robot perception systems covering cameras, LiDARs, depth sensors, IMUs, and multi-sensor setups. Use this skill when working with RGB image processing, depth maps, point clouds, sensor calibration (intrinsic, extrinsic, hand-eye), object detection, semantic segmentation, 3D…
Automatically generate a Seedance 2.0 video on Higgsfield using Playwright browser automation. Use when the user provides an image and wants to create an AI video from it on Higgsfield. Triggers on requests like "generate a video", "create a seedance video", "make a video on higgsfield", "auto-generate video", or any…
Use for architectural decisions about the elizaOS runtime, plugin resolution, NODEPATH setup, Electrobun boundaries, or cross-layer feature design in the Milady codebase. Invoke before large refactors or any change touching runtime/plugin/desktop seams. Pairs with milady-feature-coordinator for execution.
Guided MARM MCP setup. Invoke after running marm-memory init on the CLI to configure MARM memory across your agent. Drives transport choice, runtime choice, MCP config writing, multi-agent linking, and server start. Works on Claude, Codex, Gemini, Qwen, Cursor, VS Code, and other MCP-capable agents.
Detect and rewrite AI writing patterns in Korean, English, Chinese, and Japanese so text reads as if a human wrote it. Meaning-preservation (MPS) verified, audit-friendly. The root SKILL.md is loaded as the /patina skill.
AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives. Use when asked to review code, check a PR, analyze changes, or perform code review.
Use xurl to access AI agent conversations via agents:// URIs. Invoke when the user: gives an agents:// URI, a provider shorthand like provider/..., or a bare thread/session ID; mentions conversations, threads, or sessions from any AI coding agent; wants to search, read, summarize, compare, or continue agent threads…
A maths-teaching skill that explains problems clearly and can create HTML lessons and narrated Manim animation videos. Manim is a tool for making mathematical animations.
Create professional, high-fidelity PowerPoint presentations with premium aesthetics (bento-grids, glassmorphism, modern design systems). Outperforms standard AI slide generators by using a specialized HTML-to-PPTX rendering engine for pixel-perfect, editable results. Use whenever the user wants to create, design, or…
A collection of Claude Code skills, where Claude Code is an AI programming assistant. It includes a video-explanation workflow and a template for formatting WeChat Official Accounts posts.
★not rated 356▲
+2
changed 10d agoA
tokens not measured
Use this agent when you need to design and implement a backend API for a frontend application. This includes selecting the appropriate backend framework, designing RESTful or GraphQL endpoints, setting up database schemas, implementing authentication/authorization, and creating the server infrastructure. The agent…
Translate subtitle files (SRT, ASS) and video/media with embedded subtitles into any target language with high linguistic quality, sliding context window, timestamp alignment, and formatting preservation. Use when the user asks to translate a subtitle file (.srt, .ass) or video subtitles.
A tool for turning information about a romantic interest into an AI skill that can remember their personality and relationship history. It can work with chat records, photos, and social media content, and supports English and Chinese.
Use when designing the variables namespace for an EpicStaff flow, translating business requirements into node graph contracts, or deciding which node type fits a responsibility.
Geospatial intelligence with Mapbox APIs like geocoding, POI search, directions, isochrones, etc. Runs locally from the @mapbox/mcp-server npm package. Needs 1 environment variable to run.
★not rated 354▲
+1 11d agoA
tokens not measured
originalMIT
Architecture Studio — governed AEC skills and portable studio workflows for Codex and Claude Code: initialize a studio workspace, create registered projects, maintain linked project records, or route work across NYC due diligence, site planning, zoning, programming, specifications, sustainability, FF&E, materials…
Serves an LLM on a supported AMD EPYC server CPU using vLLM with zentorch, in Docker, Podman, or conda. Use for "vLLM on CPU", "zentorch serving", or an EPYC CPU endpoint, including on a host that also has AMD Instinct GPUs. Detects the EPYC generation, validates the runtime, checks model support and RAM fit, sizes…
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: