agentleFS
petekppetekp/claude-code-setup/skills/release-notes/SKILL.md

release-notes

Skill48 starsChanged 51 days agoMITView on GitHub

Write release notes or a changelog entry that tell existing users what they will notice after updating, with the technical detail after it. Use when publishing a release, writing a changelog, or editing release notes.

  • Commits and pushes

176 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brainstorm-experiments-existing, brainstorm-ideas-new and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • skytiger6724Skill

    brainstorm-experiments-existing

    Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, and other low-effort validation methods. Use when validating assumptions, testing feature ideas cheaply, or planning product experiments.

    Also in 6 projects that use this

  • skytiger6724Skill

    brainstorm-ideas-new

    Brainstorm feature ideas for a new product in initial discovery from PM, Designer, and Engineer perspectives. Use when starting product discovery for a new product, exploring features for a startup idea, or doing initial ideation.

    Also in 6 projects that use this

  • 45ckSkill

    pestle-analysis

    Also in 6 projects that use this

  • About-IntelligenceSkill

    positioning-ideas

    Brainstorm product positioning ideas differentiated from competitors.

    Also in 6 projects that use this

  • About-IntelligenceSkill

    product-name

    Brainstorm 5 unique, memorable product names with rationale aligned to brand values and target audience.

    Also in 6 projects that use this

  • +7 more from skytiger6724

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 162 edited versions we read keep these.

  • 6

    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:

    Read a change's diff when its commit subject doesn't make the user's experience clear.

    line 13
  2. Distinctive:

    A picture of the headline change: when it is visible. Reuse the before-and-after image from the PR that made the change when there is one.

    line 21
  3. Distinctive:

    Also: Every other change a user can notice, one bullet each, grouped under a bold heading per app or platform, with "Every app" first.

    line 23
  4. Distinctive:

    When nothing in a release is visible, say so in the first line, and keep only Update and Under the hood.

    line 27
  5. Distinctive:

    Not text to copy:

    line 43
  6. Distinctive:

    Follow the project's release doc for when and how to publish.

    line 76

“Common” is measured: kept by at least 6 in 10 of the 162 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

Release notes

Write for someone who already uses the product. They want to know what will feel different after they update, and whether they have to do anything. Most read the first line and stop. Some scan the highlights. Few read further. Notes they can scan in seconds beat complete notes they skip.

Gather

  • List the changes since the last release, such as with git log --oneline <last tag>..HEAD. Read the PRs and issues they reference.
  • Read a change's diff when its commit subject doesn't make the user's experience clear. Describe only effects you can trace to a change.
  • Find the project's update steps and the apps or platforms it ships to. Look in its release doc, its README, and the last release's notes.

Shape

In this order:

  1. One bold line on the effect users will notice most. Name the effect, not the area: "Other mods' notes come back above your prompt", not "Fixes for the band".
  2. A picture of the headline change when it is visible. Reuse the before-and-after image from the PR that made the change when there is one.
  3. Highlights. Three to five bullets: the changes most users will run into. Each starts with a bold label of a few words, then one short sentence.
  4. Also. Every other change a user can notice, one bullet each, grouped under a bold heading per app or platform, with "Every app" first. Leave out a group with no changes.
  5. Update. The project's update steps, as the last release gave them, changed only where this release changes them.
  6. Under the hood, inside <details><summary>Under the hood</summary>, so it starts closed. One line per change that a technical user or contributor would want to know: the mechanism behind a change above, a fix with no visible effect, a changed file format or API. Link the issue or PR when there is one, and thank the person who reported it. Work that does not ship in the product, such as a video, a plan, or a refactor with no effect, stays out.

When nothing in a release is visible, say so in the first line, and keep only Update and Under the hood.

Each item

  • One line, one change. Say what the user sees or does now. Add how it was before only when they could not recognize the change without it.
  • Leave out a change nobody acts on or notices, or move it under the hood.
  • Put anything the user must do inside the item it belongs to, such as "reopen the tab once". A step that applies to the whole release goes in Update.
  • Use the names users see on screen: button labels, tab names, and messages, quoted exactly. Name the place in plain words, such as "the terminal" or "the Codex tab". Code names and the project's own terms for its parts belong under the hood.
  • Order items by how often users run into them. A change everyone sees comes before an edge case. A removed feature or a change that breaks a workflow goes in Highlights, with what to do instead.

Check

Before publishing, give only the notes to a reader with no other context. Ask what they will notice after updating and whether they must do anything. Rewrite when either answer is wrong. When you have no way to hand the notes to a separate reader, skip this step and say so in your handoff.

Example

Not text to copy:

**Other mods' notes come back above your prompt, and commands only you can run now copy to your clipboard.**

## Highlights

- **Other mods' notes show again.** The band above the prompt shows the inbox's line, then other mods' notes under it.
- **Your commands copy.** A step the agent can't run, such as one on a phone plugged into your computer, copies its command when you press it.

## Also

**Codex**

- Updates stop breaking the Inbox tab. After this update, quit and reopen the ChatGPT app once.

## Update

- **Claude Code:** run `claude plugin marketplace update inbox`, then `claude plugin update inbox`, then `/reload-plugins` in any session that's already open.
- **Codex:** run `codex plugin marketplace upgrade`, then `codex plugin add inbox@inbox`.

<details>
<summary>Under the hood</summary>

- The band keeps what later mods draw in it (#4, reported by @fahadjibransheikh).
- A command the agent asks you to run is marked as a terminal step, so it copies instead of going to the agent.
- Codex deletes a plugin's old folder when it updates. The Codex server now loads the newest installed version after that, instead of failing with a module error.

</details>

Publishing

Follow the project's release doc for when and how to publish. Writing the notes does not authorize publishing them. Publish with gh release create <tag> --notes-file <file> or gh release edit <tag> --notes-file <file>, then re-read the published body with gh release view <tag> --json body.

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.