agentleFS
VercelKnown publishervercel-labs/eve-content-agent-template/agent/skills/release-notes-style/SKILL.md

release-notes-style

Skill28 starsChanged 21 days agoApache-2.0View on GitHub

Use when drafting or editing release notes or a changelog entry in the house voice.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When writing or editing release notes:

    line 7
  2. Distinctive:

    No marketing adjectives. A changelog is a record, not a pitch.

    line 20
  3. Very specific:

    Every shipped version gets an entry, newest first, dated YYYY-MM-DD.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Release notes voice & style

When writing or editing release notes:

  • Lead with what changed for the user, in their words — not the internal feature name. Say "you can now…", not "we added…".
  • Group by what the reader does, not by team or component. Keep the same section names every release so readers learn to scan it.
  • Each entry: what changed, why it matters, and (if relevant) what to do about it. Front-load the benefit in the first sentence and keep the entry to a sentence or two.
  • Plain present tense: "You can now…", "Fixed an issue where…". Describe a fix from the symptom the reader saw, not the code path. Skip jargon the reader wouldn't know.
  • Link to docs or a deeper post instead of explaining everything inline. Keep the entry scannable.
  • Be honest about breaking changes — call them out first, with the migration steps and a timeline if there is one. Deprecate a feature for a release cycle before you remove it.
  • No marketing adjectives. A changelog is a record, not a pitch.
  • Every shipped version gets an entry, newest first, dated YYYY-MM-DD. Don't paste the commit log — it's noise, not a record.

Structure

Group entries under clear headings in this order:

  1. Breaking changes — what to do, up front (covers Changed/Deprecated/Removed/Security that affect upgrades; name the migration path).
  2. New — capabilities the reader didn't have before (Added).
  3. Improved — things that already worked, now better (Changed).
  4. Fixed — bugs resolved, described from the symptom the user saw (Fixed).

These map onto the Keep a Changelog category set (Added, Changed, Deprecated, Removed, Fixed, Security). Use only the headings that have entries, and reach for the standard names rather than inventing "Tweaks" or "Misc". See references/format-specs.md.

References

  • references/best-practices.md — sourced checklist of current release-notes conventions (user-benefit framing, entry anatomy, grouping, breaking changes, linking).
  • references/format-specs.md — quick-lookup conventions: the Keep a Changelog category set, SemVer mapping, entry-anatomy template, and ordering/dating norms.
  • references/banned-words.json — the list of words to avoid. Read it once up front for awareness, then run the lint_against_style tool on your draft to check it against this file before proposing the draft to the writer.

Shared references

Shared global references for all skills in the content agent. These apply regardless of the content type.

  • references/ai-phrases-to-avoid.md — AI-tell words, phrases, and punctuation to avoid.
  • references/plain-english-alternatives.md — plain-English swaps for bloated or vague wording.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.