adr-writer
Use when capturing an architecture decision so it survives turnover — produces an ADR-NNNN.md from context, options considered, and the chosen path.
pinned to #7f8ee3cupdated 3 months ago
Ask your AI client: “install skills/adr-writer”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install skills/adr-writermetahub onboarded this repo on the author's behalf.
If you own github.com/oxbshw/LLM-Agents-Ecosystem-Handbook on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
533
Last commit
3 months ago
Latest release
published
- #ai
- #ai-agent
- #ai-agents
- #fine-tuning
- #finetuning-llms
- #freamework
- #llm
- #llmops
- #local-development
- #mcp-server
- #memory
- #rag
- #rag-chatbot
- #voice-agent
Automated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.7f8ee3c· 3 months ago
Behavioral checks ran but aren't published for this artifact; the static checks above ran at publish time.
Documentation
4 passed1 warningREADME has usage / example sectionswarn
README has no Usage / Example / Quick start / Installation heading at any level
Add a `# Usage`, `## Quick start`, or similar section so end users can copy/paste a working invocation. Code blocks alone work too if there are several.
Description quality
22 words · 148 chars — "Use when capturing an architecture decision so it survives turnover — produces a…"
README is present and substantial
19,199 chars · 20 sections · 2 code blocks
Tags / topics declared
14 total — ai, ai-agent, ai-agents, fine-tuning, finetuning-llms, freamework (+8)
Homepage / docs URL declared
no homepage declared (registry will use the repo URL) — info-only, not blocking
Release history
1- releasecurrent7f8ee3cwarn3 months ago
Contents
When to use
- A non-trivial architecture decision was just made
- Reverse-documenting a decision that wasn't recorded but should have been
- Preparing for a design review
When NOT to use
- Trivial choices (naming, formatting)
- Operational runbooks (those go to
runbooks/) - Product decisions without architectural impact
Inputs
| Name | Type | Required | Notes |
|---|---|---|---|
context | string | yes | The problem being solved, in 2–4 sentences |
options | list | yes | Alternatives considered |
decision | string | yes | Chosen path |
number | int | no | If omitted, finds next ADR number from memory/decisions/ |
Outputs
A file at memory/decisions/ADR-NNNN-<slug>.md matching the ADR template.
Workflow
- Find the next ADR number (or use
numberinput) - Slugify the decision's main subject
- Fill the template:
- Context, Decision, Alternatives, Consequences (positive + negative)
- Status:
accepted(default),proposed,superseded by ADR-XXXX
- Write to
memory/decisions/ADR-NNNN-<slug>.md - Add a one-line entry to
MEMORY.md#decisions
References
Success criteria
- Each alternative has a one-line "why not"
- Consequences include at least one negative
- File name matches
ADR-\d{4}-[a-z0-9-]+\.md
Failure modes
- Decision is actually a bundle of decisions → split into multiple ADRs
- Context is unclear → ask user for clarification, don't fabricate
Reviews
No reviews yet. Be the first.
Related
Verification Before Completion
Evidence before assertions, always
Writing Plans
Turn specs into phased implementation plans
Test-Driven Development
Red → green → refactor discipline for any feature or bugfix
mh install skills/adr-writer