ADR Assistant
Helps create, analyze, and maintain Architecture Decision Records
Best use case
ADR Assistant is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Helps create, analyze, and maintain Architecture Decision Records
Teams using ADR Assistant 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/adr-assistant/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ADR Assistant Compares
| Feature / Agent | ADR Assistant | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Helps create, analyze, and maintain Architecture Decision Records
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.
Related Guides
SKILL.md Source
# ADR Assistant Skill
I autonomously help with Architecture Decision Records when you're making architectural or technical decisions.
## When I Activate
I trigger when you're:
- Discussing technology choices
- Evaluating alternatives
- Making architectural decisions
- Documenting technical choices
- Updating existing ADRs
## What I Provide
### 1. ADR Analysis
- Review existing ADRs in `${WORKSPACE_DIR}/adr/`
- Identify related decisions
- Check for conflicts or dependencies
- Suggest improvements
### 2. ADR Creation
- Generate next ADR number (currently 0012+)
- Follow established template structure
- Research alternatives using Deepwiki
- Document consequences and tradeoffs
- Include implementation timeline
### 3. ADR Template Structure
```markdown
# NNNN. Title
Date: YYYY-MM-DD
## Status
Proposed | Accepted | Deprecated | Superseded
## Context
- Current situation
- Pain points
- Requirements
- Drivers
## Decision
What we decided and why
## Alternatives Considered
- Alt 1: Pros/Cons/Reason for rejection
- Alt 2: ...
## Consequences
- Positive
- Negative
- Neutral
- Risks with mitigations
## Implementation
- Action items
- Timeline
- Success metrics
## References
- Links to docs, commits, related ADRs
## Notes
- Additional insights
```
### 4. Best Practices
- Use Deepwiki to research similar ADRs
- Consider 3-5 alternatives minimum
- Document concrete consequences
- Include measurable success metrics
- Link to related ADRs
- Update ADR README index
## Current ADR Index (as of 2025-11-07)
- 0001: Use Bun as Primary Package Manager
- 0002: Adopt Turbo for Monorepo Build Orchestration
- 0003: Migrate from Docker to RAILPACK for Railway Deployment
- 0004: Use PostgreSQL for Primary Database
- 0005: Adopt ElizaOS for AI Agent Framework
- 0006: Enforce TypeScript Strict Typing Standards
- 0007: Real Gameplay Testing with Playwright
- 0008: Adopt Privy HD Wallets for User Wallet Management
- 0009: Semi-Automated Asset Approval Workflow
- 0010: Meshy.ai API Integration for 3D Asset Generation
- 0011: VRM Avatar System Architecture
Next number: **0012**
## Example Usage
**User:** "Should we use GraphQL or REST for our new API?"
**Me:** *I notice you're evaluating API architecture. Let me help create ADR-0012.*
I'll:
1. Research GraphQL vs REST using Deepwiki
2. Analyze your current tech stack (Elysia, TypeScript)
3. Consider Hyperscape-specific requirements
4. Document alternatives with detailed pros/cons
5. Propose decision with implementation plan
6. Create ADR file at `adr/0012-api-architecture-choice.md`
7. Update ADR README index
## Integration with Project
- Follows ADR template from existing records
- Updates README.md index automatically
- Links to related ADRs
- Aligns with project standards (CLAUDE.md)
- Uses Deepwiki for researchRelated Skills
lead-research-assistant
Researches and identifies potential customers, leads, and business opportunities for your product or service. Analyzes your offering, finds relevant companies and decision makers, provides contact information, and suggests outreach strategies. Use when looking for leads, researching target customers, identifying decision makers, or planning sales outreach.
ux
This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.
chrome-debug
This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.
modal-deployment
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.
grail-miner
This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.
tech-blog
Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.
astro
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.
vly-money
Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.
thor-skills
An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.
ontopo
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.
lets-go-rss
A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.