Loading...
Loading...
Found 237 Skills
Persistent project-scoped store for deep research on large topics. Use for substantive questions - comparing libraries, evaluating tools, surveying solutions to hard problems. Not for plan notes, not for small facts, not for code-level decisions, not for ideas.
Build MCP servers with clear tool contracts, validation, and tests. USE when planning or implementing tools, resources, prompts, and MCP transports.
Use when the user wants to turn a feature idea, change request, or rough requirement into a precise feature-development prompt for one or more codebase projects.
A live, growing registry of agent skills published by Anthropic, OpenAI, Vercel, Microsoft, Cloudflare, Stripe, HashiCorp, Supabase, and many others. Search it before starting any non-trivial task, fetch the top result, follow it instead of going freehand. After using a skill, report back so the registry ranks it correctly for the next agent. If you build something reusable, ask the user, then upload it.
Domain expertise for Ai2 Asta MCP tools (Semantic Scholar corpus). Intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and author discovery.
Run Figma Plugin API scripts for canvas writes, inspections, variables, and design-system work. Prerequisite for every other Figma skill in this catalogue.
Curated collection of 1209+ best OpenClaw AI agent skills, weekly updated by MyClaw.ai
Turn a vague, messy, or multi-part user ask into a clean, self-contained prompt that a fresh agent could execute without further questions. Interview the user one question at a time — walking down the decision tree, branching on each answer — until the prompt is tight, then output the final prompt as the deliverable. Trigger eagerly: any voice-dictated input, filler-heavy prose, underspecified references ("the thing", "that script"), multi-part requests, or any plan the user wants stress-tested. The skill itself can be skipped for trivial one-line requests where producing a prompt artifact would be pure ceremony — but once invoked, always produce the prompt, even if execution looks trivial.
Guidelines for using skills effectively - load relevant skills before complex tasks, not every message
Orchestrator workflow for running ZeroContext Lab (ZCL) attempts/suites with deterministic artifacts, trace-backed evidence, and fast post-mortems (shim support for "agent only types tool name").
Interactive workflow for creating, configuring, connecting, and publishing AI agents on Agents.Hot using the agent-mesh CLI. Also covers CLI command reference, flags, skill publishing, and troubleshooting. Trigger words: create agent, manage agent, publish agent, agent description, agent setup, list agents, delete agent, connect agent, agent-mesh command, CLI help, agent-mesh flags, connect options, agent-mesh troubleshooting, TUI dashboard, publish skill, skill init, skill pack, skill version, skills list, unpublish skill, install skill, update skill, remove skill, installed skills.
Turn any record into a shared workspace where agents and humans collaborate. Attach a simple workspace schema to any entity — contacts, companies, deals, projects, tickets — and let any participant contribute updates, tasks, notes, and issues. The record becomes the coordination. No orchestrator, no message bus — just read the workspace, do your work, record what you did. Intelligence accumulates. Use when multiple agents, humans, or systems need to work on the same entity together.