Diff Marketing logo

Diff Marketing

Community
Illyism
diff-marketing

Generate customer-focused marketing content from recent git changes, commits, merged pull requests, and shipped features. Use when the user invokes /diff-marketing or /marketing, or asks for blog posts, tweets, changelogs, or emails about what shipped.

Overview

PublisherIllyism
Repositoryseo-skills
Skill namediff-marketing
Stars
584
Forks
60
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 Illyism on GitHub. Read the source before you install it.

Installation

Install the Diff Marketing 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/Illyism/seo-skills/tree/main/marketing/diff-marketing
  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/Illyism/seo-skills.git /tmp/seo-skills
mkdir -p .claude/skills
cp -r /tmp/seo-skills/marketing/diff-marketing .claude/skills/diff-marketing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Diff Marketing 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 Diff Marketing 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 Diff Marketing 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.

Diff marketing

Generate content suggestions from recent code changes, commits, merged pull requests, and shipped features.

Process

  1. Analyze recent changes:

    • Look at the git log for the past week: git log --since="1 week ago" --pretty=format:"%h - %s (%an, %ar)"
    • Check merged pull requests and their descriptions.
    • Review modified files and their purpose.
    • Identify new features, bug fixes, improvements, and refactors.
  2. Categorize changes by impact:

    • High impact: new features, major improvements, breaking changes.
    • Medium impact: enhancements, notable bug fixes, performance improvements.
    • Low impact: minor fixes, refactors, dependency updates.
  3. Read relevant files to understand the user-facing change before writing.

  4. Generate specific content suggestions with drafts, prioritizing user value, SEO opportunities, and useful distribution channels.

Content suggestions by type

Blog posts

For high-impact changes:

  • Focus on features that solve user problems.
  • Include the problem, solution, benefits, screenshots or demos, and code examples when useful.
  • Use an educational, in-depth, SEO-optimized angle.
  • Aim for 800–2,000 words.
  • Possible angles:
    • "Introducing [Feature]: How We Built..."
    • "How [Feature] Helps You..."
    • "Behind the Scenes: Building [Feature]"

Tweets and social media

Use all impact levels for:

  • Launch posts that explain the benefit and include a visual.
  • Threads that break down complex features.
  • Tip posts with a quick, useful takeaway.
  • Behind-the-scenes posts about decisions and tradeoffs.

Keep the tone conversational, concise, and specific. Include emojis, hashtags, mentions, links, and visuals when they add value. Treat a meaningful release as a launch opportunity and suggest a way to gather early feedback.

Changelog updates

  • Structure entries as ## [Version] - [Date].
  • Use Added, Changed, Fixed, Deprecated, Removed, and Security categories as applicable.
  • Write in user-facing language.
  • Link to documentation or blog posts for major features.
  • Keep the writing technical but accessible.

Email updates

For medium- and high-impact changes, suggest newsletters, feature announcements, or onboarding updates.

  • Include a hero image, brief introduction, feature highlights, and CTA when appropriate.
  • Use a personal, benefit-focused, actionable tone.

Press releases

Suggest these only for major launches, milestones, partnerships, or funding. Include a headline, summary, quotes, boilerplate, and contact details. Use a professional, newsworthy, quotable tone.

Documentation

Suggest updates to:

  • Getting-started guides.
  • Feature documentation.
  • API references.
  • Code examples and use cases.
  • Troubleshooting sections.

Video content

For high-impact changes, suggest demos, tutorial walkthroughs, release overviews, or development diaries.

Content strategy

  1. Repurpose a blog post into a thread, newsletter, and documentation update.
  2. Coordinate content with the release.
  3. Lead with user benefits.
  4. Show the product with screenshots, GIFs, or videos.
  5. Include keywords, meta descriptions, and alt text where relevant.
  6. Give every piece a clear next step.
  7. Cross-link related content.
  8. Suggest how to collect feedback and measure response.

Output format

Use this structure:

markdown
## Week of [Date Range]

### Summary

[High-level overview of what shipped]

### High impact changes

- [Change 1]: [Description]
- [Change 2]: [Description]

### Medium impact changes

- [Change]: [Description]

### Low impact changes

- [Change]: [Description]

### Content suggestions

#### Blog posts

1. **"[Title]"**: [Brief description, key points, and target audience]
2. **"[Title]"**: [Brief description, key points, and target audience]

#### Tweets and threads

1. Launch post: [Draft text with emojis when appropriate]
2. Thread idea: [Topic and key points]
3. Tip: [Quick value post]

#### Changelog entry

## [Version] - [Date]

### Added

- [Feature]: [User-facing description]

### Fixed

- [Bug]: [What was fixed]

#### Email subject lines

- "[Compelling subject line option 1]"
- "[Compelling subject line option 2]"

#### Video ideas

- "[Video concept and key points to cover]"

#### Documentation updates needed

- [ ] Update [doc page] with [new information]
- [ ] Add [new guide] for [feature]

Writing standards

  • Use customer-centric messaging.
  • Say what shipped and what it does. Do not invent metrics, customer results, or product behavior.
  • Use diff output and relevant source files to ground every claim.
  • Prefer plain language over hype.
  • Avoid generic launch copy, unsupported superlatives, and vague claims.
  • Use sentence-case headings and varied, natural prose.
  • Keep emojis functional and sparse.
  • End with the most useful next action for the reader.

Frequently asked questions

What does the Diff Marketing AI skill do?

Generate customer-focused marketing content from recent git changes, commits, merged pull requests, and shipped features. Use when the user invokes /diff-marketing or /marketing, or asks for blog posts, tweets, changelogs, or emails about what shipped.

Why use Diff Marketing on TypingMind?

Because you install it once and use it with any model. Diff Marketing 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 Diff Marketing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Illyism/seo-skills/tree/main/marketing/diff-marketing. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Diff Marketing?

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 Diff Marketing?

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

Is the Diff Marketing AI skill free?

It is published on GitHub by Illyism. 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 👇