pr-writing
Skill1 starsChanged 42 days agoMITView on GitHub
Drafts pull request and merge request descriptions from the actual diff, commits, templates, and tickets, with verification steps, risk, and rollout notes for any review platform. Use when preparing a PR, MR, or code-review description.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- Hambaobao/hambaobao-skillstheir own version, first seen Nov 1, 2026
- microsoft/dynwinrttheir own version, first seen Nov 1, 2026
- timharris707/skillstheir own version, first seen Oct 13, 2026
- gustavovalverde/skillstheir own version, first seen Oct 6, 2026
- Jannchie/skillstheir own version, first seen Aug 1, 2026
- jarosser06/drifttheir own version, first seen Dec 9, 2025
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- microsoft/dynwinrt★ 64same name
- timharris707/skills★ 44same name
- gustavovalverde/skills★ 8same name
- Hambaobao/hambaobao-skills★ 2same name
- Jannchie/skills★ 1same name
- jarosser06/drift★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 42
Add a Mermaid diagram only for state transitions, architecture, data flow, or multi-step interactions that prose can't carry.
“Common” is measured: kept by at least 6 in 10 of the 5 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.
Files
Pull Request Writing
Help a reviewer see what changed, why, how to verify it, and what risk remains.
Inspect first, ask last
Read the branch, base branch (don't assume main), commits, diff, PR template, contribution guide, CI, scripts, migrations, config, and linked metadata. Draft from verified evidence in one pass, then list only material gaps (ticket, deployment step, private link, screenshot) under Needs confirmation; in automated runs, proceed with labeled assumptions. Never invent tickets, test results, screenshots, metrics, approvals, deployment steps, or completed work.
Reference order: repo template and guidance → repo conventions → ticket from branch, commits, metadata, or user (Jira, Linear, GitHub Issues, YouTrack, Azure Boards, or plain links—don't assume URL formats) → neutral default. Works for GitHub, GitLab, Bitbucket, Azure DevOps, and others.
Draft
Group changes by user-visible behavior, implementation, data/API impact, and operations. Separate facts, inferences, and open questions. Match the repo's language and template; otherwise:
## Summary
## Why this change
## What changed
## How to verify
## Risks and follow-up
## Deployment, migration, or rollback notes
## Related ticket or external context
## Screenshots or recordingsOmit empty sections. List automated checks with the real command and result. Verification by change type:
- Bug fix: reproduce the original issue → previous result → verify the fix → regression checks.
- Feature: prerequisites → acceptance scenarios → expected outcomes → edge cases.
- UI: routes/screens, responsive and interaction states, accessibility, visual evidence.
- API/backend: inputs, outputs, authorization, validation, errors, persistence, compatibility.
- Mobile: device/OS prerequisites, flow, permissions, offline, platform differences.
- Infra/deploy: environment setup, migrations, health checks, observability, rollback.
Neutral shape when nothing better exists: ### Preconditions, ### Scenarios (Given / When / Then; label the first one as the original-issue repro for bug fixes), ### Edge cases and regression checks, ### Evidence. Never claim a scenario ran without evidence.
Add a Mermaid diagram only for state transitions, architecture, data flow, or multi-step interactions that prose can't carry.
Check before returning
Ticket and external links, test commands, migration order, feature flags, security and privacy impact, accessibility, performance, API contracts, rollback. No secrets or customer data. Return the description first, then Needs confirmation (only if needed) and the evidence used.
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
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.