Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

PR from Diff — measured AI agent skill | DecimalAI

archive228/pr-from-diff

NewSkillScoreMaintained

Write a PR description a reviewer can approve fast. Use when opening any pull request.

Code Reviewby archive228

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/archive228-pr-from-diff/SKILL.md

decimalai skills pull archive228-pr-from-diff --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/archive228-pr-from-diff/SKILL.md https://app.decimal.ai/s/archive228-pr-from-diff/SKILL.md

Raw file: /s/archive228-pr-from-diff/SKILL.md ↗ · machine-readable summary at /s/archive228-pr-from-diff.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

25 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 6h ago

Yes — +40% lift-9% tokens0% turns88% of whole cases pass with skill (22/25)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-09	✗→✓	▲ Improved	-20%	0%
case-01	✗→✓	▲ Improved	-16%	0%
case-02	✗→✓	▲ Improved	-27%	0%
case-07	✗→✓	▲ Improved	-23%	0%
case-14	✗→✓	▲ Improved	-20%	0%

Showing 5 of 25 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

archive228 / loopkit

skills/pr-from-diff/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

PR from Diff

A reviewer should understand the change without reading every line. Structure:

What & why — the problem and the approach, 2-3 sentences.
Changes — bullet the meaningful ones (skip noise like formatting).
How to verify — the exact steps/commands the reviewer runs to confirm it works.
Risks / out of scope — what could break, what you deliberately didn't do.
Screenshots for UI.

Flag any decision the reviewer should weigh in on. Keep the PR small — if the diff is huge, say what could be split out. No "fixes stuff".

Want to see if archive228/pr-from-diff would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.