agentleFS
Sign inStart free
martincjarvismartincjarvis/development-skills/skills/structured-review-workflow/SKILL.md

structured-review-workflow

Skill4 starsChanged 10 months agoMITView on GitHub

Use this skill when you need an end-to-end review workflow that coordinates both requesting and receiving feedback.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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 you need the full review loop (request + receive).

    line 17
  2. Distinctive:

    When multiple review personas are involved.

    line 18
  3. Distinctive:

    When review scope or expectations are ambiguous.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Structured Review Workflow

Intent

Coordinate review activities by composing the request and response skills so feedback is handled consistently and evidence remains the source of truth.

When to Use

  • When you need the full review loop (request + receive).
  • When multiple review personas are involved.
  • When review scope or expectations are ambiguous.

Precondition Failure Signal

  • Review is requested without evidence.
  • Feedback is implemented without verification or clarification.
  • Scope grows beyond the original task.

Postcondition Success Signal

  • Review request includes summary, evidence, and focus areas.
  • Feedback is handled item-by-item with verification evidence.
  • The review loop closes with explicit reviewer notification.

Process

  1. Request: Apply requesting-code-review.
  2. Receive: Apply receiving-code-review.
  3. Close: Re-run verification and notify reviewers.
  4. Review: Tech Lead validates process adherence.

Example Test / Validation

  • Request: "Please review feat-X. Tests pass (logs attached). Focus on the migration in V1__init.sql."
  • Response: "Applied null check in UserService.cs. Keeping list as-is because [technical reason]."

Common Red Flags / Guardrail Violations

  • Skipping requesting-code-review or receiving-code-review.
  • Ignoring reviewer comments without justification.
  • Expanding scope to appease subjective feedback.

Recommended Review Personas

  • Tech Lead – validates process integrity and technical outcomes.
  • Software Engineer – validates peer-level clarity and maintainability.

Skill Priority

P2 – Consistency & Governance

Conflict Resolution Rules

  • Postcondition Success Signals from applied skills are the objective truth in any review conflict.
  • Escalate to the Skill Priority Model (P0-P4) if reviewers disagree on priorities.

Conceptual Dependencies

  • requesting-code-review
  • receiving-code-review
  • superpowers:verification-before-completion

Classification

Governance Core

Notes

Reviews are about the code, not the person. Use the defined skills as the common language for feedback.

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