Review Research PR

Automated diff-scoped research PR review using parallel audit subagents aligned to research quality dimensions. Posts inline GitHub review comments and submits a summary verdict. Use after a research PR is opened to gate on review approval.

5 stars 1 forksGit & Code Review

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add TalonT-Org/AutoSkillit --skill review-research-pr
Manual install
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit.git /tmp/AutoSkillit
mkdir -p ~/.claude/skills
cp -r /tmp/AutoSkillit/src/autoskillit/skills_extended/review-research-pr ~/.claude/skills/review-research-pr

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Review Research PR Skill

Perform an automated, diff-scoped code review on an open GitHub research PR using parallel
audit subagents tuned to research quality dimensions. Posts inline review comments and submits
a summary verdict. Called by the recipe pipeline after `open_research_pr` opens the PR.

## Arguments

`/autoskillit:review-research-pr <worktree-path-or-feature-branch> <base-branch>`

- **worktree-path-or-feature-branch** — Either an absolute path to the research worktree
  (preferred; skill derives the feature branch from `git rev-parse --abbrev-ref HEAD`)
  or the feature branch name directly
- **base-branch** — The base branch the PR targets (e.g., "main")

## When to Use

- Called by the recipe orchestrator via `run_skill` after `open_research_pr`
- Can be invoked standalone to review any open research PR

## Critical Constraints

**NEVER:**
- Create files outside `{{AUTOSKILLIT_TEMP}}/review-research-pr/`
- Approve a PR that has `changes_requested` findings
- Post review comments when `gh` is unavailable — output `verdict=approved` and exit 0
- Review files outside the PR diff — scope all audit to diff content only
- Modify any source code
- Flag the absence of a clear experimental conclusion as a deficiency — inconclusive
  results are valid outcomes for research PRs (do not flag them)
- Run subagents in the background (`run_in_background: true` is prohibited)

**ALWAYS:**
- Find the PR by feature branch at invocation time (not from a pre-captured URL)
Read the full skill on GitHub

Details

Skill name
review-research-pr
Path
src/autoskillit/skills_extended/review-research-pr/SKILL.md
License
MIT
Repo updated
8 November 2026

FAQ

What does the Review Research PR skill do?

Automated diff-scoped research PR review using parallel audit subagents aligned to research quality dimensions. Posts inline GitHub review comments and submits a summary verdict. Use after a research PR is opened to gate on review approval.

How do I install the Review Research PR skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add TalonT-Org/AutoSkillit --skill review-research-pr. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Review Research PR popular?

It lives in TalonT-Org/AutoSkillit, which has 5 GitHub stars and 1 forks.

Related skills

Browse the most popular Claude skills, all git & code review skills, or write your own with the skills generator.