Changelog logo

Changelog

Organization
ratel-ai
changelog

Update per-package CHANGELOG.md files for a Ratel release. Drafts entries with git-cliff (scoped per package), lets you curate, then writes the CHANGELOGs. Handles both RC entries and GA-graduation collapse (merging X.Y.Z-rc.* sections into a single X.Y.Z section). Invoke before tagging a release.

Overview

Publisherratel-ai
Repositoryratel
Skill namechangelog
Stars
503
Forks
30
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ratel-ai on GitHub. Read the source before you install it.

Installation

Install the Changelog AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ratel-ai/ratel/tree/main/.claude/skills/changelog
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ratel-ai/ratel.git /tmp/ratel
mkdir -p .claude/skills
cp -r /tmp/ratel/.claude/skills/changelog .claude/skills/changelog
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Changelog in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Changelog on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Changelog is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/changelog

Updates a release unit's CHANGELOG.md in preparation for tagging it. Ratel releases per unit (ADR-0008): each unit ships on its own tag (<prefix>-v*) at its own version. For workflow-wired units, .github/workflows/release.yml rejects a tag whose unit CHANGELOG doesn't contain the version being released. vercel-ai-sdk is temporarily published manually via scripts/publish-rc.sh; still run this skill before its tag even though the workflow gate does not cover it yet.

Run it once per unit you're releasing.

Release units it touches

The units and their manifests/CHANGELOGs live in one registry — scripts/release-units.mjs — which every release tool reads. Run node scripts/release-units.mjs --list for the authoritative set; the current ten units are:

UnitRegistryCHANGELOG path
coreratel-ai-core (crates.io)src/core/CHANGELOG.md
sdk-ts@ratel-ai/sdk (npm)src/sdk/ts/CHANGELOG.md
sdk-pyratel-ai (PyPI)src/sdk/python/CHANGELOG.md
telemetry-coreratel-ai-telemetry (crates.io)src/telemetry/core/CHANGELOG.md
telemetry-ts@ratel-ai/telemetry (npm)src/telemetry/ts/CHANGELOG.md
telemetry-pyratel-ai-telemetry (PyPI)src/telemetry/python/CHANGELOG.md
vercel-ai-sdk@ratel-ai/vercel-ai-sdk (npm)src/adapters/ts-vercel-ai-sdk/CHANGELOG.md
mastra@ratel-ai/mastra (npm)src/adapters/ts-mastra/CHANGELOG.md
rankers-ts@ratel-ai/rankers-plugin (npm)src/rankers/ts/CHANGELOG.md
rankers-pyratel-ai-rankers-plugin (PyPI)src/rankers/python/CHANGELOG.md

@ratel-ai/mcp-server lives in ratel-ai/ratel-mcp and maintains its own CHANGELOG there.

Procedure

1. Pick the unit and read its version

If the user hasn't named the unit, run node scripts/releasable.mjs — it lists which units have commits since their last release tag. Pick the unit $UNIT being released.

Read its canonical version:

bash
node scripts/release-units.mjs --version "$UNIT"   # -> $TARGET

If the user supplies a different version explicitly, prefer that and warn them the working tree disagrees.

2. Determine the diff range

The range is from the unit's own last release tag to HEAD:

bash
prefix=$(node scripts/release-units.mjs --tag-prefix "$UNIT")
FROM=$(git describe --tags --match "${prefix}*" --abbrev=0 2>/dev/null || true)

If $FROM is empty the unit has never shipped; the whole history is in range.

3. Generate the draft

bash
bash .claude/skills/changelog/draft.sh --unit "$UNIT"

It emits a single ### <package-name> block for the unit, containing either Keep-a-Changelog sections (### Added, ### Fixed, ### Changed) or the sentinel _No user-facing changes._. (Omit --unit to draft every unit at once.) With no <from-ref> argument the script ranges each unit from its own last tag automatically.

If draft.sh exits 127, git-cliff is missing. Tell the user how to install it (the script's stderr already does), and stop.

4. Branch on RC vs GA

Inspect $TARGET, and edit only this unit's CHANGELOG:

  • RC (X.Y.Z-rc.N): prepend a new section above the most recent versioned section:

    ## [X.Y.Z-rc.N] - YYYY-MM-DD
    
    <draft content for the unit, or the sentinel>

    Use today's date in YYYY-MM-DD (UTC).

  • GA (no -rc suffix): enter GA-collapse mode:

    1. Find every ## [X.Y.Z-rc.*] section already present that matches the same MAJOR.MINOR.PATCH as $TARGET.
    2. Union their bullet entries (per subsection: ### Added, ### Changed, ### Fixed) with the new draft entries from step 3 (commits since the last RC tag).
    3. Deduplicate bullets within each subsection (case-insensitive, whitespace-normalised).
    4. Drop the _No user-facing changes._ sentinel if any real entries exist; keep it only if the unioned set is empty.
    5. Replace all the matched RC sections with a single ## [X.Y.Z] - YYYY-MM-DD section containing the merged content.
    6. Leave non-matching prior versions (e.g. ## [0.1.4]) untouched.

5. Curate with the user

Show the unit's CHANGELOG pending changes in the conversation. Ask the user to confirm or edit. Common curation moves:

  • Rephrase bullets for user-facing clarity (the draft uses commit subjects verbatim).
  • Drop bullets that are not user-visible (internal refactors that slipped past cliff.toml's skip rules).
  • Merge duplicates that survived deduplication.
  • Promote / demote between Added / Changed / Fixed if the commit prefix was wrong.

6. Write the file

Once approved, write only this unit's CHANGELOG using the Edit tool. Do not commit. The release commit is the user's responsibility — they typically include the CHANGELOG alongside the version bump in a single release: <unit>-vX.Y.Z commit.

If releasing more than one unit, repeat from step 1 for each.

7. Remind

Tell the user:

  • The CHANGELOG is staged in the working tree (unstaged).
  • Next step is the release commit + <unit>-v<version> tag + push.
  • For workflow-wired units, the release.yml tag-version-check job verifies the unit's CHANGELOG contains the tag version; if it doesn't, the release is blocked.
  • For vercel-ai-sdk, publish manually with scripts/publish-rc.sh after the tag push; its CHANGELOG is not workflow-gated yet.

Conventions

  • Date format: YYYY-MM-DD in UTC.
  • Subsection order: ### Added, ### Changed, ### Fixed, ### Removed, ### Deprecated, ### Security. Omit empty subsections.
  • Sentinel: _No user-facing changes._ for a unit with no in-scope commits.
  • Keep ## [Unreleased] at the top — it stays empty between releases.

Why this exists

ADR 0008 (docs/adr/0008-release-engineering.md) records the per-unit tag/version split, the CHANGELOG mechanism, and the rationale. Read it if you're unsure why something is structured the way it is.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Changelog AI skill do?

Update per-package CHANGELOG.md files for a Ratel release. Drafts entries with git-cliff (scoped per package), lets you curate, then writes the CHANGELOGs. Handles both RC entries and GA-graduation collapse (merging X.Y.Z-rc.* sections into a single X.Y.Z section). Invoke before tagging a release.

Why use Changelog on TypingMind?

Because you install it once and use it with any model. Changelog is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Changelog in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ratel-ai/ratel/tree/main/.claude/skills/changelog. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Changelog?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Changelog?

As many as you like. As long as a model supports skills, you can use Changelog with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Changelog AI skill free?

Yes. It is published on GitHub by ratel-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇