agentsclimarketplace

Pr review summarizer

Skill sisodiabhumca/agent-skills/skills/pr-review-summarizer

Production-Ready Agent Skills : product analytics, growth experiments, CRM, research synthesis, postmortems, data contracts, SaaS spend, compliance, architecture maps, and LLM eval and many more.

Install
npx -y skills add sisodiabhumca/agent-skills --skill pr-review-summarizer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when reviewing a code pull request or merge request. Reads a unified diff (or fetches one from GitHub/GitLab) and produces a structured review — risk-ranked summary, files changed, hotspots, suggested test coverage, and reviewer questions. Vendor-neutral; works with any AI agent runtime that can run shell commands.

SKILL.md

1.6 KB, 315 tokens by cl100k_base, as published. Nobody here has run it

PR Review Summarizer

When to invoke

  • "Summarize this PR for me before I review."
  • "What's the risk in this diff?"
  • "Generate reviewer questions for PR #482."

Inputs needed

  1. Diff source — local unified diff file, GitHub PR URL, or GitLab MR URL.
  2. Context (optional) — service name, runtime, test framework.

Workflow

  1. Fetch / read the diff.
  2. Classify changes: code, tests, docs, config, dependencies.
  3. Score risk per file using heuristics: lines changed, security-sensitive paths, lack of tests, schema changes.
  4. Summarize intent in plain language.
  5. Produce a review brief: TL;DR, risk hotspots, missing test coverage, suggested questions.

Output format

## TL;DR
## Risk hotspots (ranked)
## Files changed (summary)
## Missing test coverage
## Reviewer questions
## Suggested follow-ups

Guardrails

  • Never approve or merge — the skill produces a review, not a verdict.
  • Flag schema, auth, crypto, and migration changes as High by default.
  • Cite exact file + line numbers from the diff for every risk claim.

Reference code

review.py reads a unified diff file or fetches via gh pr diff / glab mr diff and produces the brief.

Gives 0 of the 12 instructions most test skills give in 315 tokens

Counted across 964 of the 1,571 authors here whose files we hold, read 2026-08-06

  • close the browser when donein 55 of 964, across 12 files
  • wait for network idle statein 51 of 964, across 6 files
  • launch chromium in headless modein 49 of 964, across 6 files
  • use descriptive selectors for elementsin 49 of 964, across 6 files
  • run provided scripts with help flag firstin 49 of 964, across 6 files
  • add appropriate explicit waitsin 48 of 964, across 5 files
  • use bundled scripts as black boxesin 46 of 964, across 3 files
  • do not read script source codein 46 of 964, across 3 files
  • use sync playwright for scriptsin 46 of 964, across 3 files
  • inspect dom before executing actionsin 46 of 964, across 3 files
  • run the full test suitein 36 of 964, across 34 files
  • write the failing test firstin 25 of 964, across 18 files

Said here and by no other author read

  • classify changes by type
  • score risk per file using heuristics
  • summarize intent in plain language
  • flag schema, auth, crypto, and migration changes as high
  • cite exact file and line numbers for every risk claim

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.