agentleFS
Sign inStart free
MarioJamesMarioJames/skill-foundry/skills/changelog-writing/SKILL.md

changelog-writing

Skill1 starsChanged 5 days agoApache-2.0View on GitHub

根据发布证据撰写或审查面向用户、工程团队的更新说明；用于编写变更日志、发布说明和工程交接，支持发布流程所需的结构化输出。

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use audience-routes.md for filtering and audience-specific checks.

    line 12
  2. Distinctive:

    Use supplied notes, a concrete Git/PR range, or release evidence.

    line 20

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Changelog Writing

Audience and language

Choose the audience before drafting. Production defaults to customer-facing; beta, RC, and nightly default to technical/internal. Follow the user's requested language, then the established release channel, then the conversation language.

Use audience-routes.md for filtering and audience-specific checks. Include only sections that help the reader. If both audiences need artifacts, keep internal evidence separate from public copy.

Output

For people, write the requested prose or Markdown. For a release workflow or explicitly requested machine format, use workflow-output.md, which defines the existing three-field JSON contract. Do not force JSON on an ordinary request to write update notes.

Source material

Use supplied notes, a concrete Git/PR range, or release evidence. When Git collection is needed, resolve this skill directory and run:

bun <skill-dir>/scripts/collect-commits.ts --from <previous-tag> --to HEAD

The collector also supports --range v1.0.0..HEAD, --auto-beta --to HEAD, and --auto-production --to HEAD. Treat collected commits as evidence; group by meaningful outcome instead of pasting raw lists into customer copy.

Include upgrade actions, compatibility changes, and known risks when relevant. Do not invent a version, source range, verification result, or user impact. Keep credentials, private URLs, hostnames, and internal incident identifiers out of public artifacts.

Publication tasks

Writing release notes does not authorize publication. When the request also publishes a release, read release-closure.md for tag verification and already-authorized follow-through. A git-only submission does not need release metadata.

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.

Check your setup, free