Tools logo

Tools

Organization
ai-driven-dev
tools

Defines or modifies what the project targets, under src/contexts/tools/ — an AI/IDE tool profile, its build contract, the content-translation capability classes it composes (agents/skills/commands/rules/hooks), and its own native-plugin adapter. Use when adding a new AI or IDE tool, changing a tool's Has* capability intersection, adding or modifying a capability class, or declaring a tool's `aidd translate` build contract. Do NOT use for the canonical-to-native translation pipeline itself — use `translate`. Do NOT use for where plugin content comes from — use `distribution`. Do NOT use for manifest or install orchestration — use `framework`.

Overview

Publisherai-driven-dev
Repositoryframework
Skill nametools
Stars
515
Forks
54
Bundled files
4
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.

  • 4 bundled files

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

  • Open source

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

Installation

Install the Tools 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/tools
  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/tools .claude/skills/tools
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tools 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 Tools 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 Tools 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.

Tools

tools is what the project targets and how each target is configured. Every AI assistant and IDE the CLI supports is one AiTool<C> or IdeToolConfig object in contexts/tools/domain/profiles/<tool>/profile.ts, where C is the intersection of Has* capability interfaces the tool actually supports. translate depends on tools (never the reverse) to call the tool's own rewriteContent and to read its build contract — a tool profile is data and behavior the rest of the CLI is handed, not a place that reaches out to fetch or install anything itself.

What goes in

ConceptLocation
A tool's identity, capabilities, content-rewritedomain/profiles/<tool>/profile.ts
A tool's aidd translate build behaviordomain/profiles/<tool>/build.ts (only if the tool is a build target)
A string transform used by exactly one profilethat profile's own directory
A string transform shared by ≥2 profilesdomain/formats/
A content-translation capability class (agents/skills/commands/rules/hooks)domain/capabilities/ + a Has* entry in contracts.ts
Catalog/manifest shaping shared by ≥2 tools' build contractsdomain/marketplace-catalog.ts
A port only tools needsdomain/ports/
A tool's own plugin-CLI driverinfrastructure/

How

  • AiTool<C> fields: read domain/contracts.ts. A list copied here aged at every field.
  • Has* interfaces live in contracts.ts, always readonly, never optional — a tool either includes Has<Name> in its C intersection or does not have the field at all. Guard presence with "name" in tool.capabilities, never instanceof.
  • rewriteContent(content) is one way, per tool, with no reverse and no shared base helper. See references/content-rewrite.md.
  • A capability class ends in Capability, takes one params object, all fields readonly, throws CapabilityConfigError (from kernel/errors.ts) on an invalid combination, carries no application/infrastructure imports. See references/capability-conventions.md.
  • PluginsCapability has three modes (native, flat, unsupported) and a translationMode (marketplace | flat | null) — see references/plugins-capability.md.
  • Build behavior is ONE artifact-symmetric ToolBuildContract per tool, read by the two mode-generic orchestrators (MarketplaceBuildStrategy, FlatBuildStrategy) in translate — never a per-tool strategy class, never a per-tool or per-artifact-kind branch in an orchestrator. See references/build-contract.md.
  • registerTool(config) is called once, at the bottom of profile.ts, never from a use-case.
  • Follow the port/adapter rule in .claude/rules/00-architecture/ for the shape of a port and its adapter, and the shared-module rule there before promoting a helper out of a single profile.

Public surface

Nothing outside contexts/tools/ may import a module this context has not declared public — tests/architecture/context-boundary.arch.test.ts holds the list (PUBLIC_MODULES.tools). A new module is invisible to translate and framework until it is added there; there is no index.ts and there never will be (barrels are forbidden by the export rule in .claude/rules/01-standards/).

How it's tested

  • tests/contexts/tools/ mirrors src/contexts/tools/ — one profile's profile.ts/build.ts gets a unit test asserting the AiTool<C> type is satisfied and each rewrite rule holds.
  • tests/architecture/tool-addition-cost.arch.test.ts ratchets how many files outside a new tool's own directory must change to add it — keep new tool-specific logic inside the profile.
  • See the test skill for tier conventions; capability/format round-trip tests are unit-tier.

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 Tools AI skill do?

Defines or modifies what the project targets, under src/contexts/tools/ — an AI/IDE tool profile, its build contract, the content-translation capability classes it composes (agents/skills/commands/rules/hooks), and its own native-plugin adapter. Use when adding a new AI or IDE tool, changing a tool's Has* capability intersection, adding or modifying a capability class, or declaring a tool's `aidd translate` build contract. Do NOT use for the canonical-to-native translation pipeline itself — use `translate`. Do NOT use for where plugin content comes from — use `distribution`. Do NOT use for...

Why use Tools on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ai-driven-dev/framework/tree/main/cli/.claude/skills/tools. 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 Tools?

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 Tools?

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

Is the Tools 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 👇