Ready to supercharge your AI agents?

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

Get Started Free →

Changelog from Diff — measured AI agent skill | DecimalAI

archive228/changelog-from-diff

NewSkillScoreMaintained

Turn a set of commits or a diff into a clean, user-facing changelog entry. Use before a release or PR description.

Documentationby archive228

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

Automatic

Doc Ops pack

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

pip install decimalai

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

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

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

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

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

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

Yes — +27% lift+8% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-13	✗→✓	▲ Improved	-12%	0%
case-03	✗→✓	▲ Improved	-9%	0%
case-05	✗→✓	▲ Improved	52%	0%
case-14	✗→✓	▲ Improved	-6%	0%
case-18	✗→✓	▲ Improved	-7%	0%

Showing 5 of 22 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/changelog-from-diff/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Changelog from Diff

Read the actual diff/commits, not the commit messages (they lie). Group into: Added · Changed · Fixed · Removed · Security (skip empty groups). Each line: user-facing impact, not implementation. "Fixed login failing for emails with uppercase characters" — not "fixed bug in user lookup".

Lead with what the user notices. Bury internals.
Call out breaking changes loudly, with the migration step.
Link the PR/issue. No marketing fluff.

Output: markdown ready to paste. If a change has no user impact, leave it out.

Want to see if archive228/changelog-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.