agentleFS
amplifthqamplifthq/openmeld/.agents/skills/openmeld-changelog/SKILL.md

openmeld-changelog

Skill1.4k starsChanged 6 days agoMITView on GitHub

Maintain the official OpenMeld Changelog from repository evidence. Use when deciding whether a change needs a Changelog entry, writing or publishing an entry, preparing release notes, validating generated Changelog files, or historically backfilling missing changes.

1 other project uses a version of this.

Trending

More talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 24 mentionsNov 2026: 7 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the amplifthq/openmeld repository that our weekly crawl found. There is no adoption data for this file yet.

Most recently taken up by

Who's talking about amplifthq/openmeld

The biggest 5 of 31 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 31

Talked about on GitHub (31 times).

On GitHub · 31

26 more on GitHub

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep changelog/entries/*.md as the human- and agent-authored source of truth.

    line 8
  2. Very specific:

    Treat CHANGELOG.md, changelog/index.json, and changelog/releases/*.md as generated projections.

    line 9
  3. Very specific:

    Publish a change: add publishedAt, optional release, and concrete evidence only after the delivery claim is proven.

    line 18
  4. Distinctive:

    Use the coding agent's native file, Git, GitHub, test, and search tools.

    line 29
  5. Very specific:

    Use a unique lowercase slug for both the filename and id.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

OpenMeld Changelog

Keep changelog/entries/*.md as the human- and agent-authored source of truth. Treat CHANGELOG.md, changelog/index.json, and changelog/releases/*.md as generated projections. Read developing/engineering/changelog.md before editing either source or projections.

Choose the job

  • Record a change: inspect the implementation and add one concise draft entry when users or contributors gain, lose, or materially experience a capability.
  • Publish a change: add publishedAt, optional release, and concrete evidence only after the delivery claim is proven.
  • Backfill history: reconstruct an omitted entry from tags, commits, pull requests, tests, deployment records, or other durable evidence. Use the original availability date, not today's date.
  • Prepare release notes: publish the applicable entries, rebuild the projections, and hand the generated release file to the authorized release workflow. A notes file is not release authorization.

Gather evidence

Use the coding agent's native file, Git, GitHub, test, and search tools. No custom Changelog command is required for investigation or writing.

Establish these facts separately:

  1. what behavior changed;
  2. who can notice or use it;
  3. which code, pull request, or commit contains it;
  4. whether it was merged;
  5. whether the relevant component was delivered; and
  6. whether any required real-user smoke produced the visible outcome.

Merge, tag, deployment, and smoke are different claims. Keep an entry draft when the evidence proves only an earlier claim.

Decide whether to record it

Record changes that affect users, operators, integrators, or contributors:

  • new or removed capabilities;
  • material workflow or behavior improvements;
  • user-visible fixes and security changes;
  • breaking behavior and deprecations; or
  • developer-facing changes that alter supported integration or contribution work.

Skip internal refactors, test-only changes, routine dependency maintenance, and documentation cleanup when they do not change an external workflow. Combine several implementation commits into one user-meaningful entry when they deliver one outcome.

Write the entry

Use a unique lowercase slug for both the filename and id. Write native-level English for OpenMeld's North American audience. Lead with what is now possible or what changed, not implementation details.

---
id: slack-channel-invitations
title: Invite teammates from Slack
kind: new
areas: ["channels", "center-agent"]
audiences: ["admins"]
---

Organization admins can invite a teammate while working with the Center Agent
in Slack, without switching to a separate setup flow.

That entry is a draft. Publish it only after delivery is proven:

publishedAt: 2026-08-17
release: v0.3.60
evidence: ["pr:72", "commit:1d5254d", "workflow:123456789"]

release is optional for continuously delivered changes. Every published entry requires durable evidence. Keep uncertain historical work as a draft rather than inventing a date, scope, or release.

Rebuild and verify

Run:

pnpm changelog:build
pnpm changelog:check

Review the resulting diff. A complete change has valid source entries, up-to-date deterministic projections, and no unsupported publication claim.

For a historical backfill, also confirm that adding the older entry placed it by publishedAt rather than by the date of the backfill commit.

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.