codex-build
Orchestrator drives, Codex codes. Execute an approved plan one task at a time: your agent (Claude Code, etc.) sequences the work, briefs OpenAI Codex to write…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-23 00:13
Agents & models
24,552 results
mailchimp-automation
Automate Mailchimp email marketing including campaigns, audiences, subscribers, segments, and analytics via Rube MCP (Composio). Always search tools first for…
hermes
This skill should be used when self-hosting, installing, configuring, operating, updating, troubleshooting, or learning to use NousResearch Hermes Agent,…
ops-fires
Production incidents dashboard. Reads ECS health, Sentry errors, CI failures. Offers to dispatch fix agents for active fires.
ev
Agent-first home inventory. Use when the user talks about where things are at home (shelves, drawers, boxes, storage, pantry, car), wants to record, find,…
aim-write
Manually write a durable page to an ai-memory instance via the MCP (memory_write_page) — for decisions, rules, gotchas, schemas/contracts, or operational…
mobile-harness
Portable Android and iOS device-control harness for agents. Use when an agent needs to control or automate Android/iOS devices — tap, swipe, screenshot, app…
service-omni-permission-set-assign
Assign the required Omni permission sets to provisioned agent users. TRIGGER when users ask to assign Omni permissions to agents, grant Omni-Channel access,…
service-omni-skills-based-routing-configure
Use to make agents routable by Omni skills-based routing: ensure an Omni Skill exists, then assign it to each active agent through the classic Omni-Channel…
stitch-mcp-get-screen
Retrieves full details of a specific Stitch screen — HTML download URL, screenshot URL, dimensions. This is the final step in design retrieval before code…
engram-cultural-norms
Cultural and collaboration norms for Engram contributors and agents. Trigger: Starting substantial work, reviewing changes, or defining team conventions.
mini-context-graph
A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph. Ingest documents once — the LLM writes…
cursor-best-practices
Best practices for using Cursor—rules, commands, skills, subagents, ignore files, Agent security, workflows, and community resources. Use when setting up…
agent-council
Create autonomous AI agents with Discord bindings. Use when setting up new agents, managing agent cron jobs, or scheduling agent tasks. Covers agent creation,…
mcp
Guide to creating and managing Model Context Protocol (MCP) servers. How to add custom tools. When to use: (1) When you want to add custom tools to Claude Code (2) When integrating with external services (3) When you want to create project-specific automation tools (4)…
last-mile-delivery
When the user wants to optimize last-mile delivery operations, urban logistics, or final-mile fulfillment. Also use when the user mentions "last mile," "final…
game-changing-features
Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact…
add-skill-installer
Install Agent Skills locally. This skill is triggered when the user wants to "install skills", "add a skill", "install a skill from GitHub", or "install skill from repo".
progressive-disclosure
Split an oversized skill, CLAUDE.md, or spec into an entry file plus files that load only when they're needed.
gastown
Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work,…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
find-tool
Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databases, or infrastructure options for a…
llm-council-decision-framework
Run decisions through 5 AI advisors with peer review using the LLM Council methodology
h3-prompt-writing
MiniMax H3 storyboard/video prompt foundation: rewrite requirements into structured T2VA, I2VA, FL2VA, L2VA, Ref2VA final drafts. Includes field specifications, keyframe alignment, reference tags, two-level timeline, and state ledger. Use when writing any H3 prompt, multi-reference continuous storyboards, or precise physical handoffs.