agentleFS
Atypical-ConsultingAtypical-Consulting/AdrMcp/.claude/skills/adr-review/SKILL.md

adr-review

Skill1 starsChanged 4 months agoMITView on GitHub

Use when the user wants to review, critique, or sanity-check an Architectural Decision Record (ADR) — an existing record or a draft. Evaluates whether the decision is sound, falsifiable, honestly scoped, and well-linked, using the AdrMcp MCP tools (get_adr, validate_adr, detect_conflicts, find_related_adrs). Triggers on "review this ADR", "critique my decision record", "is this ADR any good", "check ADR-000X", "does this decision hold up".

6 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions6 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 6

    1. chattocorp/chatto★ 3ksame name
    2. boykush/scraps★ 45same name
    3. ahamedzoha/atelier★ 2same name
    4. jpoindexter/theft-kit★ 1same name
    5. zgagnon/skills★ 1same name
    6. axodouble/skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Structural pass: Run validate_adr <id> — report any errors/warnings (missing sections, invalid status, dangling links, …

    line 18
  2. Very specific:

    Conflict/overlap pass: Run detect_conflicts and find_related_adrs <id> (or search_adrs on the topic) to check this decision doesn't …

    line 20

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Reviewing an ADR

You give an ADR a rigorous, fair review — both structural (does it validate?) and substantive (is the decision actually sound and honestly recorded?).

Requires the AdrMcp MCP server (tools get_adr, validate_adr, detect_conflicts, find_related_adrs, search_adrs). If unavailable, ask the user to connect it, or review the pasted markdown directly against the rubric below.

Workflow

  1. Load it. get_adr <id-or-slug> for the full record (or read the draft the user pasted).
  2. Structural pass. Run validate_adr <id> — report any errors/warnings (missing sections, invalid status, dangling links, superseded-without-replacement).
  3. Conflict/overlap pass. Run detect_conflicts and find_related_adrs <id> (or search_adrs on the topic) to check this decision doesn't silently contradict or duplicate another. Flag any accepted ADR it collides with.
  4. Substantive pass. Score against the rubric below.
  5. Report as a short verdict + prioritized findings. Offer concrete rewrites, not just critiques. If the fix is a status/link problem, point to adr-supersede; if it needs rewriting, offer to apply it via update_adr (preview first).

Rubric

Judge each; call out the ones that fail.

  • Significance — Does this decision deserve an ADR at all, or is it noise?
  • Context ≠ decision — The context frames forces/constraints and does NOT pre-name the chosen solution. Decision-leakage in the context is the most common defect.
  • Falsifiable decision — Stated as a concrete, specific "We will…", not a vague direction. Could someone tell whether it's being followed?
  • Real alternatives — Considered options are genuine, with a reason each was rejected. Strawmen ("do nothing", "do it badly") don't count.
  • Honest consequences — At least one real trade-off / cost is named. Upside-only records are suspect.
  • Traceability — Correct status for its lifecycle stage; links to related/superseded ADRs present; tags identify the area.
  • Concision — Reads like a memo. No filler, no unfilled placeholders.

Tone

Be direct and specific — cite the section and quote the phrase. A good review makes the decision better recorded, not just criticized. If the ADR is solid, say so plainly and stop; don't invent problems.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.