Smithery Logo
MCPsSkillsDocsPricing
Login
Smithery Logo

Accelerating the Agent Economy

Resources

DocumentationPrivacy PolicySystem Status

Company

PricingAboutBlog

Connect

© 2026 Smithery. All rights reserved.

    anntnzrb

    go

    anntnzrb/go
    AI & ML
    1 installs

    About

    SKILL.md

    Install

    Install via Skills CLI

    or add to your agent
    • Claude Code
      Claude Code
    • Codex
      Codex
    • OpenClaw
      OpenClaw
    • Cursor
      Cursor
    • Amp
      Amp
    • GitHub Copilot
      GitHub Copilot
    • Gemini CLI
      Gemini CLI
    • Kilo Code
      Kilo Code
    • Junie
      Junie
    • Replit
      Replit
    • Windsurf
      Windsurf
    • Cline
      Cline
    • Continue
      Continue
    • OpenCode
      OpenCode
    • OpenHands
      OpenHands
    • Roo Code
      Roo Code
    • Augment
      Augment
    • Goose
      Goose
    • Trae
      Trae
    • Zencoder
      Zencoder
    • Antigravity
      Antigravity
    ├─
    ├─
    └─

    About

    Execute a plan with parallel agent orchestration. Activate when user says /go, asks to execute a plan, or requests multi-agent parallelism.

    SKILL.md

    Go Orchestration Skill

    Execute the plan using multi-level parallelism.

    Context

    • Extract the plan from previous messages (source of truth)
    • If a todo-list tool exists, use it as supplementary reference, but prioritize the conversational plan
    • Optional arguments provide additional context: $ARGUMENTS

    Step 1 - Analyze dependencies

    • Identify independent tasks (can run in parallel)
    • Identify dependent tasks (must wait)
    • Group into phases; each phase contains only independent tasks

    Step 2 - Orchestrate

    • For each phase, spawn multiple subagents concurrently using parallel spawn_agent tool calls
    • Each subagent prompt must include:
      1. Full context (architectural decisions, patterns, constraints from planning)
      2. Specific task, files, and acceptance criteria
      3. Instruction: "Batch ALL independent tool calls in a single message"
      4. Expected return: "Return only: OK [confirmation] or BLOCKER [blocker]"

    Step 3 - Execute phases

    • Phase N: spawn all independent agents in one parallel batch
    • Wait for phase completion
    • Phase N+1: spawn next batch (may depend on Phase N results)
    • On failure: stop, report blocker, await decision

    Rules

    • Orchestration only; do not perform file operations directly
    • No redundant explanations; the plan is already understood
    • Compact output: report phases, agents spawned, and final status
    Recommended Servers
    Thoughtbox
    Thoughtbox
    Parallel Tasks
    Parallel Tasks
    Browser tool
    Browser tool
    Repository
    anntnzrb/agents
    Files