agentleFS
Sign inStart free
r3bl-orgr3bl-org/r3bl-open-core/.agents/skills/review-pr/SKILL.md

review-pr

Skill486 starsChanged 15 days agoApache-2.0View on GitHub

Create a structured integration and review plan for a Pull Request

We split this skill into the rules it gives an agent

9 rules. 0 are common, 3 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Use this skill when the user runs the /review-pr <number> slash command or uses any of these natural language triggers:

    line 8
  2. Distinctive:

    When triggered, you MUST follow these exact steps:

    line 17
  3. Very specific:

    Run gh pr view <number> to read the PR description.

    line 20
  4. Very specific:

    Run gh pr diff <number> to see the exact code changes and files touched.

    line 21
  5. Very specific:

    Create a new markdown task file at task/pr-<number>-fix.md with exact Rust struct/trait definitions and target file paths.

    line 23
  6. Very specific:

    Run antigravity-ide task/pr-<number>-fix.md to open the file for the user.

    line 28
  7. Distinctive:

    Ask the user to manually review and explicitly approve the plan before any implementation begins.

    line 29
  8. Very specific:

    When creating task/pr-<number>-fix.md, structure it exactly like this:

    line 37
  9. Distinctive:

    Do NOT merge or apply the PR automatically.

    line 102

“Common” is measured: kept by at least 6 in 10 of the 178 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

PR Review and Integration Workflow

Use this skill when the user runs the /review-pr <number> slash command or uses any of these natural language triggers:

  • "lets review pr <number>"
  • "lets work on pr <number>"
  • "lets take a look at pr <number>"

Workflow

When triggered, you MUST follow these exact steps:

  1. Information Gathering
    • Run gh pr view <number> to read the PR description.
    • Run gh pr diff <number> to see the exact code changes and files touched.
  2. Task File Generation (No Source Code Edits)
    • Create a new markdown task file at task/pr-<number>-fix.md with exact Rust struct/trait definitions and target file paths.
    • The file MUST follow the template structure below, organizing the PR into distinct, actionable chunks (phases/headings).
  3. Format, Present & Execute
    • Automatically run prettier --write task/pr-<number>-fix.md to format the new file.
    • Run antigravity-ide task/pr-<number>-fix.md to open the file for the user.
    • Ask the user to manually review and explicitly approve the plan before any implementation begins.
    • Once approved, execute each phase (in a clean or /compact-ed thread) and verify with ./check.fish --check (cargo check -q --message-format=short).

Task File Template

Canonical Example: See task/done/pr-455-fix.md for a complete, canonical example of a well-written PR review task file.

When creating task/pr-<number>-fix.md, structure it exactly like this:

_Task: PR <number> Integration (<short description>)_

# User Story & Context

## Problem

[Describe the user-facing problem that this PR is attempting to solve. What triggers the
bug?]

## Root Cause

[Describe the underlying technical root cause. Why is this happening in the codebase?]

## Expected Behavior

[Describe what the expected behavior should be after the fix.]

# Overview

[Brief summary of the PR, author, and what problem it solves.]

# Implementation Plan

We will process each of the action items iteratively using the following loop:

1. **Implementation:** Write the specific code changes for the current heading.
2. **Local Testing:** Run `./check.fish --check` and, where applicable, test
   functionality.
3. **Mandatory Manual Review:** You (the user) will manually review the specifically
   touched files before the heading is marked as checked `[x]`.

_(Once all headings are successfully implemented and checked off, we will proceed to final
verification and cleanup.)_

## Phase 1: [Name of first distinct fix/feature]

[Brief context of the problem and the specific fix.]

- _Context:_ [Why this change is needed.]
- _The Fix:_ [What the code actually does.]
- _File(s) Touched:_ [List the files.]

## Phase 2: [Name of next fix/feature...]

...

## Final Verification & Cleanup

- [ ] Verify full test suite coverage using `./check.fish --full`.
- [ ] When ready to merge, invoke the `/merge-pr` slash command to push the changes,
      optionally update the author, and cleanly merge to `main`.
- [ ] Update the current meta-task (e.g. `task/prepare-vX.Y.Z-meta-task.md`) to check off
      PR #<number>.
- [ ] **Mandatory manual review:** Verify every file modified in this task for correct
      implementation and ensure no regressions.
  - [ ] `path/to/modified_file_1.rs`
  - [ ] `path/to/modified_file_2.rs`
  - [ ] `task/prepare-vX.Y.Z-meta-task.md`

Critical Rules

  • Do NOT merge or apply the PR automatically. The purpose of this workflow is to rewrite or cherry-pick the fixes systematically while validating them against the current main branch.
  • Break down the PR diff into logical, self-contained action items rather than just one giant block.

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