adr-writing
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.
adr-writing generates and formats architectural decision records using the MADR template with completeness verification.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-21
adr-writing generates and formats architectural decision records using the MADR template with completeness verification. 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.
Use it when
- MADR (Markdown Architectural Decision Records) is a standardized format for documenting architectural decisions.
- adr-writing verifies ADR completeness against Definition of Done criteria using the E.C.A.D.R.
Verify before relying
Read SKILL.md below before installing (4 files). Open directory: indexed for reading, not audited.
Install
existential-birds/beagle/adr-writing · 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
How do I write an ADR document using adr-writing?
adr-writing guides you through creating architectural decision records in MADR format. Start by providing the core decision details—title, context, and options being considered. The tool structures your input into the complete MADR template, applies E.C.A.D.R. quality criteria to verify completeness, and flags any gaps where information is missing so you can address them systematically.
What is the MADR template and how does adr-writing format it?
MADR (Markdown Architectural Decision Records) is a standardized format for documenting architectural decisions. adr-writing formats your decisions as MADR by organizing them into sections like title, status, context, decision, consequences, and related decisions. It sequences numbering automatically, explores related ADRs and code context, and ensures each section follows the template structure for consistency.
How can I check ADR quality and completeness with adr-writing?
adr-writing verifies ADR completeness against Definition of Done criteria using the E.C.A.D.R. quality checklist. It systematically checks that all required sections are filled, evaluates the depth and clarity of each part, and marks gaps where data is unavailable. This ensures your architectural decisions meet quality standards before finalization.
Can adr-writing convert meeting notes into formal ADR format?
Yes. adr-writing transforms meeting notes and discussions into formal ADR documents by extracting decision points and structuring them into MADR sections. It identifies the decision, context, and consequences from your notes, fills the template sections systematically, and marks any gaps that need follow-up investigation before the ADR is complete.
What happens when adr-writing finds missing information in an ADR?
adr-writing marks and tracks gaps in ADR sections for follow-up investigation. When required information is unavailable—such as incomplete consequences or missing stakeholder input—the tool flags these sections so you know exactly what needs investigation. This prevents incomplete decisions from being finalized and ensures thorough documentation.
Does adr-writing generate ADR documents from decision data automatically?
adr-writing generates ADR documents from extracted decisions with systematic checks built in. Provide your decision data, and the tool fills the MADR template sections, sequences numbering, explores related decisions and code context, applies quality criteria, and generates the complete document while verifying it meets Definition of Done standards.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
ADR Writing
Overview
Generate Architectural Decision Records (ADRs) following the MADR template with systematic completeness checking.
Quick Reference
``` ┌─────────────┐ ┌──────────────┐ ┌─────────────┐ │ SEQUENCE │ ──▶ │ EXPLORE │ ──▶ │ FILL │ │ (get next │ │ (context, │ │ (template │ │ number) │ │ ADRs) │ │ sections) │ └─────────────┘ └──────────────┘ └─────────────┘ │ │ │ ▼ │ ┌─────────────┐ │ │ VERIFY │ │
(truncated - see the full file via the links below)
File tree — 4 files
plugins/beagle-analysis/skills/adr-writing/SKILL.md
plugins/beagle-analysis/skills/adr-writing/references/definition-of-done.md
plugins/beagle-analysis/skills/adr-writing/references/madr-template.md
plugins/beagle-analysis/skills/adr-writing/scripts/next_adr_number.py
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 › “Write and format architectural decision records following MADR template”
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.
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.
This skill walks you through the complete ADR lifecycle—from evaluating whether a decision is ready to record, through structured creation using the MADR template, to quality checks and ongoing log management. It grounds decisions in proven frameworks like START (readiness criteria) and ECADR (completion criteria), helping teams capture architectural rationale rather than just outcomes.
This skill streamlines creation and organization of temporary project work products like architecture decision records, research investigations, spike analyses, and implementation plans. It provides templated Python scripts, standardized naming conventions, and a date-based directory structure within `.claude/artifacts/` to keep artifacts organized and discoverable.
adr-author guides you through structured architecture decision authoring in three phases: Frame captures scope and drivers, Decide evaluates options and rationale, and Govern writes the final ADR file with lineage tracking. Choose between compact Y-Statement or detailed MADR v4.0.0 output, and enter via interactive capture, planner handoff, or template adoption.
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 (NOASSERTION) · Adr Skill (NOASSERTION) · adr-drafting (MIT)