migrate-skill-to-agent
Use only when migrating an existing skill directory from `.claude/skills/{name}` to `.agents/skills/{name}` and creating `.claude/skills/{name}` and…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,639 results
claude-advisor
Consult Claude for a second opinion or send a result, finding, update, or work handoff to a specific existing Claude Code conversation from Codex or another…
docxmakebetter
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude…
vercel-workflow
Build durable workflows with Vercel Workflow DevKit using "use workflow" and "use step" directives. Use for long-running tasks, background jobs, AI agents,…
67
Runs the task through six agents in parallel, each locked to a different strategy, then a seventh judge ranks the six attempts and synthesizes a final answer…
promptmaster
Rewrite the user's raw request into an optimized prompt before answering it, audit it against the 35 credit-waste patterns in waste-patterns.json, and enforce…
agent-dev-workflow
Set up an agent-friendly local dev workflow — a bin/ task-runner (inspired by GitHub's scripts-to-rule-them-all) over a shared Postgres container that gives…
handover
Fully delegates a task to a subagent for complete execution. Main agent writes a handoff doc via /handoff, subagent executes the ENTIRE task, subagent writes…
handover-loop
Delegate a code-changing task to a fresh subagent, then adversarially review the result on the main agent and loop — re-delegating to a new fresh subagent each…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
exploring-claude-sessions
Finds and explores Claude Code session history stored locally as JSONL transcripts. Use when the user asks to find, search, read, export, or resume a past…
agent-creation
Standards-compliant agent definitions with templates. Trigger: When creating agent definitions, setting up project agents, or documenting workflows.
stb-reviewer
Stacking the Bricks reviewer — Amy Hoy & Alex Hillman persona for reviewing business decisions, pitches, emails, copy, and product strategy. Use when reviewing…
release
Handles version bumps and npm releases for the swarm-tools monorepo (opencode-swarm-plugin, claude-code-swarm-plugin, swarm-mail, swarm-queue). Use when:…
celebrity_naval
Naval Ravikant, angel investor, co-founder of AngelList, public philosopher. Known for the 'How to Get Rich Without Getting Lucky' tweetstorm and 'The Almanack of Naval Ravikant,' his thinking spans wealth, leverage, judgment, happiness, and rational Buddhism.
agentmail
Operate the agent's own AgentMail email inboxes via the `agentmail` CLI — send, receive, and poll for verification links/codes and invitations. Use when a task…
implement-with-subagents
Orchestrates parallel waves of isolated workers over ready-for-agent frontier tickets; the orchestrator reviews and commits. User-invoked via…
skill-architect
A meta-skill for creating, documenting, and refining other Antigravity skills. Use this when the user wants to codify a workflow, automate a repetitive task,…
agents-md-generator
Generate hierarchical AGENTS.md structures for codebases. Use when user asks to create AGENTS.md files, analyze codebase for AI agent documentation, set up…
caveman-browse
Drive web pages through the caveman-browse MCP tools (browser_snapshot, browser_act, browser_eval, browser_recover). Use whenever interacting with a web page,…
loop-factory
Use when orchestrating Loop Factory specs from factory/specs/inbox or factory/specs/active, dispatching work to Codex or Claude agents, generating…
omnisonant-design
Product design guide for Omnisonant - omni-channel voice agents that replace call center staff. Use when designing, reviewing, or improving Omnisonant…
fan-out
Dispatch the current task to multiple subagents — after checking that fan-out is actually justified. Use for /fan-out, when the user says "multi-agent this" or…
long-horizon
Execute a spec'd goal in one long autonomous run — hours of agent work pushing a whole acceptance ledger, with humans only at the two gates, spec before and…