agentleFS
Sign inStart free
anxndsgnanxndsgn/skills/spec-review/SKILL.md

spec-review

Skill1 starsChanged 52 days agoApache-2.0View on GitHub

Review a spec through three lenses — is the feature needed, is the spec complete, does the implementation plan hold up. Use when the user asks to review, critique, or sanity-check a spec or draft spec.

47 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use get-pr-reviews, push-everything and 9 more.

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.
  • saffron-healthSkill

    get-pr-reviews

    Get nicely formatted output of the last review comments on a PR. Used internally by other skills.

    Also in 3 projects that use this

  • saffron-healthSkill

    push-everything

    Stage ALL changes in the repository (not just session changes), commit, and push. Use when you need to commit all pending changes.

    Also in 3 projects that use this

  • NVIDIASkill

    generate-spec

    Produce a feature specification covering API changes, backward compatibility, cross-language impact, performance, and a file-level change plan. Use when designing a new feature, planning a significant change, or the user asks to spec something out.

    Also in 3 projects that use this

  • telefrekSkill

    spec-init

    Bootstrap the spec corpus for this project

    Also in 3 projects that use this

  • AWSSkill

    implement-spec

    Implement the result of /to-spec and /to-tickets in code.

    Also in 8 projects that use this

  • ArvorCoSkill

    specify

    Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.

    Also in 3 projects that use this

  • +2 more from saffron-health

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 43 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a finding is really a decision only the user can make, phrase it as a question with your recommended answer, rather than reporting it …

    line 24

“Common” is measured: kept by at least 6 in 10 of the 43 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 the named spec (or the spec currently under discussion). For a review-only request, deliver the review. If the user has also authorized revisions or implementation, finish the review and continue within that scope; authorization given earlier in the conversation counts.

Read only what the review needs: the target spec, whatever the repo uses to state project intent and constraints (README, CLAUDE.md, ADRs), and the specs the target names or amends. Do not sweep the whole repo — a review that costs more than the spec is a bad trade.

Work through three lenses, in this order (a feature that fails lens 1 makes lenses 2–3 moot):

  1. Necessity. Does the problem justify the feature? Test it against the project's stated intent and boundaries — where a spec conflicts with them, the spec is defective. Ask: could an existing surface (a verb, a plugin, another spec) absorb this instead? What actually breaks for the user if this is never built?
  2. Completeness. Would two implementers reading only this spec build the same thing? Hunt the underspecified edges: empty and error states, interactions with the specs it touches, concurrency and idempotency where the domain has them, and whether every Acceptance Criterion is observable and mapped to credible evidence in the Verification Plan. Check that the project's domain terms are used exactly — a term used loosely is a decision left unmade.
  3. Implementation. Will the plan survive contact with the codebase? Check it against the architecture invariants in the repo CLAUDE.md; flag hidden migrations, hard-to-reverse choices, and machinery out of proportion to the problem it solves.

Report format — keep it short:

  • One verdict line per lens: sound / gaps / defective, with a half-sentence reason.
  • Findings as one ranked list, most severe first. Each finding: one sentence naming the defect, the spec section it lives in, and a concrete fix or question. Cite sections, not vibes.
  • A clean lens gets one line saying so. No praise padding.

When a finding is really a decision only the user can make, phrase it as a question with your recommended answer, rather than reporting it as a defect.

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.

Check your setup, free