Reviewing PR Description
SkillDev toolsreviewing-pr-description is a skill that lets an AI agent evaluate a pull request's title and description for readability. It checks whether they clearly and concisely convey what changed and why to a reviewer, and returns findings with concrete proposed rewrites. The caller decides whether to apply the suggestions or present them as feedback.
Available today. Use it from your connected AI after setup.
No other account needed.
Have gh available so the skill can fetch the PR's title and description with gh pr view.
Then ask your AI: use the Reviewing PR Description skill
What your AI can do with it
- Fetches a PR's title and description using gh pr view
- Flags buried leads, unexplained jargon, passive voice, and redundant bullets
- Returns issues paired with concrete rewritten wording
- Reports suggestions only; applying them is left to the caller
Getting started
- Have gh available so the skill can fetch the PR's title and description with gh pr view.
- Add the reviewing-pr-description skill to your agent's available skills.
- Invoke it when finalizing a PR or reviewing PR metadata, and decide whether to apply the suggested rewrites or share them as feedback.
What this skill tells your AI
The instructions your AI receives, as published by streamlit/streamlit in .claude/skills/reviewing-pr-description/SKILL.md and read by ahel’s review.
Review a PR's title and description for readability: do they clearly and concisely tell a reviewer what changed and why? Focus on the prose — checking the format (title pattern, required template sections) is a secondary, lighter concern.
This skill only evaluates: it produces findings with concrete proposed rewrites and does not apply them. The caller decides whether to apply the rewrites or present them as feedback.
Audience
The reader is a reviewer or teammate skimming the PR to understand what changed and why. They may not know the implementation context, and later readers will find this text via the commit log or changelog. The title and description should stand on their own.
Principles
- Lead with the change and its purpose — the first sentence should state what changed and why, not setup, process, or a description of the problem area.
- Explain intent, not mechanics — say what the change enables or why it was made; don't narrate the diff step by step.
- Cut what the diff already shows — omit routine, obvious changes (added tests, updated types, fixed lint). Call out only what's non-obvious or decision-worthy.
- Concise wins — fewer, denser bullets beat many thin ones. If a bullet restates the title or another bullet, drop it.
- Explain non-obvious decisions — deprecations, unit choices, fallback behavior, and trade-offs deserve a sentence on why.
- Avoid jargon without context — spell out internal terms or acronyms a newcomer wouldn't know.
- Active voice; name the actor — "Deprecates
use_container_width" or "The server now rejects oversized uploads" reads more directly than passive or vague phrasing. - The title stands alone — it should convey the change on its own in a commit list or changelog, without the body.
- No meta-commentary — cut "This PR...", "We have...", "I added..."; state what changed directly.
Evaluation Process
- Gather the PR title and description (
gh pr view <n> --json title,body). - For each, ask:
- Does the title convey the change on its own, or does it need the body to make sense?
- Does the description lead with the main change and its purpose, or bury it under context/mechanics?
- Does it explain why for non-obvious decisions, or only list what?
- Is there jargon or an acronym a newcomer wouldn't understand?
- Could it be shorter — are there obvious or duplicated points to cut?
- Is it in passive or vague voice where naming the actor would read more directly?
- Is there meta-commentary that adds no information?
- Also confirm the format briefly (secondary): title matches
[type] Descriptionwithin ~63 chars, and the required template sections from.github/pull_request_template.mdare present. For the full standards, seecreating-pull-requestsandwiki/pull-requests.md. - Report the findings per the Output Format below.
Common Patterns to Flag
- A title that only makes sense alongside the body (e.g. "[fix] Fix the bug")
- A description that opens with context or process instead of the change itself
- Bullets that restate the diff (added tests, updated types) instead of explaining intent
- Non-obvious decisions (deprecations, fallbacks, unit choices) stated without the why
- Internal jargon or acronyms with no expansion
- Passive or actor-less phrasing where naming the actor reads more directly
- Meta-commentary ("This PR...", "I added...") that could be cut
- More bullets than the change warrants, or bullets that duplicate each other
Output Format
For the title and for the description, give the issue and a concrete proposed rewrite.
Signals
- GitHub stars
- 46k
- Forks
- 4k
- Last commit
- Sep 2026
Questions
- Does the skill apply the rewrites itself?
- No. It only reports suggestions with concrete rewritten wording; applying them or presenting them as feedback is left to the caller.
- When should the skill be used?
- When finalizing a PR or reviewing PR metadata, that is, checking whether a PR's title and description clearly convey what changed and why.
- What kinds of problems does it look for?
- Buried leads, unexplained jargon, passive voice, and redundant bullets in the PR title or description.
- Does it review the code in the PR?
- No. It evaluates only the PR's title and description for readability, not the code changes.
Advanced
- Item type
- skill
- Key
reviewing-pr-description- Source
- github.com/streamlit/streamlit