agentleFS
rpraharajrpraharaj/ai-sdlc/skills/review-architecture/SKILL.md

review-architecture

Skill0 starsChanged 18 days agoMITView on GitHub

Adversarially review an architecture document; fail closed without evidence. Use when the user asks to review architecture, challenge a system shape, or /review-architecture. Do not edit the architecture file. Do not implement.

15 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use review-testing and review-correctness.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • worldbankSkill

    review-testing

    Review test code for quality, design, and completeness after implementing a feature or fixing a bug. Use when the user asks to "review my tests", "check my test quality", "are these tests good enough", "review testing", or after completing a feature implementation that includes tests. Also use when tests feel brittle, flaky, or superficial. Cross-references production code to find coverage gaps.

    Also in 4 projects that use this

  • navjyotnishantSkill

    review-correctness

    Use this skill when the user asks to "review my changes for bugs", "check this diff for correctness", "did I introduce a regression", or wants a correctness-focused review of the current commit or uncommitted work before pushing. Reviews the changed lines and their blast radius for logic errors, regressions, unhandled edge cases, and missing validation. Works in any git repo; nothing here is project-specific.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 4

    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. Distinctive:

    Do not edit the architecture file.

    line 19
  2. Distinctive:

    If the file is missing, stop.

    line 35
  3. Very specific:

    Read AGENTS.md if present.

    line 44
  4. Distinctive:

    Read the architecture file.

    line 45
  5. Very specific:

    Check each checkable claim against the repo or named context.

    line 46
  6. Distinctive:

    Look for: invented SLOs, missing trust boundaries, expand+contract ignored, alternatives missing.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 14 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

Review architecture

Attack the shape, not the author’s pride. This is not write-architecture, not write-design, and not review-change (that is a code diff).

Do not edit the architecture file. Missing evidence means unverified, not passed.

Is this the right skill?

SignalDo this instead
No architecture file yetwrite-architecture
How this initiative is builtwrite-design
One sticky choicerecord-decision
Code diffreview-change

Required inputs

  • Path to the architecture document
  • Access to the repo (or an explicit “greenfield — no code”) so claims can be checked

If the file is missing, stop.

Human decisions (do not invent)

  • Whether a finding is accepted
  • Quality targets not already in the doc or write-nfr

Procedure

  1. Read AGENTS.md if present. Read context/systems-of-record.md if present.
  2. Read the architecture file. List claims that can be checked (services, stores, actors).
  3. Check each checkable claim against the repo or named context. Unchecked → unverified.
  4. Find the home: sibling of the architecture file, docs/architecture/<area>-review.md.
  5. Open references/architecture-review-template.md. Copy every heading. Write n/a when unused.
  6. Findings: severity, section, evidence path, suggestion. Empty list is valid only after you checked claims.
  7. Look for: invented SLOs, missing trust boundaries, expand+contract ignored, alternatives missing.

Output

  • Path: docs/architecture/<area>-review.md
  • Template: references/architecture-review-template.md

Quality bar

  • Architecture path is named
  • Every finding has evidence or is marked unverified
  • The architecture file was not edited
  • Unused headings are n/a

Done

  1. Path
  2. Finding count (including unverified)
  3. Next skill: write-architecture (author revises) or record-decision

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.