Install
$ agentstack add skill-lichamnesia-awesome-antigravity-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.
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
Produce a PR description a busy reviewer can act on in under a minute.
When to use this skill
- The user asks to open a PR or "write the PR description".
- A branch is ready and needs a summary before review.
How to use it
- Collect the real change surface — never write from memory:
``bash git log main..HEAD --oneline git diff main...HEAD --stat ``
- Structure the description:
- What — 1-2 sentences: the user-visible outcome, not the mechanics.
- Why — the problem or ticket this solves; link issues.
- How — only the non-obvious decisions (tricky trade-offs, rejected alternatives). Skip a file-by-file tour; the diff already shows it.
- Testing — what was actually run (commands + result), not what "should" pass.
- Risk / rollback — what could break and how to revert.
- Call out anything a reviewer must look at extra carefully (migrations, auth changes, deletions).
Decision tree
- Diff > ~800 lines → open with a "review order" hint (which files to read first).
- Pure dependency bump → compress to What + changelog link + test evidence.
- Breaking API change → put a BREAKING banner at the top with the migration step.
Done means
The description answers what/why/testing without the reviewer opening the diff, and every claim in "Testing" corresponds to a command that was actually executed.
Part of awesome-antigravity-skills. Browse more Agent Skills at orangebot.ai/skills.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: LichAmnesia
- Source: LichAmnesia/awesome-antigravity-skills
- License: CC0-1.0
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.