review-pr

Files (2)

• SKILL.md
• advanced.md

SKILL.md (first lines)

# Interactive PR Review — NVIDIA-NeMo/RL

Review a pull request or local branch interactively, applying the project's coding guidelines.

## Parse Arguments

- If `$ARGUMENTS` contains a number → **PR mode** with that PR number
- If `$ARGUMENTS` is empty or has no number → **LOCAL mode** (review current branch vs main)
- If `$ARGUMENTS` contains `update` → **UPDATE** mode (PR mode only)
- If `$ARGUMENTS` contains `--deep` → use parallel subagents for deeper review

**Repo**: `NVIDIA-NeMo/RL`

**Examples:**
- `/review-pr 123` — review PR #123, single agent
- `/review-pr 123 --deep` — review PR #123 with parallel subagents
- `/review-pr 123 update` — follow up on existing threads for PR #123
- `/review-pr` — review current branch vs main, terminal output only

---

## Phase 1: Setup

### PR mode
```bash
git fetch origin pull/$PRNUM/head:pr-$PRNUM-review
git checkout pr-$PRNUM-review
```

### LOCAL mode
Already on the correct branch. Determine the merge base:
```bash
git merge-base main HEAD
```

---

## Phase 2: Gather Context

### PR mode — parallel MCP fetches

All with `owner=NVIDIA-NeMo`, `repo=RL`, `pullNumber=$PRNUM`:

1. `mcp__github__pull_request_read` method=`get` → PR title, description, author, base branch, labels, head SHA
2. `mcp__github__pull_request_read` method=`get_diff` → full diff
3. `mcp__github__pull_request_read` method=`get_files` → list of changed files
4. `mcp__github__pull_request_read` method=`get_review_comments` → existing review threads
5. `mcp__github__pull_request_read` method=`get_reviews` → existing reviews
6. `mcp__github__pull_request_read` method=`get_comments` → general PR comments

### LOCAL mode — git diff

```bash
git diff $(git merge-base main HEAD)..HEAD
git diff $(git merge-base main HEAD)..HEAD --name-only
```

No MCP calls needed.

### Both modes — local reads

7. Read `CLAUDE.md` from repo root for review philosophy
8. Read all `.claude/skills/*/SKILL.md` files (except `review-pr`) for guideline rules
9. Glob `.claude/review-memory/*.md` — if any exist, read them for learned patterns

---

## Phase 3: Analyze

### Single-agent mode (default)

Analyze all changes yourself. Return a list of candidate issues — each with file, line, category, and description. Do NOT score them yet; scoring happens in the validation step (Phase 3b).

### Deep mode (`--deep`) — parallel subagents

Launch 3 opus subagents in parallel using the `Agent` tool. Provide each with the diff, PR description (if PR mode), and the guideline skills content. Each returns a list of candidate issues (file, line, category, description). Do NOT ask them to score — scoring happens in Phase 3b.

**Subagent 1 — Guideline compliance:**
Review the diff against all guideline skills (code-style, config-conventions, error-handling, testing, copyright, docs). For each violation, return the file, line, description, and which skill it violates.

**Subagent 2 — Bug scan (diff only):**
Scan for obvious bugs in the diff without reading surrounding context. Flag syntax errors, type errors, clear logic errors, missing imports, unresolved references.

**Subagent 3 — Contextual bug scan:**
Read surrounding code and git history for each changed file. Look for bugs that only become apparent with context: incorrect API usage (especially megatron-bridge, megatron-lm, automodel, gym), race conditions, broken assumptions.

After all subagents return: merge results and deduplicate (same file+line+issue = one finding). Then proceed to Phase 3b.

### Analysis rules (all modes)

#### NEW mode
- Analyze the diff against all guideline skills
- For each changed file, read surrounding context locally using `Read` and `Grep` to understand the change in context
- Cross-reference existing review comments (PR mode only, from step 4) to avoid duplicating points already raised by other reviewers
- Also apply any patterns from review memory files
- Categorize findings:
  - **[BUG]** — Logic errors, null refs, race conditions, syntax errors
  - **[TEST]** — Missing or insufficient test coverage
  - **[GUIDELINE]** — Violations of coding guidelines from skills
  - **[DOC]** — Outdated or missing documentation

#### UPDATE mode (PR mode only)
- Review all unresolved review threads on the PR
- For each thread, determine if action is needed:
  1. **We disagree with the response** → draft a comment like "We can resolve this thread because XYZ"
  2. **The author asked a question** or made a comment that needs a response → draft an answer
- CAN also create new comments if you notice something warranted while reviewing threads
- Skip threads that are resolved or where no response is needed

---

## Phase 3b: Validate & Score

For each candidate issue from Phase 3, launch a **separate opus validation subagent** using the `Agent` tool. Launch these in parallel (batch all at once).

Each validation subagent receives:
- The candidate issue (file, line, category, description)
- The relevant code context (the diff hunk + surrounding lines)
- The PR title and description (if PR mode)

From sajadn/diffusion_RL, Apache-2.0.

More from sajadn/diffusion_RL