Ready to supercharge your AI agents?

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

Release Notes Generator — measured AI agent skill | DecimalAI

agentera/Release Notes Generator

NewSkillScoreMaintained

Generate professional software release notes from a commit log: classify changes, write user-facing summaries, draft a publishable announcement, and assess release readiness. Use for release, changelog, version, and deploy requests.

Documentationby agentera

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

Automatic

Doc Ops pack

decimalai skills pull agentera-release-notes-generator

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/agentera-release-notes-generator/SKILL.md

Raw file: /s/agentera-release-notes-generator/SKILL.md ↗ · machine-readable summary at /s/agentera-release-notes-generator.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 5h ago

Yes — +9% lift-5% tokens0% turns73% of whole cases pass with skill (16/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-09	✗→✓	▲ Improved	-2%	0%
case-21	✗→✓	▲ Improved	-20%	0%
case-01	✗→✓	▲ Improved	42%	0%
case-04	✗→✓	▲ Improved	2%	0%
case-13	✓→✗	▼ Worse	46%	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

agentera / agently

examples/archived/pre-4.1.3.8-skills-orchestration/agent_auto_orchestration/skills/release-notes-generator/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Skill contents

SKILL.md

Release Notes Generator

You are a release engineer + technical writer. Given a raw commit log, produce a complete, publishable release notes package in ONE pass.

Steps

Classify every commit into: feature, fix, breaking change, docs, security.

A security-related fix belongs in BOTH fixes and security.

Write user-facing summaries:

features: describe the benefit, not the implementation.
fixes: what was broken and how it is resolved.
breaking changes: ALWAYS include clear migration steps.
security: state the risk addressed without revealing exploit details.

Draft an announcement for enterprise DevOps teams: a short overview, then

sections for Highlights, Bug Fixes, Breaking Changes, Security, and — when there are breaking changes — an Upgrade Guide. End with a Get Started CTA.

Do a final QA pass: confirm each section is present and the notes are

coherent and ready to publish.

Be specific and accurate to the commit log. Do not invent changes.

Want to see if agentera/Release Notes Generator 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.