agentleFS
krishnamallamkrishnamallam/upbox/.claude/skills/pr-review/SKILL.md

pr-review

Skill2 starsChanged 6 months agoMITView on GitHub

Review code changes or a pull request. Delegates to specialist agents for code quality, security, performance, and documentation, in parallel.

195 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use clack-cli-patterns, drag-to-reorder and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • openchamberSkill

    clack-cli-patterns

    Use when creating or modifying OpenChamber CLI commands, prompts, terminal output, non-TTY behavior, `--quiet`, or `--json` behavior.

    Also in 3 projects that use this

  • openchamberSkill

    drag-to-reorder

    Use when implementing or modifying OpenChamber sortable or drag-to-reorder behavior, especially `@dnd-kit`, touch/mobile interactions, variable-width items, or wrapping layouts.

    Also in 3 projects that use this

  • jtenniswoodSkill

    expert-reset

    Reimagine this repository from first principles using the current product and user experience as the target. Use when the user says "/expert-reset", asks how the project should be rebuilt if starting again, wants bold architecture or component-structure recommendations, or wants a research-only reset plan unconstrained by current implementation details.

    Also in 3 projects that use this

  • CES-LtdSkill

    oss-pr

    Use when creating a pull request, after committing changes, or when user invokes /oss-pr. Covers branch management, quality checks, commit, push, and PR creation.

    Also in 3 projects that use this

  • CES-LtdSkill

    pr-automation

    PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs. Use when: (1) Invoked by daemon via scripts/pr-automation.sh, (2) User says "/pr-automation".

    Also in 3 projects that use this

  • +7 more from openchamber

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 180 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check $ARGUMENTS for the word verbose.

    line 12
  2. Very specific:

    When dispatching reviewers in Step 3, include the word verbose in each Task call's prompt only if the user asked for it.

    line 17
  3. Distinctive:

    If there are no changes to review, say so and stop.

    line 28
  4. Distinctive:

    When reviewing a PR, fetch and check:

    line 34
  5. Very specific:

    If only one reviewer applies (a pure-docs diff, for example), a single Task call is fine.

    line 61
  6. Very specific:

    Use the terse template by default.

    line 67
  7. Distinctive:

    If no findings, output a single line: "No issues found across [agents]."

    line 96

“Common” is measured: kept by at least 6 in 10 of the 180 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

Review code changes by delegating to specialist agents in parallel and synthesizing a unified report. Works with PRs, staged changes, or specific files.

Verbosity

Check $ARGUMENTS for the word verbose. Strip it from the argument string before parsing the rest.

  • Default: terse output. Each finding is one line (file:line: issue (fix: hint)). Synthesis report stays compact.
  • verbose: full breakdown. Each finding gets the multi-field block (Severity, Confidence, etc.). Synthesis report uses the full template.

When dispatching reviewers in Step 3, include the word verbose in each Task call's prompt only if the user asked for it. Otherwise omit; the reviewers default to terse.

Step 1: Determine Scope

Parse $ARGUMENTS to determine what to review:

  • PR number (e.g., 123 or #123): fetch with gh pr view $ARGUMENTS. This is the full PR review path (includes PR quality checks in Step 2).
  • No argument: try gh pr view to detect a PR for the current branch. If a PR exists, use it. If not, fall back to git diff --cached (staged), then git diff (unstaged).
  • staged: review git diff --cached. If nothing staged, fall back to git diff.
  • File path: review that specific file's current state.

If there are no changes to review, say so and stop.

Step 2: PR Quality Check (PR path only)

Skip this step if reviewing staged changes or a file. Jump to Step 3.

When reviewing a PR, fetch and check:

  • PR title, description/body, author, base branch, head branch
  • gh pr diff $NUMBER for the full diff
  • gh pr checks $NUMBER for CI status
  • gh api repos/{owner}/{repo}/pulls/$NUMBER/comments for review comments

Review the PR itself before the code:

  • Title: descriptive and under 72 chars?
  • Description: explains the why? Includes a test plan? Flag if empty or template-only.
  • Size: count changed files and lines. Flag if >500 lines changed (suggest splitting).
  • Base branch: targeting the right branch?
  • CI status: passing, failing, or pending? If failing, note which checks. Fix CI first.
  • Unresolved comments: list open review threads with file:line and comment text.

Step 3: Code Review (fan out to specialists in parallel)

Decide which reviewers apply by reading the diff content, not just file paths:

ReviewerWhen to include
code-reviewerAlways. Universal correctness pass.
security-reviewerAuth, input handling, queries, tokens, session management, file path construction, SQL or HTML or template strings.
performance-reviewerEndpoints, DB queries, loops over collections, caching, connection management. Skip for pure-docs, config-only, or static-asset diffs.
doc-reviewer.md changes, significant docstring or JSDoc changes, API docs.

Dispatch all applicable reviewers in PARALLEL. Send one message that contains one Task tool call per applicable reviewer (use subagent_type matching the reviewer name). Do NOT invoke them sequentially. Parallel dispatch cuts wall-clock time from N times the slowest review to roughly the slowest single review, with no extra token cost.

If only one reviewer applies (a pure-docs diff, for example), a single Task call is fine. Skip the parallel pattern when there's nothing to parallelize.

While the reviewers run, you can read the PR description, recent CI logs, or open comments to enrich the synthesis in Step 4. Don't wait idly.

Step 4: Synthesize Report

Use the terse template by default. Use the verbose template only if the user passed verbose.

Default (terse)

For PR reviews:

## PR Review: #[number]: [title]

[base] -> [head]. [N files, +X/-Y lines]. CI: [pass | fail: <checks>]. PR quality: [ok | issues: <list>].

### Findings ([N])
- [agent] file:line: issue (fix: hint)
- [agent] file:line: issue (fix: hint)

### Verdict
[Ready to merge | Needs changes: <one-line blocker>]

For non-PR reviews (staged or file):

## Review ([scope])

[N findings from <agents>]:
- [agent] file:line: issue (fix: hint)
- [agent] file:line: issue (fix: hint)

If no findings, output a single line: "No issues found across [agents]."

Verbose (when the user passed verbose)

For PR reviews:

## PR Review: #[number]: [title]

**Author**: [author] | **Base**: [base] -> **Head**: [head] | **Changed**: [N files, +X/-Y lines]

### PR Quality
- Title: [ok / needs improvement]
- Description: [ok / missing test plan / empty]
- Size: [ok / large, consider splitting]
- CI: [passing / failing, list failures]
- Unresolved comments: [none / list]

### Code Review
#### Critical / High
- [Agent] File:Line: issue

#### Medium
- [Agent] File:Line: issue

#### Low
- [Agent] File:Line: issue

### Verdict
[Ready to merge / Needs changes, summarize blockers]

For non-PR reviews (staged or file):

## Review Summary

**Scope**: [staged changes / file path]
**Agents run**: [list]

### Critical / High
- [Agent] File:Line: issue

### Medium / Low
- [Agent] File:Line: issue

### Passed
- [areas with no issues]

Either way: deduplicate findings that overlap between agents. Attribute each finding to the agent that found it.

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.