maestro-setup
Setup Maestro in a project using or adopting Maestro: use for init/install/sync/doctor, global skills, hooks, harness setup, or agent integration diagnosis/repair.
214 repo starsObserved in 1 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
create-feature
Create a Switchboard feature from a remote session by writing the feature file directly — use when the VS Code extension is not running and create-feature.js is unreachable
213 repo starsObserved in 1 repos
Agent Building
discovery-services-agent-deployer
Deploy Discovery catalog agents end-to-end with one command: discover the agent, build and bind its tool when present, skip tool stages for agents without tools, deploy the agent, and optionally run validation. Use this skill whenever the user asks to deploy a Discovery agent, publish or rebuild an agent tool image, register a Discovery tool from a repo Dockerfile/tool.yaml, resume a failed deployment, or produce a dry-run deployment plan for an agent in this catalog.
213 repo starsObserved in 1 repos
Agent Building
discovery-services-starter-kit-deployer
Deploy Discovery catalog starter-kits end-to-end: validate kit.json agentRefs, build and deploy every referenced agent tool, deploy each referenced agent individually, and summarize deployed agents/tools plus customer-ready sample prompts. Use this skill whenever the user asks to deploy a Discovery starter-kit or deploy all agents listed in starter-kits/*/kit.json.
213 repo starsObserved in 1 repos
Agent Building
goal-prompt-builder
Build high-quality /goal commands for OpenAI Codex CLI 0.128+ that maximize audit-friendliness and minimize false-completion. Use this skill whenever the user wants to write, draft, generate, improve, or refine a /goal prompt — even if they don't say "skill" — including phrases like "help me write a goal", "design a goal for X", "review my goal command", "make a goal for this repo", or any request involving long-running Codex tasks. Also trigger when the user mentions Ralph loop, persistent agent objectives, or asks Codex to "keep working until done". Produces a complete, copy-pasteable /goal command using the 5-section golden template (Objective/Scope/Constraints/Done when/Stop if), supports three interaction modes (step-by-step, full-description, hybrid), auto-detects project type (Node/Python/Swift/Go/Rust/static) by inspecting filesystem or repo URL, reads AGENTS.md/CLAUDE.md if present, and predicts audit-friendliness before output.
213 repo starsObserved in 1 repos
Agent Building
hermes-lazyown
Use when running LazyOwn inside a Hermes agent session. Provides Hermes-optimized MCP tools with compact output, checkpoint resume, dynamic rules, and native delegation planning.
213 repo starsObserved in 1 repos
Agent Building
switchboard-contracts
System behavior contracts for agents driving Switchboard — consult when unsure how the system behaves; never for invocation. This doc answers how the system behaves. It never answers how to invoke something — for invocation, use the switchboard-orchestration skill and GET /catalog.
213 repo starsObserved in 1 repos
Agent Building
switchboard-mcp
Local stdio MCP server bridging Claude Desktop (and other MCP-only hosts) to Switchboard's LocalApiServer HTTP surface
213 repo starsObserved in 1 repos
Agent Building
switchboard-orchestration
Switchboard orchestration HTTP surface — the complete LocalApiServer contract for external AI coding tools and fleet agents. Discover the port, read the board/plans/features/worktrees/inbox/session-log, manage plan lifecycle, move cards, group and split features, dispatch fan-out, file requests to the orchestrator, and merge/clean up worktrees — all over localhost HTTP. Includes end-to-end workflows for a fleet coder inside a worktree and for an external orchestrator driving the board.
213 repo starsObserved in 1 repos
Agent Building