Holistic logo

Holistic

Organization
AgentiveStack
holistic

Zoom out to see how code, features, or plans fit into the bigger picture. Maps bounded contexts, traces cross-cutting concerns, surfaces hidden dependencies, and identifies systemic risks. Use when you're lost in details, unfamiliar with an area, or need to understand the full impact of a change.

Overview

PublisherAgentiveStack
Repositoryskills
Skill nameholistic
Stars
72
Forks
17
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 AgentiveStack on GitHub. Read the source before you install it.

Installation

Install the Holistic 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/AgentiveStack/skills/tree/main/holistic
  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/AgentiveStack/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/holistic .claude/skills/holistic
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Holistic 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 Holistic 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 Holistic 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.

Holistic View

Provide a comprehensive, multi-layered view of how a piece of code, feature, or plan fits into the broader system. This skill operates at the system level, not the implementation level.

Process

1. Discover project context

Read existing domain documentation to ground the analysis:

  1. docs/CONTEXT_MAP.md — bounded contexts and relationships
  2. docs/UBIQUITOUS_LANGUAGE.md — canonical terminology
  3. docs/contexts/*/CONTEXT.md — per-context ownership and contracts
  4. CLAUDE.md — project-level context

If these don't exist, explore the codebase organically to build the picture.

2. Identify the focal point

Determine what the user wants to understand. This could be:

  • A specific file, module, or package
  • A feature or capability
  • A planned change or new feature
  • A bug or unexpected behavior
  • A concept or term they're uncertain about

3. Map the context

For the focal point, produce a multi-layer map:

Layer 1: Domain Position
  • Which bounded context does this belong to?
  • What domain concepts does it implement?
  • What is its role within that context? (core logic, infrastructure, surface/UI, contract/boundary)
Layer 2: Data Flow
  • What data flows INTO this component? (upstream dependencies)
  • What data flows OUT? (downstream consumers)
  • What shared kernels or contracts does it participate in?
  • Trace the full request/data path from origin to destination
Layer 3: Cross-Context Impact
  • Which other bounded contexts does this touch?
  • What are the coupling points? (shared tables, events, APIs, window globals)
  • If this breaks, what else breaks? (blast radius)
  • If this changes, what else needs to change? (change propagation)
Layer 4: Temporal View
  • How does this relate to recent changes? (check git log)
  • Are there planned changes that will affect this? (check specs, open issues)
  • Is this area stable or actively evolving?
  • Are there known technical debt or open questions? (check CONTEXT.md open questions)

4. Surface insights

After mapping, highlight:

  • Hidden dependencies — coupling that isn't obvious from imports alone (e.g., shared ClickHouse tables, window globals, convention-based contracts)
  • Systemic risks — single points of failure, untested boundaries, stale assumptions
  • Opportunities — places where the current structure creates unnecessary friction or where a small change would have outsized positive impact
  • Missing documentation — if this exploration revealed gaps in CONTEXT.md, UBIQUITOUS_LANGUAGE.md, or CONTEXT_MAP.md, note what should be added

5. Present the map

Structure the output as:

## [Focal Point Name]

### Domain Position
[Which context, what role, what concepts]

### Data Flow
[Upstream → This → Downstream, with specific contracts]

### Cross-Context Impact
[What it touches beyond its own context, blast radius]

### Key Insights
[Hidden dependencies, risks, opportunities]

### Recommended Reading
[Specific files or docs to read for deeper understanding]

Keep it concise. The goal is orientation, not exhaustive documentation.

When to use this skill

  • "I don't know this area of code well" → map the modules and callers
  • "What would break if I change X?" → trace the blast radius
  • "How does feature Y actually work end-to-end?" → trace the data flow
  • "Where does this concept live in the codebase?" → map to bounded context + ownership
  • "I'm about to start a big change — what should I be aware of?" → full holistic view

Related skills

  • /domain — stress-test a plan against the domain model (deeper, interactive)
  • /architect — surface friction and design better interfaces (prescriptive)
  • /spec — after understanding the picture, formalize a plan

Frequently asked questions

What does the Holistic AI skill do?

Zoom out to see how code, features, or plans fit into the bigger picture. Maps bounded contexts, traces cross-cutting concerns, surfaces hidden dependencies, and identifies systemic risks. Use when you're lost in details, unfamiliar with an area, or need to understand the full impact of a change.

Why use Holistic on TypingMind?

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

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

Which AI models can use Holistic?

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 Holistic?

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

Is the Holistic AI skill free?

Yes. It is published on GitHub by AgentiveStack 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 👇