go

GitHub

无配置目标到任务引擎,作为编排器读取管道状态并分发至设置、发现、生成、交接或执行阶段技能。支持软件、渗透测试等目标,通过自适应发现和CDD验证执行计划。

skills/go/SKILL.md anombyte93/prd-taskmaster

触发场景

用户提及PRD 用户提及产品需求 用户表示想要构建某物 任何目标驱动型短语

安装

npx skills add anombyte93/prd-taskmaster --skill go -g -y
更多选项

不安装直接使用

npx skills use anombyte93/prd-taskmaster@go

指定 Agent (Claude Code)

npx skills add anombyte93/prd-taskmaster --skill go -a claude-code -g -y

安装 repo 全部 skill

npx skills add anombyte93/prd-taskmaster --all -g -y

预览 repo 内 skill

npx skills add anombyte93/prd-taskmaster --list

SKILL.md

Frontmatter
{
    "name": "go",
    "description": "Zero-config goal-to-tasks engine. Takes any goal (software, pentest, business, learning), runs adaptive discovery, generates a validated spec, parses into TaskMaster tasks, creates an implementation plan, and executes with built-in CDD verification. Use when user says \"PRD\", \"product requirements\", \"I want to build\", or any goal-driven phrase.",
    "allowed-tools": [
        "Read",
        "Skill",
        "Bash",
        "AskUserQuestion",
        "ToolSearch",
        "mcp__atlas-engine",
        "mcp__plugin_prd_go",
        "mcp__plugin_prd-taskmaster_go",
        "mcp__plugin_atlas-go_go"
    ],
    "user-invocable": true
}

go (orchestrator)

Pure routing. Reads pipeline state, dispatches to the correct phase skill.

Deferred MCP tools: in Claude Code the engine's MCP tools are often deferred — not callable until loaded. If a tool below is not directly callable, first run ToolSearch(query="select:mcp__plugin_prd_go__preflight") (keyword fallback ToolSearch(query="+atlas engine preflight", max_results=10)) and use whichever prefix matches (mcp__plugin_prd_go__ or mcp__atlas-engine__).

Flow

  1. Call mcp__plugin_prd_go__preflight() — get environment state

  2. Call mcp__plugin_prd_go__current_phase() — get pipeline state

  3. Route via Skill tool:

    • current_phase is null or SETUP → invoke /prd:setup
    • current_phase is DISCOVER → invoke /prd:discover
    • current_phase is GENERATE → invoke /prd:generate
    • current_phase is HANDOFF → invoke /prd:handoff
    • current_phase is EXECUTE → invoke /prd:execute-task
  4. After phase skill returns, re-check current_phase. If it advanced, route to the next phase. If not, report the blocker.

Stateless routing

This skill does NOT hold procedure. Each phase skill owns its own logic. The orchestrator survives context loss because every phase skill reads current_phase() on entry.

Red flags

These thoughts mean STOP, you're rationalising:

  • "I know which phase we're in, skip preflight" → NO. Preflight is cheap.
  • "The phase skill already ran, I don't need to re-check" → NO. Context might have died.
  • "I can just do the work myself" → NO. Dispatch to the phase skill.

版本历史

  • 5ac4b54 当前 2026-07-05 10:38

同 Skill 集合

skills/atlas/SKILL.md
skills/discover/SKILL.md
skills/execute-fleet/SKILL.md
skills/execute-task/SKILL.md
skills/expand-tasks/SKILL.md
skills/generate/SKILL.md
skills/setup/SKILL.md
skills/customise-workflow/SKILL.md
skills/handoff/SKILL.md

元信息

文件数
0
版本
5ac4b54
Hash
a3f471e1
收录时间
2026-07-05 10:38

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-14 08:28
浙ICP备14020137号-1 $访客地图$