iterative-retrieval
Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to complete scoped work.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
Agents & models
26,287 results
reviewer-protocol
Reviewer rejection workflow and strict lockout semantics
squad-help
How to actually use Squad — Squad is a custom Copilot agent (invoked via the task tool with agent_type='Squad'), not a skill. This file explains the right…
tiered-memory
Three-tier agent memory model (hot/cold/wiki) for context reduction per spawn
spec-compliant
A fully spec-compliant skill for testing agentskills.io support. Use this when testing skill loading, validation, and progressive disclosure.
check-agentkit-prod
Checks AgentKit go-live so an agent can sign off only when every item is PASS or WAIVE with a reason. Use when the user wants AgentKit production, or to go…
check-saaskit-prod
Checks SaaSKit production so an agent can finish a go-live checklist. Use when the user wants SaaSKit production or to go live SaaSKit. It does not write login…
discover-connectors
Discovers AgentKit connectors from the live catalog and MCP so an agent can name tools and schemas. Use when the user asks what connectors exist, wants…
expose-agentkit-mcp
Exposes AgentKit tools over MCP so a client can call them on a per-user instance URL. Use when the user wants to expose AgentKit over MCP, generate a per-user…
integrate-agentkit
Integrates AgentKit so an agent can create a connection, a connected account, and an authorized token, then call one downstream API. Use when the user wants…
setup-agentkit
Configures AgentKit so a project has a dashboard connection, env credentials, and a first connector path. Use when the user wants to setup AgentKit in this…
antigravity-cli
Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent. Includes a background client for task progress,…
grok-cli
Delegate bounded tasks to Grok Build from a supervising agent such as Codex. Use when the user asks Grok to investigate, review, implement, or provide another…
refined-plan-mode
Use this skill when the user asks to plan, review, revise, continue, checkpoint, handoff, reset, or execute work using Refined Plan Mode. Also use it for…
unsloth-mcp-server
Work with the Unsloth MCP Server codebase. Use when maintaining, extending, or debugging this specific MCP server implementation. Provides architecture…
unsloth-tokenizer
Analyze, compare, and work with tokenizers using Unsloth tools. Compare different tokenizers, analyze token efficiency, and integrate with Unsloth models. For…
solo
Use when the user asks to use Solo or the Solo MCP server to spawn coding agents, manage scratchpads, inspect processes, or manage todos.
screenpipe-chats
Search what was said in existing screenpipe, Codex, Claude, Cursor, and Gemini CLI chats, then continue or steer one exact chat when the user explicitly asks.…
agentctl-setup
Install and set up the optional agentctl mod (task scope, refusal before execution, evidence that goes stale, model-free hand-over) — checks the environment,…
create-skill
Create or refactor Claude Code skills. Use when: building new skills, restructuring existing skills. Not for: skill quality audit (use skill-health-check),…
Agent Creating
Used to create a new agent. Used when a user wants to create a new agent
Creating Expert
Create new domain expert with expertise file and workflows. Use when adding new technology or domain area.
Meta Prompt
Generate prompt variations from templates. Use when creating new commands, skills, or workflows.
Skill Creating
Used to create a new skill. Used when a user wants to create a new skill