agent-coordination
Coordinate multiple specialized Skills and Task Agents through parallel, sequential, swarm, hybrid, or iterative execution strategies. Use when orchestrating…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-27 00:15
Agents & models
24,910 results
rename-swarm
Parallel bulk rename across many files using a swarm of haiku agents. Use when mechanically renaming identifiers, parameters, or keys across 5+ files.
envelope-team
Design and generate .envelope.json AI agent team definitions — the open standard for multi-agent teams with hierarchy, access policies, human-in-the-loop…
swarm-expert
Multi-agent coordination expert for agent-swarm MCP. Use when the user asks about swarm coordination, delegating tasks to agents, checking swarm status, agent…
dart-genkit
Use when building AI workflows, tool calling agents, structured outputs, or LLM pipelines using the Genkit Dart SDK.
skill-create
[Skill Management] Use when you need to create new Claude Code skills or scan/fix invalid skill headers.
connection-doctor
Diagnose and health-check the Connections and credentials a Duvo Agent relies on. Use when the user asks whether a Connection is set up or available, why an…
remember-learnings
Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with…
learn-agent-skills
A focused interactive tutor for the Agent Skills Engineering track in AI Engineering from Scratch. Start or continue this track when learners want to create, discover, invoke, secure, evaluate, package, or migrate Agent Skills. Teach one lesson per invocation and record evidence in...
learn-mcp
A focused interactive tutor for the Model Context Protocol (MCP) track in AI Engineering from Scratch. The learner wants to build, secure, debug, validate, or operate MCP clients, servers, transports, gateways, registries, or conformance...
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
skillify
Capture this session's repeatable process into a reusable skill. Call at end of a process you want to automate.
skill-builder
Create, improve, or audit reusable agent skills from real work and user preferences: skill instructions, descriptions, resources, scripts, packaging,…
skills-creator
Create and manage Agent Skills following the agentskills.io specification. Use when users want to create, validate, or modify skills for AI agents.
agent-aware-cli
Guide for designing and implementing command-line interfaces (CLIs) that are equally usable by human developers and automated coding agents. Use when the user…
honey-hive
Decide when to delegate to Honey's read-only subagents (hive-scout, hive-reviewer) instead of working inline, so the expensive tokens — large file reads and…
agent-teams-guide
Guide for orchestrating and controlling Claude Code agent teams. Use when working with or managing multi-agent team coordination in Claude Code, including: (1)…
fable-anti-churn
Prevent duplicate agent actions, infinite retry loops, and unverified churn across all lifecycles. Reuses matching accepted evidence, enforces typed…
qgis-agents-map-generator
Use when generating complete maps from data: loading, styling, composing layouts, and exporting. Prevents poor cartographic choices and empty map exports.…
tavily
Tavily AI search API for LLM applications: web search, content extraction, site crawling, mapping, and research. Use when integrating real-time web search into…
LangGraph Fundamentals
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph creation, node functions, edges, state schemas with reducers (Annotated), and the Command…
moltbook
The social network for AI agents. Post, comment, upvote, and create communities.
claude-api
This skill provides comprehensive knowledge for working with the Anthropic Messages API (Claude API). It should be used when integrating Claude models into…
implement-spec-in-workflow
Implement a whole spec as a stack of PRs — one per ticket, registered as a native GitHub stack — driven by a dynamic workflow of subagents instead of by you.