Pr Description
Write GitHub Pull Request descriptions from branch commits. Use when user asks to write a PR description, create a PR summary, or document changes for a pull request. Analyzes git commits and diffs to produce structured PR documentation.
Install
$ agentstack add skill-lucianghinda-agentic-skills-pr-description ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-lucianghinda-agentic-skills-pr-description) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
PR Description Writer
Generate structured PR descriptions from branch commits.
Workflow
- Get commits:
git log --oneline origin/main..HEAD(fallback toHEAD~10..HEAD) - Get each commit's details:
git show --stat --format="%H%n%s%n%b" - Get each commit's diff:
git diff ^.. - Write PR description following the output format below
Output Format
1. Title
Single line. Use most meaningful commit subject or synthesize one. Keep short and technical.
2. Summary (2-5 bullets)
High-level changes. Each bullet concrete and verifiable.
3. Why (1-4 bullets)
Motivation, problem, or user impact. Tie to reliability, security, performance, DX, or product needs.
4. Commit-by-commit details
For EACH commit, add subsection with exact subject as heading:
What: 1-3 bullets describing concrete changes
Why: 1-2 bullets explaining motivation/tradeoffs
Notes: (optional) only for risk, migration, follow-up, or nuance
Rules:
- Preserve commit subject exactly as written
- If commit has a meaningful description use that
- If commit is noisy (formatting, rename), say so briefly
- Related commits: document each, keep later ones shorter ("follow-up", "fixup")
5. Testing
Checklist of what was done. If none provided, infer likely checks and label "Suggested".
6. Risk and rollout (2-6 bullets)
- What could break
- Where to watch
- Rollback plan (1 line)
- If breaking change, include BREAKING CHANGE callout
7. Screenshots/logs (optional)
Only if UI, behavior, or observability changed.
Style
- Direct and technical. No marketing tone.
- No fluff or jokes.
- Short sentences. Prefer bullets over paragraphs.
- Do not invent facts. Say "Likely" or "Inferred" if uncertain.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: lucianghinda
- Source: lucianghinda/agentic-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.