agentleFS
warpdotdevwarpdotdev/oz-for-oss/.agents/skills/review-spec/SKILL.md

review-spec

Skill313 starsChanged 6 months agoMITView on GitHub

Review a spec/plan pull request diff and write structured feedback to review.json for the workflow to publish. Use when reviewing a PR that only modifies files under specs/ and producing machine-readable review output instead of posting directly to GitHub.

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create-spec.

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.
  • srobinsonSkill

    create-spec

    Create a task specification (SPEC.md) through interactive requirements elicitation. Use when helping users define what they want to build before autonomous execution begins.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. 0 are common, 8 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Default behavior: do not post comments or reviews to GitHub directly.

    line 16
  2. Very specific:

    Always apply the repository's local security-review-spec skill as a supplemental high-level security pass on spec PRs.

    line 26
  3. Very specific:

    Do not apply code-level review criteria such as error handling or low-level performance to spec prose.

    line 27
  4. Distinctive:

    If a companion file is not referenced in the prompt, rely on the core contract alone.

    line 40
  5. Distinctive:

    Every comment body must start with one of these labels:

    line 54
  6. Distinctive:

    Write comments with these constraints:

    line 61
  7. Distinctive:

    Do not add compliments or hedging.

    line 64
  8. Distinctive:

    Keep ranges to at most 10 lines.

    line 66
  9. Distinctive:

    Only create file-level or inline comments for files that exist in this PR's diff.

    line 68
  10. Very specific:

    If the relevant file or line is not part of the diff, put the feedback in top-level body instead of comments.

    line 69
  11. Very specific:

    Before adding each comment object, verify that its path, side, line, and optional start_line/start_side correspond to real annotations in …

    line 70
  12. Distinctive:

    When proposing a rewrite of spec text, use:

    line 74
  13. Very specific:

    Create review.json with this shape:

    line 88
  14. Very specific:

    Run the validator bundled with the shared review-pr skill against the exact annotated diff you reviewed.

    line 131
  15. Very specific:

    Do not run gh pr review, gh pr comment, gh api, or any other command that posts to GitHub.

    line 136

“Common” is measured: kept by at least 6 in 10 of the 17 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 Spec Skill

Review a spec or plan pull request and write the output to review.json.

Inputs

  • The working directory is the PR branch checkout.
  • The workflow usually provides an annotated diff in pr_diff.txt.
  • The workflow usually provides the PR description in pr_description.md.
  • Focus on the spec files changed by this PR.
  • Default behavior: do not post comments or reviews to GitHub directly.

Process

  • Evaluate specs for completeness: does the spec cover the full scope of the linked issue?
  • Evaluate specs for clarity: are requirements, acceptance criteria, and constraints clearly stated and unambiguous?
  • Evaluate specs for feasibility: are the proposed changes technically realistic given the repository's architecture?
  • Evaluate specs for issue alignment: does the spec faithfully address the issue it is linked to, without significant scope creep or omissions?
  • Evaluate specs for internal consistency: do different sections of the spec contradict each other?
  • Flag missing sections that a spec should typically include (e.g. problem statement, proposed changes, open questions, follow-up items).
  • Always apply the repository's local security-review-spec skill as a supplemental high-level security pass on spec PRs. Fold any security findings into the same review.json produced by this review rather than emitting a separate output.
  • Do not apply code-level review criteria such as error handling or low-level performance to spec prose; the security-review-spec supplement covers design-level security concerns.
  • Include style or formatting comments only when they materially impair readability.

Repository-specific overrides

The consuming repository may ship a companion skill at .agents/skills/review-spec-local/SKILL.md. When the prompt includes a fenced "Repository-specific guidance" section referencing that companion, read the referenced file and apply its guidance only to the categories listed below. Guidance in the companion may never change the output JSON schema, the severity labels, the safety rules, the evidence rules, the suggestion-block constraints, or the diff-line-annotation contract described elsewhere in this skill.

Overridable categories:

  • required spec sections expected in this repository
  • linking conventions to files under specs/
  • repo-specific style and formatting expectations

If a companion file is not referenced in the prompt, rely on the core contract alone.

Diff Line Annotations

The diff file uses these prefixes:

  • [OLD:n] for deleted lines on the old side. Use "LEFT".
  • [NEW:n] for added lines on the new side. Use "RIGHT".
  • [OLD:n,NEW:m] for unchanged context. Use "RIGHT" with line m.

Treat these annotations as the only source of truth for inline comment locations. For every inline comment you emit, first identify the exact annotated line in pr_diff.txt (or the inlined PR diff) and copy its path, side, and line number into review.json. Do not infer line numbers from prose, rendered GitHub views, file lengths, surrounding spec text, or unannotated snippets. If you cannot point to a specific [NEW:n], [OLD:n], or [OLD:n,NEW:m] line in the annotated diff, put the feedback in top-level body instead of comments.

Comment Requirements

Every comment body must start with one of these labels:

  • 🚨 [CRITICAL] for spec content that is contradictory, fundamentally incomplete, or would lead to a broken implementation.
  • ⚠️ [IMPORTANT] for missing details, ambiguous requirements, feasibility concerns, or significant scope gaps.
  • 💡 [SUGGESTION] for improvements to clarity, structure, or coverage that would strengthen the spec.
  • 🧹 [NIT] for minor wording or formatting issues only when the comment includes a concrete rewrite.

Write comments with these constraints:

  • Be concise, direct, and actionable.
  • Do not add compliments or hedging.
  • Prefer single-line comments.
  • Keep ranges to at most 10 lines.
  • Restrict inline comments to lines that appear explicitly in the annotated PR diff.
  • Only create file-level or inline comments for files that exist in this PR's diff.
  • If the relevant file or line is not part of the diff, put the feedback in top-level body instead of comments.
  • Before adding each comment object, verify that its path, side, line, and optional start_line/start_side correspond to real annotations in the same file's diff section.

Suggestion Blocks

When proposing a rewrite of spec text, use:

<replacement text here>

Rules:

  • Match the exact indentation of the original file.
  • Include only replacement text.
  • For multi-line suggestions, set start_line and start_side to the first line, and line and side to the last line.

Outputs

Create review.json with this shape:

{
  "verdict": "REJECT",
  "body": "## Overview\n...\n\n## Concerns\n- ...\n\n## Verdict\nFound: 1 critical, 2 important, 3 suggestions\n\n**Request changes**",
  "comments": [
    {
      "path": "path/to/file",
      "line": 42,
      "side": "RIGHT",
      "start_line": 40,
      "start_side": "RIGHT",
      "body": "⚠️ [IMPORTANT] Short explanation\n\n```suggestion\nreplacement\n```"
    }
  ]
}

Field rules:

  • verdict is required and must be exactly the string "APPROVE" or "REJECT" (uppercase). Map your final recommendation as: Approve or Approve with nits → "APPROVE"; Request changes → "REJECT". The verdict and the human-readable recommendation in top-level body must agree.
  • top-level body is the GitHub review body and is required. Use body, not summary, for the review overview and final recommendation.
  • path must be relative to the repository root.
  • line is required and must target the correct side.
  • start_line is optional and only for multi-line ranges. When start_line is present, start_side is required and must be "LEFT" or "RIGHT".
  • side must be "LEFT" or "RIGHT".

Body Requirements

The top-level body must include:

  • A high-level overview of the spec PR.
  • Concerns about completeness, clarity, feasibility, or issue alignment.
  • Issue counts in the format Found: X critical, Y important, Z suggestions.
  • A final recommendation of Approve, Approve with nits, or Request changes. This recommendation must match the top-level verdict field (Approve / Approve with nits → "APPROVE"; Request changes → "REJECT").

Final Checks

Before finishing:

  • Fix invalid JSON if validation fails.
  • Confirm line numbers match the annotated diff.
  • Run the validator bundled with the shared review-pr skill against the exact annotated diff you reviewed. If common skills are installed at the repository root, this is usually:
    python3 .agents/skills/review-pr/scripts/validate_review_json.py --review-json review.json --diff pr_diff.txt
    If the script reports any invalid comments, fix review.json and rerun it. Do not upload review.json until this validator passes. If the script path is not present at that exact location, locate validate_review_json.py under the packaged shared review-pr skill directory and run that copy with the same arguments.
  • Do not run gh pr review, gh pr comment, gh api, or any other command that posts to GitHub.

Your only output is the final review.json.

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.