菜单
Comprehensive knowledge of amplihack framework architecture, patterns, and usage
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Auto-generates code flow diagrams from multi-language module analysis. Detects when architecture diagrams become stale (code changed, diagram didn't). Supports Python, TypeScript/JavaScript, Rust, and Go out of the box. Use when: creating new modules, reviewing PRs for architecture impact, or checking diagram freshness across polyglot repositories. Generates mermaid diagrams showing imports, dependencies, and module relationships.
Execute multiple independent development tasks in parallel using subprocess isolation. Each task runs in a clean /tmp clone with Recipe Runner code-enforced workflow execution. Proven pattern: 4/5 PRs created successfully in first production use.
Interactive teaching agent for the goal-seeking agent generator and eval system. Provides a structured 14-lesson curriculum covering agent generation, SDK selection, multi-agent architecture, progressive evaluation (L1-L12), retrieval strategies, intent classification, math code generation, self-improvement loops with patch proposer and reviewer voting, and memory export/import.
Development workflow for features, bugs, refactoring. Normally executed as a sub-recipe by dev-orchestrator/smart-orchestrator. Supports direct invocation via recipe runner for standalone use.
Default task orchestrator for all development and investigation work. Classifies tasks, decomposes into parallel workstreams if appropriate, and routes execution through the recipe runner. Replaces ultrathink-orchestrator.
Writing clear, discoverable software documentation following the Eight Rules and Diataxis framework. Use when creating README files, API docs, tutorials, how-to guides, or any project documentation. Automatically enforces docs/ location, linking requirements, and runnable examples.
| name | amplihack-expert |
| description | Comprehensive knowledge of amplihack framework architecture, patterns, and usage |
| version | 2.0.0 |
| author | amplihack team |
| tags | ["amplihack","framework","architecture","workflows","agents","commands"] |
| triggers | {"keywords":["amplihack","dev-orchestrator","smart-orchestrator","/dev","workstream","recipe runner","workflow","DEFAULT_WORKFLOW","/.claude/","agent system","specialized agent","command system","hook system","continuous work","skill system","extensibility"],"patterns":["How does amplihack.*work","What is.*amplihack","amplihack.*(architecture|structure|design)","How do I.*amplihack","What.*agents.*available","How.*orchestrat","When.*use.*dev|When.*use.*/dev"],"file_paths":["~/.amplihack/",".claude/agents/",".claude/commands/",".claude/workflow/",".claude/skills/"]} |
| token_budget | {"skill_md":800,"reference_md":1200,"examples_md":600,"total":2600} |
| disclosure_strategy | {"quick_answer":"SKILL.md only","architecture_question":"SKILL.md + reference.md","how_to_question":"SKILL.md + examples.md","comprehensive":"All three files"} |
| references | ["reference.md: Comprehensive architecture details","examples.md: Real-world usage scenarios","@~/.amplihack/.claude/context/PHILOSOPHY.md: Core principles","@~/.amplihack/.claude/workflow/DEFAULT_WORKFLOW.md: Main workflow"] |
Engineering system for coding CLIs (Claude, Copilot, Amplifier): 5 mechanisms, 23-step workflow, 30+ agents, 80+ skills. Core entry point: /dev <task> — unified task orchestrator with auto-classification, parallel workstream detection, and goal-seeking execution loop.
| Command | Purpose | Use When |
|---|---|---|
| /dev | Orchestrate | Any non-trivial task |
| /analyze | Review | Check compliance |
| /fix | Fix errors | Common error patterns |
| /amplihack:ddd:* | Doc-driven dev | 10+ file features |
| /multitask | Parallel tasks | Sprint/batch work |
| Agent | Role |
|---|---|
| architect | Design |
| builder | Code |
| reviewer | Quality |
| tester | Tests |
| Name | Steps |
|---|---|
| DEFAULT_WORKFLOW | 23 |
| INVESTIGATION | 6 |
| FIX | 3 |
Quick: SKILL.md | Architecture: reference.md | How-To: examples.md | Deep: all
5 Mechanisms: Workflow (process), Command (entry), Skill (auto), Agent (delegate), Hook (runtime)
Composition: Commands → Workflows → Agents → Skills
Execution: /dev orchestrates — classifies task, detects parallel workstreams, executes via smart-orchestrator recipe, goal-seeking loop (3 rounds max)
Entry point: /dev <task> → dev-orchestrator skill → smart-orchestrator recipe → default-workflow recipe
Entry point: /dev <task> or any non-trivial prompt
Routing:
amplihack:core:analyzer responds directlyamplihack:core:builder (complex)Execution flow:
Session tree: Prevents infinite recursion
AMPLIHACK_MAX_DEPTH=3 (default) — increase to 5 for deep orchestrationAMPLIHACK_MAX_SESSIONS=10 (default) — max concurrent sessions per treeStatus signals:
GOAL_STATUS: ACHIEVED — all criteria metGOAL_STATUS: PARTIAL -- [gaps] — another round will runGOAL_STATUS: NOT_ACHIEVED -- [reason] — final failure status