mcpField
A
amplihack-expert

amplihack-expert

github.com/rysweetAgent workflows76113 installsUpdated 21w ago
Repository

About amplihack-expert

amplihack-expert is a knowledge and navigation skill for the amplihack engineering system, aimed at users coding with Claude, Copilot, or Amplifier. It explains how commands, workflows, agents, and skills fit together, including `/dev` task classification and orchestration.

Key features

  1. 01Describe five core mechanisms
  2. 02Index commands and workflows
  3. 03Explain agent responsibilities
  4. 04Outline `/dev` task orchestration
  5. 05Document session tree limits and status signals

Use cases

  1. 01Choose an entry point for non-trivial development tasks
  2. 02Split work into parallel workstreams
  3. 03Find analysis, fixing, and testing responsibilities
  4. 04Track orchestration results and goal status

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/rysweet/amplihack --skill amplihack-expert

After installing, type/amplihack-expertin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

examples.md
reference.md
tests/
__init__.py
test_amplihack_expert_skill.py

Details

From the project README

amplihack Expert Knowledge

What is amplihack?

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.

Quick Reference

Top Commands
CommandPurposeUse When
/devOrchestrateAny non-trivial task
/analyzeReviewCheck compliance
/fixFix errorsCommon error patterns
/amplihack:ddd:*Doc-driven dev10+ file features
/multitaskParallel tasksSprint/batch work
Top Agents
AgentRole
architectDesign
builderCode
reviewerQuality
testerTests
Workflows
NameSteps
DEFAULT_WORKFLOW23
INVESTIGATION6
FIX3

Navigation Guide

Quick: SKILL.md | Architecture: reference.md | How-To: examples.md | Deep: all

Core Concepts

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

dev-orchestrator Architecture

Entry point: /dev <task> or any non-trivial prompt

Routing:

  • Q&A → amplihack:core:analyzer responds directly
  • Operations → bash (simple) or amplihack:core:builder (complex)
  • Development/Investigation → smart-orchestrator recipe (full orchestration)

Execution flow:

  1. Classify task (architect agent → JSON decomposition)
  2. Detect workstreams (1 = single session, 2-5 = parallel via multitask)
  3. Register session in tree (depth/capacity enforcement)
  4. Execute rounds (up to 3, goal-seeking reflection loop)
  5. Summarize results with PR links and GOAL_STATUS

Session tree: Prevents infinite recursion

  • AMPLIHACK_MAX_DEPTH=3 (default) — increase to 5 for deep orchestration
  • AMPLIHACK_MAX_SESSIONS=10 (default) — max concurrent sessions per tree

Status signals:

  • GOAL_STATUS: ACHIEVED — all criteria met
  • GOAL_STATUS: PARTIAL -- [gaps] — another round will run
  • GOAL_STATUS: NOT_ACHIEVED -- [reason] — final failure status

Related Docs

  • reference.md: Architecture (5 mechanisms, 5 layers, hooks)
  • examples.md: Scenarios (5+ real examples)
  • @~/.amplihack/.claude/context/PHILOSOPHY.md: Core principles
  • @~/.amplihack/.claude/workflow/DEFAULT_WORKFLOW.md: 23 steps
  • @~/.amplihack/.claude/agents/amplihack/: All agents
  • @~/.amplihack/.claude/commands/amplihack/: All commands
  • @~/.amplihack/.claude/tools/amplihack/hooks/: Hook system
  • amplifier-bundle/recipes/smart-orchestrator.yaml: Core orchestration recipe
  • amplifier-bundle/tools/session_tree.py: Recursion guard (depth limits)
  • amplifier-bundle/tools/orch_helper.py: JSON extraction helper

Comments

Markdown supported