All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 433,983 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.
Create, edit, import, analyze, repair, validate, inspect, and render Archinsight Insight architecture-as-code models and custom views. Use when working with .ai models or .aiq queries, migrating architecture from another DSL or diagram, C4-style architecture models, system/container/component/code diagrams, deployment…
Drive Blender with the official Blender MCP for everything inside the app, and computer-use only for what has no API. Never read Blender through the accessibility tree.
A browser-control skill that uses Playwright, a tool for driving a real web browser. It supports opening pages, reading their accessible structure, filling forms, clicking controls, handling tabs, and taking screenshots.
OpenDesk by VitalOps — open-source computer-use MCP server that lets AI agents see and control macOS, Windows and Linux desktops, locally or across paired machines.
★not rated 92▲
+2 todayA
tokens not measured
originalMIT
A set of procedures and templates for managing long coding tasks. It covers restating goals, breaking work into parts, checking progress, recording state between sessions, and handing work to another session or agent.
Guide and build custom YAML SQL tools for the IBM i MCP Server (@ibm/ibmi-mcp-server). Covers designing the tool, discovering the right Db2 for i SQL services, prototyping and testing the SQL live on IBM i through IBM i Developer mode, writing the YAML tool file, validating it against the tool JSON schema with the…
Skills for tracing, evaluating, and improving AI agents with MLflow. Supports the full agent improvement loop: instrument → trace → evaluate → iterate → validate.
A human-first method for handing ongoing work from one chat, AI model, device, or language to another. It creates or reads a small handoff document, or a package with files when the receiver needs them.
Give your AI agent a professional health checkup (AgentVitals). Use when the user asks the agent to run a checkup / test itself / benchmark itself ("run a checkup", "check your vitals", "test yourself", "how stable are you", "/checkup"), or an advanced personality checkup (backbone, proactivity, creativity). 给 AI…
Post-implementation auditor for Trellis. Reviews concrete diffs against task artifacts, specs, migration/release rules, generated templates, and docs parity. Demands file:line citations, concrete fixes, and validation results. Does not commit or push.
Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.
Migrate a Tableau, Looker, or Power BI dashboard to a Hex app that matches it exactly — same queries, results, filters, colors, layout, and tooltips. Use when the user pastes a Tableau dashboard/view link, a Looker dashboard link, or a Power BI report link and asks to migrate, replicate, copy, or rebuild it in Hex, or…
Use when an agent needs isolated, forkable compute, running untrusted or model-written code safely, or exploring several attempts in parallel (best-of-N) and keeping the winner. Mitos boots Firecracker microVMs and forks a running VM via copy-on-write snapshots, so a fan-out is cheap and each attempt is…
MCP server "codealive-mcp" as configured in CodeAlive-AI/codealive-mcp. Runs in Docker (ghcr.io/codealive-ai/codealive-mcp:3.0.3). Needs 1 environment variable to run.
★not rated 91▲
+1 yesterdayA
tokens not measured
originalMIT
Use Helixir persistent graph memory through its MCP tools. Invoke at the start of non-trivial work, after context compaction, when recalling past decisions, when storing durable outcomes, when tracing why facts are connected, and when using FastThink or Helixir RBAC.
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: