adr-decision-extraction
Extract architectural decisions from conversations. Identifies problem-solution pairs, trade-off discussions, and explicit choices. Use when analyzing session transcripts for ADR generation.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/anderskev/adr-decision-extractionWhat This Skill Does
The adr-decision-extraction skill acts as an automated architectural scribe for engineering teams. It parses technical conversations, meeting transcripts, or chat logs to identify, structure, and categorize architectural decisions. By utilizing natural language processing, the skill extracts the 'why' behind a choice, the alternatives that were discarded, and the specific drivers that influenced the outcome, transforming informal discussions into formal ADR (Architecture Decision Record) material.
Installation
To integrate this skill into your OpenClaw agent, execute the following command in your terminal within the project directory:
clawhub install openclaw/skills/skills/anderskev/adr-decision-extraction
Ensure your agent has the necessary permissions to access the text sources you intend to scan.
Use Cases
- Post-Meeting Syncs: Quickly generate summaries of architectural debates after a sprint planning session.
- Project Onboarding: Extract historical decisions to help new team members understand why certain technologies (e.g., PostgreSQL vs. MongoDB) were chosen.
- Compliance & Audit: Document the reasoning behind security or infrastructure choices for future technical audits.
- Refactoring Documentation: Capture the rationale for replacing legacy components during ongoing maintenance.
Example Prompts
- "Analyze the last three hours of our Slack channel logs and extract any architectural decisions regarding our new microservices migration. Output the results in the standard JSON format."
- "I've pasted the transcript from our design sync. Please identify the decision regarding the authentication provider and identify if any trade-offs were discussed."
- "Look through the project chat context and find any decisions made about our API gateway. If the confidence is low, highlight the section for me to verify."
Tips & Limitations
- Explicit Tags: For mission-critical decisions, encourage your team to use the
[ADR]tag in chat to guarantee the skill captures the decision with 'high' confidence. - Context Windows: The skill performs best when provided with coherent, chronological discussion logs. Avoid feeding in fragmented snippets where the subject matter is ambiguous.
- Verification: Always review 'low' confidence extractions, as these are based on contextual inference and may misinterpret sarcasm or hypothetical scenarios as actual project commitments.
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-anderskev-adr-decision-extraction": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Related Skills
tutorial-docs
Tutorial patterns for documentation - learning-oriented guides that teach through guided doing
fetch-pr-feedback
Fetch review comments from a PR and evaluate with receive-feedback skill
swift-testing-code-review
Reviews Swift Testing code for proper use of
rust-testing-code-review
Reviews Rust test code for unit test patterns, integration test structure, async testing, mocking approaches, and property-based testing. Covers Rust 2024 edition changes including async fn in traits for mocks,
explanation-docs
Explanation documentation patterns for understanding-oriented content - conceptual guides that explain why things work the way they do