Product Changelog logo

Product Changelog

Organization
inference-sh
product-changelog

Product changelog and release notes that users actually read. Covers categorization, user-facing language, visuals, and distribution. Use for: release notes, changelogs, product updates, feature announcements, versioning. Triggers: changelog, release notes, product update, version notes, what's new, feature announcement, product changelog, update log, release announcement, version release, product release, ship notes

Overview

Publisherinference-sh
Repositoryskills
Skill nameproduct-changelog
Stars
790
Forks
106
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by inference-sh on GitHub. Read the source before you install it.

Installation

Install the Product 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/inference-sh/skills/tree/main/guides/product/product-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/inference-sh/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/guides/product/product-changelog .claude/skills/product-changelog
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Product 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 Product 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 Product 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.

Install the belt CLI skill: npx skills add belt-sh/cli

Product Changelog

Write changelogs and release notes that users read and care about via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions

bash
belt login

# Generate a feature announcement visual
belt app run falai/flux-dev-lora --input '{
  "prompt": "clean product UI screenshot mockup, modern dashboard interface showing a new analytics chart feature, light mode, minimal design, professional SaaS product",
  "width": 1248,
  "height": 832
}'

Entry Format

The Anatomy of a Good Entry

markdown
### New: Bulk Export for Reports 📊

You can now export up to 10,000 rows at once from any report view.
Select your rows, click Export, and choose CSV or Excel format.

Previously limited to 500 rows per export.

![Bulk export button in the reports toolbar](screenshot.png)

Structure: Category label -> User-facing title -> What you can do now -> How -> What changed -> Visual

User-Facing Language

❌ Internal language:
"Implemented batch processing queue for the export service"
"Refactored the ReportExporter class to support pagination"
"Fixed bug in CSV serialization (PR #4521)"

✅ User-facing language:
"You can now export up to 10,000 rows at once from any report"
"Reports now load 3x faster when filtering large datasets"
"Fixed an issue where exported CSV files had missing columns"

Rules:

  • Write what the user can DO, not what you BUILT
  • Start with "You can now..." / "Reports now..." / "Fixed an issue where..."
  • Include the benefit, not just the mechanism
  • Use present tense

Categories

Standard Categories

CategoryColorIconUse For
NewGreen✨ or 🆕Entirely new features or capabilities
ImprovedBlue⚡ or 🔧Enhancements to existing features
FixedYellow/Orange🐛 or 🔨Bug fixes
RemovedRed🗑️ or ⚠️Deprecated or removed features
SecurityPurple🔒Security patches

Categorization Rules

  • New = something users couldn't do before at all
  • Improved = something users could do, now it's better/faster/easier
  • Fixed = something that was broken, now works correctly
  • Don't use "Updated" — it's meaningless. Was it improved or fixed?

Version Numbering

Semantic Versioning (SemVer)

MAJOR.MINOR.PATCH
  3   .  2  .  1
ComponentIncrement WhenExample
MAJORBreaking changes, major redesign2.0.0 -> 3.0.0
MINORNew features, backward-compatible3.1.0 -> 3.2.0
PATCHBug fixes, small improvements3.2.0 -> 3.2.1

Date-Based Versioning

2026-02-08  or  2026.02.08  or  February 8, 2026

Best for SaaS products with continuous deployment.

Changelog Page Structure

markdown
# Changelog

## February 8, 2026

### New
- **Bulk Export for Reports** — Export up to 10,000 rows at once. [Learn more →](link)
- **Dark Mode** — Toggle dark mode from Settings > Appearance.

### Improved
- **Dashboard Loading** — Dashboards now load 3x faster on large datasets.
- **Search** — Search results now include archived items.

### Fixed
- Fixed an issue where exported CSV files had missing column headers.
- Fixed a bug where the date picker showed incorrect timezone.

---

## February 1, 2026

### New
- **API Webhooks** — Get notified when events happen in your account.

### Fixed
- Fixed an issue where email notifications were delayed by up to 2 hours.

Visual Changelogs

When to Add Visuals

Change TypeVisual
New UI featureScreenshot of the new feature
UI redesignBefore/after comparison
New workflowStep-by-step screenshots or short video
Performance improvementChart showing improvement
Complex featureAnimated GIF or video demo

Generating Visuals

bash
# Feature screenshot (if you have the app running, use agent browser)
belt app run infsh/agent-browser --input '{
  "url": "https://your-app.com/new-feature",
  "action": "screenshot"
}'

# Before/after comparison
belt app run infsh/stitch-images --input '{
  "images": ["before-screenshot.png", "after-screenshot.png"],
  "direction": "horizontal"
}'

# Annotated screenshot with callout
belt app run bytedance/seededit-3-0-i2i --input '{
  "prompt": "add a red circle highlight around the export button in the top right area",
  "image": "screenshot.png"
}'

# Feature announcement banner
belt app run falai/flux-dev-lora --input '{
  "prompt": "clean modern product announcement banner, gradient blue to purple background, abstract geometric shapes, professional SaaS aesthetic, wide format",
  "width": 1248,
  "height": 832
}'

Breaking Changes

Breaking changes need special treatment:

markdown
### ⚠️ Breaking: API v2 Endpoints Deprecated

**What changed:** API v1 endpoints will stop working on March 15, 2026.

**What you need to do:**
1. Update your API calls to use v2 endpoints ([migration guide →](link))
2. Update authentication to use Bearer tokens instead of API keys
3. Test your integration before March 15

**Timeline:**
- Now: v2 endpoints available, v1 still works
- March 1: v1 returns deprecation warnings
- March 15: v1 stops working

If you need help migrating, contact support@company.com.

Distribution Channels

ChannelFormatWhen
Changelog pageFull detail, all entriesEvery release
In-app notification1-2 line summaryNew features, breaking changes
EmailCurated highlights, visualsMajor releases (monthly/quarterly)
Blog postDeep dive with contextBig launches
Social mediaSingle feature highlightNotable features
Slack/DiscordBrief announcementIf you have a community

Social Media Snippet Format

🆕 New in [Product]: [Feature Name]

[1-2 sentence description of what you can now do]

[Screenshot or demo video]

Try it now → [link]

Writing Tips

Do

  • Group related changes together
  • Lead with the biggest/most requested change
  • Link to documentation for complex features
  • Include who requested it ("By popular request:")
  • Show migration paths for breaking changes
  • Date every entry

Don't

  • Don't say "various bug fixes" — list specific fixes or skip them
  • Don't include internal references (PR numbers, ticket IDs, branch names)
  • Don't use "Updated [feature]" without saying how
  • Don't list changes nobody cares about (dependency bumps, internal refactors)
  • Don't commit-dump — one changelog entry may represent many commits

Changelog Frequency

Product TypeFrequencyNotes
SaaS (continuous deploy)Weekly batchGroup a week of changes
SaaS (major features)Per feature launchWith blog post
Versioned softwarePer version releaseTied to semver
APIPer version + deprecation noticesInclude migration guides
Mobile appPer app store releaseMatch store listing "What's New"

Common Mistakes

MistakeProblemFix
Developer languageUsers don't understandWrite what users can do
"Bug fixes and improvements"Zero informationList specific fixes
No datesCan't tell what's newDate every entry
No visualsUsers skip textScreenshot major features
Breaking changes buriedUsers discover too lateProminent warning + timeline
Commit log as changelogNoisy, unhelpfulCurate and rewrite

Related Skills

bash
npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@prompt-engineering

Browse all apps: belt app list

Frequently asked questions

What does the Product Changelog AI skill do?

Product changelog and release notes that users actually read. Covers categorization, user-facing language, visuals, and distribution. Use for: release notes, changelogs, product updates, feature announcements, versioning. Triggers: changelog, release notes, product update, version notes, what's new, feature announcement, product changelog, update log, release announcement, version release, product release, ship notes

Why use Product Changelog on TypingMind?

Because you install it once and use it with any model. Product 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 Product Changelog in TypingMind?

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

Which AI models can use Product 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 Product Changelog?

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

Is the Product Changelog AI skill free?

It is published on GitHub by inference-sh. Check the repository for licensing terms. 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 👇