single-agent-loop
Move a multi-agent system (router, planner, subagents) toward one agent loop with skills and tools, one measured change at a time. Use when asked to audit…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,658 results
brownfield-onboarder
Intelligently onboards brownfield projects by merging existing CLAUDE.md backups into SpecWeave structure. Use when installing SpecWeave into existing projects…
context-loader
Explains how SpecWeave achieves context efficiency through Claude's native progressive disclosure and sub-agent parallelization. Use when asking about token…
role-orchestrator
Multi-agent orchestration system that coordinates PM, Architect, DevOps, QA, Tech Lead, and Security agents for complex tasks. Use when building full products,…
deliberation
When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.
agenticflow-workforce
Deploy and operate a multi-agent AgenticFlow workforce — a DAG of agents that hand off to each other (trigger → coordinator → worker agents → output). Use when…
arc-shield
Output sanitization for agent responses - prevents accidental secret leaks
fulcra-context
Access user-consented Fulcra context data including biometrics, sleep, activity, calendar, location, and the Fulcra metric catalog through the hosted MCP…
screenshot
Orchestrate reproducible product screenshot sets for documentation: audit the docs contract, plan assets and alt text, choose astroshot or agent-browser,…
trigger-realtime
Subscribe to Trigger.dev task runs in real-time from frontend and backend. Use when building progress indicators, live dashboards, streaming AI/LLM responses,…
vllm-ascend_faq_generator
Build an automated workflow for the vLLM-ascend project to process closed issues and generate a Debug FAQ. Use when users want to process closed issues from the vLLM-ascend repository, generate debug FAQ, categorize…
diagnosing-skills
Use to diagnose and fix ZCode skill configuration problems in the ZCode client. Applies when a skill is not discovered, is installed but does not trigger…
dynamic-workflows
Use when writing, debugging, or resubmitting a dynamic-workflow script for the CreateWorkflow tool: choosing subagent topology, typing subagent results,…
fleet
Fan out a fleet of independent agent-deck child sessions from inside a session and check their progress non-blockingly. Use when the user wants to "launch…
prompt-optimization
Applies prompt repetition to improve accuracy for non-reasoning LLMs
claude-code-plugin-reference
Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not use for ops; use night-market-operations.
night-market-validation-and-qa
Enforce evidence bar, coverage gates, and regression guards. Use when adding tests or claiming done. Do not use to run suites; use night-market-operations.
skill-library-mission
Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review. Use when packaging tribal knowledge. Do not use for one skill.
repo-maintainer
Audits and reorganizes messy repositories into clean, LLM-friendly structures. It uses a non-destructive "Migration Manifest" process to safely consolidate…
catalog-deslop
Catalog-then-fix slop removal on an existing prose draft. Parallel catalog subagents inventory four slop categories (theatrics, overwrought register,…
agentform
Create and debug Agentform AI agent configurations (.af files). Use when: (1) Creating new agentform projects or workflows (2) Debugging agentform syntax…
agent-skills-manager
Manage skills across AI coding agents (Claude Code, Codex, Pi, OpenCode, Hermes) with a unified symlink architecture. Use when the user wants to install a new…
skill-eval
Evaluate AI Agent Skills across safety, quality, reliability, and cost efficiency. Audit for security issues (secrets, injection, unsafe installs), test…
agentcore
Deep-dive into Amazon Bedrock AgentCore platform design, service selection, deployment, and production operations. This skill should be used when the user asks…