architecture-decision-records-(adrs)
Skill by wpank
Why use this skill?
Improve technical documentation and institutional memory with the OpenClaw ADR skill. Effortlessly capture design choices and trade-offs.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/wpank/architecture-decision-recordsWhat This Skill Does
The architecture-decision-records-(adrs) skill by wpank provides a structured framework for the OpenClaw agent to generate, manage, and maintain Architecture Decision Records (ADRs). ADRs are lightweight, persistent documents that capture the "why" behind significant technical choices. Instead of forcing developers to decipher legacy code or dig through years of chat history to understand why a specific database, framework, or API pattern was chosen, this skill allows the agent to create standardized documentation that acts as the institutional memory for your project. By adopting this practice, teams ensure that context, decision drivers, and long-term consequences are clearly archived for future maintainers.
Installation
To integrate this documentation capability into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/wpank/architecture-decision-records
Use Cases
This skill is ideal for:
- Onboarding new engineers by providing a clear history of system design.
- Evaluating trade-offs during major refactoring projects.
- Defending architectural choices to stakeholders or during security audits.
- Preventing the 're-discovery' of technical limitations by documenting why certain paths were previously rejected.
- Ensuring consistency across distributed teams regarding infrastructure and security patterns.
Example Prompts
- "OpenClaw, draft an ADR for migrating our backend from a monolithic service to microservices, including pros and cons regarding latency and development velocity."
- "Review our current infrastructure. Can you create an ADR comparing the trade-offs of using AWS RDS vs. Aurora for our high-traffic e-commerce database?"
- "Summarize the consequences and risks of our decision to use GraphQL instead of REST, and save it to our repository using the standard ADR template."
Tips & Limitations
- Be Specific: Always provide the agent with the specific technical constraints or business requirements, such as expected load or team familiarity.
- Stay Lightweight: ADRs are not meant to be 50-page design docs. Keep the 'Context' and 'Decision' sections concise (2-3 paragraphs max).
- Lifecycle Awareness: Do not edit old records. If a decision changes, use the 'Superseded' status to link to a new ADR. This maintains a clear audit trail of how the system evolved over time.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-wpank-architecture-decision-records": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write
Related Skills
mermaid-diagrams
Create software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams, sequence diagrams, flowcharts, ERDs, C4 architecture diagrams, state diagrams, git graphs, and other diagram types. Triggers include requests to diagram, visualize, model, map out, or show the flow of a system.
api-design-principles
Skill by wpank
auto-context
Automatically read relevant context before major actions. Loads TODO.md, roadmap.md, handoffs, task plans, and other project context files so the AI operates with full situational awareness. Use when starting a task, implementing a feature, refactoring, debugging, planning, or resuming a session.
clear-writing
Write clear, concise prose for humans — documentation, READMEs, API docs, commit messages, error messages, UI text, reports, and explanations. Combines Strunk's rules for clearer prose with technical documentation patterns, structure templates, and review checklists.
track-performance
Track the performance of Uniswap LP positions over time — check which positions need attention, are out of range, or have uncollected fees. Use when the user asks how their positions are doing.