adr-decision-extraction
This skill scans conversations, session transcripts, and design discussions to isolate architectural decisions—capturing problem statements, chosen options, alternatives considered, and decision drivers. It recognizes explicit `[ADR]` tags alongside implicit choice patterns and trade-off debates, then rates each decision's confidence level. Output feeds directly into ADR writing tools rather than generating documents itself.
adr-decision-extraction mines conversations and transcripts for architectural decisions, surfacing problem-solution pairs and trade-offs to feed ADR writing.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-21
adr-decision-extraction mines conversations and transcripts for architectural decisions, surfacing problem-solution pairs and trade-offs to feed ADR writing. This skill scans conversations, session transcripts, and design discussions to isolate architectural decisions—capturing problem statements, chosen options, alternatives considered, and decision drivers. It recognizes explicit `[ADR]` tags alongside implicit choice patterns and trade-off debates, then rates each decision's confidence level. Output feeds directly into ADR writing tools rather than generating documents itself.
Use it when
- Feed adr-decision-extraction your conversation, transcript, or design meeting notes.
- Yes.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
existential-birds/beagle/adr-decision-extraction · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What architectural decisions can adr-decision-extraction find?
adr-decision-extraction scans conversations and transcripts to isolate architectural decisions, capturing problem statements, chosen options, alternatives considered, and decision drivers. It recognizes explicit [ADR] tags alongside implicit choice patterns and trade-off debates from design discussions, then rates each decision's confidence level for use in ADR documentation.
How do I extract architectural decisions from conversation?
Feed adr-decision-extraction your conversation, transcript, or design meeting notes. The skill identifies both explicit [ADR] tags and implicit architectural choices embedded in planning sessions. It extracts problem-solution pairs, technology selections, and trade-off debates, then outputs structured decision data ready for ADR writing tools.
Does adr-decision-extraction find implicit decisions?
Yes. adr-decision-extraction mines implicit decisions from planning sessions alongside explicit [ADR] tags. It detects architectural choices woven through design discussions—technology preferences, alternatives debated, and drivers behind selections—even when not formally tagged, preparing all findings for ADR documentation.
What output does adr-decision-extraction produce?
adr-decision-extraction extracts decision context, problem-solution pairs, and trade-offs from transcripts, then assigns confidence levels to each detected choice. Output feeds directly into ADR writing tools rather than generating documents itself, giving you structured input ready for formal architectural decision records.
Can adr-decision-extraction identify alternatives discussed?
Yes. adr-decision-extraction identifies alternatives discussed in meetings and captures trade-off debates from planning sessions. It extracts decision drivers, technology choices, and rationale alongside the options considered, helping you document the full context of architectural choices for ADR preparation.
What are the main intents of adr-decision-extraction?
adr-decision-extraction prioritizes extracting architectural decisions from transcripts for ADR input, identifying problem-solution pairs and trade-offs, finding explicit [ADR] tags, mining implicit decisions from planning, and assessing confidence levels of detected choices. Each intent supports preparing comprehensive, well-sourced architectural decision records.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
ADR Decision Extraction
Extract architectural decisions from conversation context for ADR generation.
Detection Signals
| Signal Type | Examples |
|---|---|
| Explicit markers | [ADR], "decided:", "the decision is" |
| Choice patterns | "let's go with X", "we'll use Y", "choosing Z" |
| Trade-off discussions | "X vs Y", "pros/cons", "considering alternatives" |
| Problem-solution pairs | "the problem is... so we'll..." |
Extraction Rules
Explicit Tags (Guaranteed Inclusion)
Text marked with [ADR] is always extracted:
``` [ADR] Using
(truncated - see the full file via the links below)
File tree — 1 file
plugins/beagle-analysis/skills/adr-decision-extraction/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Extract architectural decisions from transcripts to prepare ADR input”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Write ADR captures architectural decisions from your conversation and generates formatted Architecture Decision Records automatically. It orchestrates the full workflow—extracting decisions, confirming selections with you, writing ADRs in parallel, and verifying output against quality standards.
adr-writing creates and formats architectural decision records using the MADR structure, applying E.C.A.D.R. quality criteria to ensure completeness. It sequences numbering, explores related decisions and code context, fills template sections, and marks gaps for investigation where data is unavailable.
Prompt Improver refines code-related prompts by evaluating task clarity, investigation depth, verification steps, and scope control. It applies transformation rules to strengthen prompts for implementation, debugging, refactoring, code review, and testing tasks. The skill ensures prompts follow investigation-first principles and include appropriate verification checks before execution.
This skill generates Architecture Decision Records (ADRs) that capture the context, decision, and consequences of significant technical choices. It guides you through gathering essential information, selecting from three formats (MADR, Nygard, or Y-Statement), and produces a structured document that preserves reasoning for future engineers.
This skill structures architecture decisions by enforcing a rigorous trade-off analysis: context, constraints, at least three viable options, and explicit consequences. It produces formal decision records (ADR/RFC/RFD) that capture both positive and negative outcomes, ensuring decisions remain auditable and reversible.
Create and maintain Architecture Decision Records that capture the reasoning behind significant technical choices. This skill provides multiple templates—from standard MADR format to lightweight Y-statements—and guidance on when ADRs matter most, helping teams establish clear decision-making processes and onboard members through documented architectural history.
More skills Create Adr Spike (unlicensed) · Create Adr (NOASSERTION) · architecture-decision-records (MIT) · adr-discovery (MIT)