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(other options considered), Consequences (trade-offs and implications), and Status (proposed, accepted, deprecated, superseded).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
--- name: advisory-edit description: A strict advisory-only editing discipline for a writer who dictates ("speaks out") essays and wants help WITHOUT having their voice changed. The editor directs structure, flags grammar, and suggests strategic language — but never modifies the writer's text unless the writer explicitly says "apply" / "make that change" / "rewrite this." Produces a line-referenced, suggestion-only critique where every item is marked the writer's call. Four passes: structural, l
testing
Provides the house style for analyst-grade strategist writing — third-person register with sparing first-person, no em dashes, no "not X, not Y, not Z" negation cascades, numbered footnote citations rather than inline source parentheticals, specific opinion-signaling phrases, and topic-forward paragraph structure modeled on voice patterns observed in Damodaran's Musings on Markets and Thompson's Stratechery. Use when consolidating working notes into a finished long-form strategist or analyst report that must read as written by a senior human analyst rather than an AI assistant.
testing
Renders a markdown report to a PDF using pandoc with xelatex (11pt serif body, 1-inch margins, numbered footnotes, formal heading hierarchy). Requires a one-time install of pandoc and a LaTeX engine on the user's machine — basictex on macOS or texlive-xetex on Linux. Does not attempt automatic install. Fails loudly with the exact install commands if pandoc or xelatex is missing on the user's PATH. Use when producing a finished strategist or analyst report PDF from a polished markdown source.
testing
Produces step-by-step computational walkthroughs of vector and matrix operations as a sequence of numbered "frames", showing the explicit state at each step. The text-equivalent of a 3Blue1Brown animation — each frame shows what changed and why, so the learner can re-trace the operation by hand. Use when the learner needs to *see* a computation unfold (eigenvalue computation, attention with 3 tokens, gradient descent step, SVD on a 2×2, layer norm on a 3-vector, softmax of a small input), when an explanation has been given but the learner needs to ground it in a worked example, or when introducing an operation that's intimidating in symbol form but trivial in pencil-and-paper form.