All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 434,187 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.
Deploy applications to bex by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on bex's cloud platform.
A Chinese-language framework for explaining how power, incentives, resources, and responsibilities shape county, town, and local government in China. It also applies those ideas to choices about education, public-service careers, investment, retirement, and starting a business.
UI/UX design intelligence expert for web and mobile applications. Use when designing interfaces, selecting color palettes, typography, visual styles, building landing pages, dashboards, or reviewing code for UX issues. Covers 50+ design styles, 97 color palettes, 57 font pairings, 99 UX guidelines, 25 chart types…
Summarize the current conversation session and append results to the weekly agent-log. Use when user says "log this", "session log", "summarize this session", or asks to write results to the agent-log.
Local-first Apple Health MCP server for questions about your sleep, workouts and heart data. Runs locally from the @neiltron/apple-health-mcp npm package. Needs 3 environment variables to run.
★not rated 574 1mo agoA
tokens not measured
originalMIT
EN: Senior software design consultant. Interviews you about what you want to build, designs the complete architecture, and generates a self-contained blueprint another Claude Code instance can build from autonomously — with acceptance criteria and a verify command on every step. Works on new projects and existing…
Drive the skvm CLI on behalf of a user to profile models, AOT-compile skills, run skill-assisted tasks, run benchmarks, and manage compiled proposals. Trigger when the user asks to "profile", "aot-compile", "bench", "run a single ad-hoc task with a skill", or asks about skvm proposals. Do NOT trigger for jit-optimize…
User-invoked learning toolkit — guided reading, investigation, pattern extraction, or second opinions. Manual /maestro-learn only; NEVER auto-invoke for code exploration or analysis — route those intents to the analyze step via /maestro-next.
Sync new Granola meetings to local Knowledge folder. Use during morning planning, when user asks "what should I do today", or asks to review/sync meetings.
A skill that applies a project's DESIGN.md file as visual and brand guidance for interface work. It covers components, colors, fonts, layout, copy, motion, and visual assets.
An image-generation tool for adding illustrations to articles, creating slide presentations and infographics, or making cover images and thumbnails. It can also create prompts without generating the images.
Use the token-optimizer MCP tools to reduce context/token usage when reading, searching, or editing files, or when the context window is filling up. Trigger when reading large files, re-reading files already seen, searching a big/unknown tree, making edits to large files, or when you need to store bulky output…
Search the web and fetch/read pages via a real headless browser (CDP). Use this instead of curl when sites are JS-heavy or bot-protected. Works on Linux, macOS, and Windows.
An entire marketing department as one Claude skill. 14 modules: audits scored 0-100, an 18-tactic hook engine, copy graded before you see it, ad diagnosis, GEO, email, launches, pricing. Works in Claude, Codex and Cursor.
★not rated 571▲
+5 2mo agoA
tokens not measured
originalMIT
Drive AgentBox from Claude Code on the host: create isolated sandboxes for coding agents, run them in parallel, queue background jobs, push via the host relay.
★not rated 572▲
+6 1mo agoA
tokens not measured
originalMIT
Encrypted, fully offline memory for Claude Code: one vault on your machine, shared with Claude Desktop, Cursor, Hermes and any other MCP client. Adds 14 memory tools and the compartmentalize skill (/compartment:compartmentalize). Requires pip install compartment && compartment init first (the vault passphrase is your.
★not rated 570▲
+10
changed todayA
tokens not measured
originalApache-2.0
Create a new Harbor task for evaluating agents. Use when the user wants to scaffold, build, or design a new task, benchmark problem, or eval. Guides through instruction writing, environment setup, verifier design (pytest vs Reward Kit vs custom), and solution scripting.
★not rated 568 3d agoA✓ AI review56 tokens
copy · 88%Apache-2.0
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: