mcpField
S
spec-loop-assess-pull-request

spec-loop-assess-pull-request

github.com/dpolivaevTesting & quality3550 installsUpdated 2w ago
Repository

About spec-loop-assess-pull-request

A Spec Loop skill for reviewing pull requests, merge requests, branch diffs, and commit ranges in repositories the user trusts. It reconstructs the implemented work as a retrospective review artifact, then adds assessment and recommendations.

Key features

  1. 01Trust checks before fetching repository content
  2. 02Read-only evidence collection with gh or glab
  3. 03Retrospective Spec Loop review artifact
  4. 04AI assessment and recommendations

Use cases

  1. 01Reviewing a trusted pull request
  2. 02Assessing a merge request or branch diff
  3. 03Evaluating a repository commit range

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/dpolivaev/spec-loop --skill spec-loop-assess-pull-request

After installing, type/spec-loop-assess-pull-requestin Claude Code to confirm it loaded.

Bundled filesexamples/example-review-settings-loader.mdreview-guidance.md

Details

From the project README

Use this skill only for pull requests, merge requests, branch diffs, or commit ranges from repositories the user trusts. This skill is optional and is not required for the core Spec Loop planning workflow. If trust is unclear, stop and ask before fetching provider or Git content.

Follow review-guidance.md for trust handling, evidence collection, review structure, diagram rules, and sharing-variant behavior.

Before work:

Reconstruct already-implemented work as the retrospective Spec Loop review artifact that should have existed, then add AI assessment and recommendations. Do not treat the change as waiting at the normal PLAN -> EXECUTION gate.

Use read-only provider commands for evidence when available:

  • gh for GitHub
  • glab for GitLab, including self-hosted GitLab when available

When trust, provider, evidence source, or comparison range is unclear, stop and ask.

Comments

Markdown supported