roast
Generate an Agent Workflow Roast report from recent local session history and optional memory context. Use when the user invokes @roast, /roast, or asks for…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-08 00:04
Agents & models
25,881 results
oci generative ai services
Expert in Oracle Cloud Infrastructure Generative AI services including foundation models, embeddings, chat, text generation, and fine-tuning. Complete CLI and…
create-anyone
Distill anyone into a runnable OpenPersona skill pack — real or fictional, personal or public, living or historical. Collects chat logs, documents, and public…
microduck-skill
Train, export, publish, and deploy Microduck reinforcement-learning policies (PPO on MuJoCo Warp via mjlab) onto a real robot via robotctl. Use when the user…
create-anyone
Distill anyone into a runnable OpenPersona skill pack — real or fictional, personal or public, living or historical. Collects chat logs, documents, and public…
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
mission-control
Mission Control (Claw Control) task and feed management for AI agents. Use when creating tasks, posting to agent feed, managing Kanban boards, or coordinating…
ralph-loop
Guide OpenClaw agents to execute Ralph Wiggum loops using exec and process tools. Agent orchestrates coding agents (Codex, Claude Code, OpenCode, Goose) with…
chrome-cdp-live-browser
Connect AI agents to your live Chrome session via CDP — interact with open tabs, logged-in accounts, and real page state without launching a new browser.
lightpanda
Expert skill for Lightpanda — the headless browser built in Zig for AI agents and automation. 9x less memory, 11x faster than Chrome. Installation, CLI, CDP…
desktop-agent-activity
Use when checking whether Orca/Claude Code is still working. Process+files first.
kimi-computer-use
Install, register, diagnose, or upgrade Kimi Computer Use (kimi-cu) MCP for Cursor CLI, Grok, WorkBuddy, Claude Code, Codex, or Hermes; fix kimi-cu tool-call…
opendia-harness
Install, configure, and troubleshoot OpenDia for Grok Build (and other MCP harnesses). Use when setting up the plugin, config.toml MCP entry, ports, extension…
ag2-architect
An agent that helps design multi-agent systems using the AG2 framework
ag2-imports
Correct import paths and module structure for the AG2 framework
integrate-web-search
Register and use web search tools with AG2 agents to search the web and extract page content
open-video
Generate, edit, or direct videos via open-source models (MiniMax H3 baseline; Wan2.2 / LTX future). Use when the user wants to turn a concept, script, or…
banthis
Use when user asks to ban, stop, or remember not to repeat an agent behavior ('stop doing X', 'you keep doing X', 'ban this'). Immediately capture it as a…
skill-curator
Use when user asks to create, improve, or review production-grade SKILL.md files for Claude Code, Cursor, Codex, OpenCode, Kiro, and other agent tools. Focuses…
recommend
Analyze accumulated skillers knowledge and suggest skills, hooks, and agents. Use when compacting is done and patterns need classification. Checks existing…
system-prompt-curator
Use when user asks to create, improve, or debug production-grade system prompts for autonomous coding agents and multi-agent orchestration. Not for user-facing…
agent-release-gate
Run the agent release gate — a portable, wire-level QA harness for the agent runtime. Drives the same product endpoint the playground drives and asserts on the…
sync-model-catalog
Regenerate and refresh the curated agent model catalog (the label/description/pricing/ratings behind the agent model picker). Use when the pinned…