skills/adr-architecture/SKILL.md
Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
npx skillsauth add lyndonkl/claude adr-architectureInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Each ADR captures: Context (what situation necessitates this decision), Decision (what we're choosing), Alternatives (other options considered), Consequences (trade-offs and implications), and Status (proposed, accepted, deprecated, superseded).
Quick Example:
# ADR-042: Use PostgreSQL for Primary Database
**Status:** Accepted
**Date:** 2024-01-15
**Deciders:** Backend team, CTO
## Context
Need to select primary database for new microservices platform.
Requirements: ACID transactions, complex queries, 10k+ QPS at launch.
## Decision
Use PostgreSQL 15+ as primary relational database.
## Alternatives Considered
- MySQL: Weaker JSON support, less robust constraint handling
- MongoDB: No ACID across documents, eventual consistency issues
- CockroachDB: Excellent but adds operational complexity we can't support yet
## Consequences
✓ Strong consistency and data integrity
✓ Excellent JSON support for semi-structured data
✓ Team has deep PostgreSQL experience
✗ Vertical scaling limits (will need read replicas at 50k+ QPS)
✗ More complex to shard than DynamoDB if we need it
Copy this checklist and track your progress:
ADR Progress:
- [ ] Step 1: Understand the decision
- [ ] Step 2: Choose ADR template
- [ ] Step 3: Document the decision
- [ ] Step 4: Validate quality
- [ ] Step 5: Deliver and file
Step 1: Understand the decision
Gather decision context: what decision needs to be made, why now, who decides, constraints (budget, timeline, skills, compliance), requirements (functional, non-functional, business), and scope (one service vs organization-wide). This ensures the ADR addresses the right problem.
Step 2: Choose ADR template
For technology selection (frameworks, libraries, databases) → Use resources/template.md. For complex architectural decisions with multiple interdependent choices → Study resources/methodology.md. To see examples → Review resources/examples/ (database-selection.md, microservices-migration.md, api-versioning.md).
Step 3: Document the decision
Create adr-{number}-{short-title}.md with: clear title, metadata (status, date, deciders), context (situation and requirements), decision (specific and actionable), alternatives considered (with pros/cons), consequences (trade-offs, risks, benefits), implementation notes if relevant, and links to related ADRs. See Common Patterns for decision-type specific guidance.
Step 4: Validate quality
Self-check using resources/evaluators/rubric_adr_architecture.json. Verify: context explains WHY, decision is specific and actionable, 2-3+ alternatives documented with trade-offs, consequences include benefits AND drawbacks, technical details accurate, understandable to unfamiliar readers, honest about downsides. Minimum standard: Score ≥ 3.5 (aim for 4.5+ if controversial/high-impact).
Step 5: Deliver and file
Present the completed ADR file, highlight key trade-offs identified, suggest ADR numbering if not provided, recommend review process for high-stakes decisions, and note any follow-up decisions needed. Filing convention: Store ADRs in docs/adr/ or architecture/decisions/ directory with sequential numbering.
For technology selection:
For architectural changes:
For standards and conventions:
For deprecations:
Do:
Don't:
resources/template.mdresources/methodology.mdresources/examples/database-selection.md, resources/examples/microservices-migration.md, resources/examples/api-versioning.mdresources/evaluators/rubric_adr_architecture.jsonADR Naming Convention: adr-{number}-{short-kebab-case-title}.md
adr-042-use-postgresql-for-primary-database.mdtesting
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.