agentleFS
CsHengCsHeng/agent-skills/skills/review-design/SKILL.md

review-design

Skill3 starsChanged 10 days agoMITView on GitHub

Read-only evaluator for one bounded design brief. Return evidence-backed boundary findings; direct review requests belong to review-change, and final adjudication stays with the calling agent.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use review-pr.

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.
  • DockerSkill

    review-pr

    Review one or more incoming Docker documentation pull requests as a maintainer. Independently validate technical claims, assess editorial fit and information architecture, choose a verdict, and draft exact inline or PR-wide feedback behind a confirmation gate. Use for requests such as "review PR 123", "is this PR correct?", "does this information belong here?", "validate this PR", or "help review backlog PRs". Do not use to maintain or fix a PR you own; use maintain-pr for that.

    Also in 3 projects that use this

The file

Files
SKILL.md

Review Design

Evaluate only the supplied design target and brief under the finding rules, causal scope, and verdict in review-change. For a whole-design target, defects anywhere in the artifact are in scope; for a diff-scoped target, a blocking candidate is caused or newly activated by that diff.

Design-Specific Checks

  • Scope and ownership: one bounded change surface with a named owner, a sane dependency direction, and durable truth boundaries that stay put; material rollout or recovery risk the design does not own.
  • Decisions versus means: a material unresolved decision, or an omitted main goal, necessary condition, specified technical choice, or inviolable boundary. Local choices an executor can investigate stay with the executor.
  • Acceptance and cutover: success is verifiable without turning every acceptance condition into a prerequisite for switching; coexistence, qualification environments, rollback systems, and observation windows cite a concrete protected interest, per the replacement-and-cutover reference in development-standards.
  • Delivery intent: delivery intent, existing authority, and actual capability stay separate; facts material to feasibility or protected boundaries are preserved in the design or an accessible owner record, with supplied facts distinct from assumptions.
  • Secondary space: authorized best-effort secondary work is recorded without an exhaustive failure catalog; commitments that would force item-by-item reapproval are flagged.
  • Architecture tradeoff: demand, constraints, ownership, and practical evidence support the choice; recovery or reconsideration detail appears where a concrete risk or unsettled premise needs it.

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.