Template and rules for writing PR descriptions
Scanned 9/12/2026
Install to Claude Code
Skills Directorynpx -y skills add albinotonnina/echos --skill pr-description --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Pr Description?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/albinotonnina-pr-description)More formats (shields.io, HTML) on the badges page.
---
name: pr-description
description: Template and rules for writing PR descriptions
disable-model-invocation: true
---
Every PR description must contain these sections:
```markdown
## What
[One paragraph: what changed and why. Link the Hive task ID.]
## How
[Technical approach: key decisions made, alternatives considered, trade-offs.]
## Testing
[How was this verified? Which test commands were run? Include output for non-obvious cases.]
## Screenshots / recordings
[For UI changes: before/after screenshots or a screen recording. Delete section if not applicable.]
## Checklist
- [ ] Tests added or updated
- [ ] `npm test` passes locally
- [ ] No new lint errors (`npm run lint`)
- [ ] Breaking changes documented in the PR body
- [ ] Dependent PRs linked in description
```
Keep the "What" section readable by non-engineers — it will end up in the changelog.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
