ADAPTATION_GUIDE

Use when adapting Droidz framework or creating custom workflows. Guide for customizing droids, skills, and commands for specific project needs.

181 stars

Best use case

ADAPTATION_GUIDE is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Use when adapting Droidz framework or creating custom workflows. Guide for customizing droids, skills, and commands for specific project needs.

Teams using ADAPTATION_GUIDE should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/adaptation-guide/SKILL.md --create-dirs "https://raw.githubusercontent.com/majiayu000/claude-skill-registry/main/skills/data/adaptation-guide/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/adaptation-guide/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How ADAPTATION_GUIDE Compares

Feature / AgentADAPTATION_GUIDEStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use when adapting Droidz framework or creating custom workflows. Guide for customizing droids, skills, and commands for specific project needs.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Superpowers Skills Adaptation Guide

## Overview

Adapting 21 workflow skills from obra/superpowers for Factory.ai Droid CLI.

## Key Differences: Superpowers vs Factory.ai

| Aspect | Superpowers (Claude Code) | Factory.ai Droid CLI |
|--------|---------------------------|----------------------|
| **Skill Reference** | `superpowers:skill-name` | Just `skill-name` (auto-loaded) |
| **User Reference** | "your human partner" | "the user" |
| **Slash Commands** | `/superpowers:command` | `/command` or native Droid commands |
| **Skill Location** | `~/.superpowers/skills/` | `.factory/skills/` |
| **Plan Location** | `docs/plans/` | `.droidz/specs/` or `docs/plans/` |
| **Worktree** | Git worktrees assumed | Optional, document if needed |
| **Subagents** | `superpowers:subagent-*` | Task tool with droidz-* droids |

## Adaptation Rules

### 1. Keep Core Methodology
- ✅ **KEEP**: The process/workflow (these are excellent!)
- ✅ **KEEP**: Red flags, rationalizations, checklists
- ✅ **KEEP**: Examples (Good/Bad patterns)
- ✅ **KEEP**: The "Iron Laws" and core principles

### 2. Update References
- ❌ **REMOVE**: "superpowers:" prefix from skill references
- ✅ **UPDATE**: "REQUIRED SUB-SKILL" → "RECOMMENDED SKILL" or "SEE ALSO"
- ✅ **UPDATE**: "your human partner" → "the user"
- ✅ **UPDATE**: Slash commands to Factory.ai equivalents

### 3. Simplify Frontmatter
```yaml
---
name: skill-name
description: When to use this skill
category: workflow  # Add this for workflow skills
---
```

### 4. Update File Paths
- Plans: `docs/plans/` → `.droidz/specs/` (or keep docs/plans)
- Skills: Reference other skills without prefix
- Tests: Keep language-agnostic examples

### 5. Update Subagent References
- `superpowers:subagent-driven-development` → Use Task tool with droidz-codegen
- `superpowers:executing-plans` → Use Task tool with droidz-orchestrator
- Document Factory.ai Task tool patterns

## Skills to Adapt (21 Total)

### Testing Skills (5)
1. **test-driven-development** - TDD process (RED-GREEN-REFACTOR)
2. **systematic-debugging** - 4-phase debugging framework
3. **verification-before-completion** - Pre-completion checklist
4. **defense-in-depth** - Multi-layer validation
5. **testing-anti-patterns** - What NOT to do

### Collaboration Skills (5)
6. **brainstorming** - Design through questions
7. **writing-plans** - Detailed implementation plans
8. **executing-plans** - Following plans step-by-step
9. **requesting-code-review** - How to ask for review
10. **receiving-code-review** - How to respond to feedback

### Development Skills (5)
11. **root-cause-tracing** - Backward tracing technique
12. **subagent-driven-development** - Task-by-task with fresh agents
13. **finishing-a-development-branch** - Completing work properly
14. **using-git-worktrees** - Parallel work branches
15. **condition-based-waiting** - Replace arbitrary timeouts

### Advanced/Meta Skills (6)
16. **dispatching-parallel-agents** - Spawning multiple agents
17. **writing-skills** - Creating new skills
18. **testing-skills-with-subagents** - Validating skill quality
19. **sharing-skills** - Publishing skills
20. **using-superpowers** → **using-droidz** - How to use this system
21. **commands** - Custom command reference

## Adaptation Workflow

For each skill:
1. **Fetch** original from obra/superpowers
2. **Keep** core methodology (process, principles, examples)
3. **Update** Factory.ai references (no "superpowers:" prefix)
4. **Simplify** frontmatter, update paths
5. **Test** that references work (skill → skill not superpowers:skill)
6. **Save** to `.factory/skills/[name].md`

## Quality Standards

Each adapted skill must:
- ✅ Preserve the original methodology and quality
- ✅ Remove superpowers-specific references
- ✅ Update to Factory.ai Droid CLI patterns
- ✅ Keep all examples, checklists, red flags
- ✅ Maintain 800+ lines (these are already comprehensive!)
- ✅ Add `category: workflow` to distinguish from framework skills

## Success Criteria

- ✅ All 21 skills adapted
- ✅ No broken references (superpowers: removed)
- ✅ Factory.ai Task tool patterns documented
- ✅ Skills work with Factory.ai auto-loading
- ✅ Total skill count: 42 (21 framework + 21 workflow)

Related Skills

Addon/Feature System Development Guide

181
from majiayu000/claude-skill-registry

**Version:** 1.0

adaptation-synthesis

181
from majiayu000/claude-skill-registry

Synthesize new works from extracted functional DNA documents. Use when adapting a source work to a new context, when combining multiple source extractions, or when generating variations that preserve function while changing form.

brand-guidelines

181
from majiayu000/claude-skill-registry

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

5-styleguide-generation

181
from majiayu000/claude-skill-registry

Fifth step in building instruction context for codebase

1k-feature-guides

181
from majiayu000/claude-skill-registry

Feature development guides for OneKey. Use when adding new chains, socket events, notifications, pages, or routes. Covers blockchain integration, WebSocket subscriptions, push notifications, and navigation patterns.

web-design-guidelines

181
from majiayu000/claude-skill-registry

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

tech-blog

159
from majiayu000/claude-skill-registry

Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.

Content & DocumentationClaude

whisper-transcribe

159
from majiayu000/claude-skill-registry

Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.

Media Processing

modal-deployment

159
from majiayu000/claude-skill-registry

Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.

DevOps & Infrastructure

astro

159
from majiayu000/claude-skill-registry

This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.

Coding & Development

ontopo

159
from majiayu000/claude-skill-registry

An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.

General Utilities

thor-skills

159
from majiayu000/claude-skill-registry

An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.

SecurityClaude