Distribution logo

Distribution

Organization
ai-driven-dev
distribution

Owns where plugin and marketplace content comes from and how it is fetched, under src/contexts/distribution/ — marketplace registration, catalog parsing, and the ports/adapters that reach git and HTTP. Use when adding a new marketplace source kind, a catalog parser for a foreign format, or a fetch/cache/trust-store adapter. Do NOT use for what a tool does with fetched content — use `tools` or `translate`. Do NOT use for recording what got installed on a project — use `framework`.

Overview

Publisherai-driven-dev
Repositoryframework
Skill namedistribution
Stars
515
Forks
54
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

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

Installation

Install the Distribution 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/ai-driven-dev/framework/tree/main/cli/.claude/skills/distribution
  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/ai-driven-dev/framework.git /tmp/framework
mkdir -p .claude/skills
cp -r /tmp/framework/cli/.claude/skills/distribution .claude/skills/distribution
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Distribution 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 Distribution 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 Distribution 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.

Distribution

distribution is a leaf: it depends on kernel only, and knows no tool and no manifest. It answers exactly one question — where does content come from, and how is it fetched — for whoever asks. framework is the only context that reaches it (framework → distribution); a plugin's own content and how it gets translated are someone else's job once it has arrived here.

What goes in

ConceptLocation
A marketplace registration (name, source, scope, staleness)domain/marketplace.ts, domain/marketplace-source-mode.ts
A cached catalog fetchdomain/ports/marketplace-cache.ts
The plugin catalog shapedomain/catalog.ts (the Claude-shaped parser lives here too)
A reader for a non-Claude catalog shapedomain/catalog-parsers/
A port this context's callers holddomain/ports/ — registry, cache, trust-store, catalog-repository, fetcher, raw-catalog-fetcher
Add / list / refresh / register / resolve / fetch a marketplace sourceapplication/
The concrete adapter behind one of the six portsinfrastructure/

How

  • This context is a leaf by construction: it must never gain an edge to tools, translate, or framework — tests/architecture/context-graph.arch.test.ts enforces the chain (framework → distribution, plus everything to kernel) and fails the build the moment a new edge appears. If a change seems to need one, the orchestration belongs to the caller (framework), not here — see BASELINE in tests/architecture/helpers.ts for the one documented exception, distribution->framework, and the comment there that explains it (marketplace add --overwrite removing before adding), which is framework work that has not yet been moved out.
  • A port here follows the port/adapter rule in .claude/rules/00-architecture/: interface only, ≤5 methods, no null in the return type unless "not found" is genuinely a normal domain state (documented per-port, not assumed).
  • An adapter owns every technical constant for its integration (API base URLs, cache TTLs, error-pattern regexes for classifying a third-party failure) — none of that belongs in a port, a use-case, or a domain model. try/catch inside an adapter exists only to translate a raw error into a typed one from kernel/errors.ts.
  • A new foreign catalog shape gets its own parser in domain/catalog-parsers/, producing the same PluginCatalog/PluginCatalogEntry shape the Claude parser produces — callers above this context never branch on which format a catalog came from.
  • Follow the use-case rule in .claude/rules/00-architecture/ for the application layer's shape.

Public surface

Nothing outside contexts/distribution/ may import a module this context has not declared public — tests/architecture/context-boundary.arch.test.ts holds the list (PUBLIC_MODULES.distribution). Measured at extraction, ten modules were reached from outside and not one was an adapter: the adapters are wired by the composition root (runtime/wiring/distribution.ts) alone, and stay internal for that reason. A module that exposes its own plumbing to a caller outside the composition root is not a leaf context anymore — keep new adapters unreachable from outside.

How it's tested

  • tests/contexts/distribution/ mirrors src/contexts/distribution/ — domain models and application use-cases are unit-tier; adapters against a real temp filesystem or a mocked network boundary are integration-tier. See the test skill for tier conventions.
  • A new catalog parser needs a fixture of the real foreign format and a test asserting the parsed PluginCatalog matches what the Claude-shaped parser would produce for an equivalent catalog.

Frequently asked questions

What does the Distribution AI skill do?

Owns where plugin and marketplace content comes from and how it is fetched, under src/contexts/distribution/ — marketplace registration, catalog parsing, and the ports/adapters that reach git and HTTP. Use when adding a new marketplace source kind, a catalog parser for a foreign format, or a fetch/cache/trust-store adapter. Do NOT use for what a tool does with fetched content — use `tools` or `translate`. Do NOT use for recording what got installed on a project — use `framework`.

Why use Distribution on TypingMind?

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

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

Which AI models can use Distribution?

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 Distribution?

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

Is the Distribution AI skill free?

Yes. It is published on GitHub by ai-driven-dev 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 👇