# Team toolboxes and skills for every AI client | Elaichi

> Build a toolbox of chosen tools, frozen values and a written skill once, and every AI client your team connects is served the same kit from one endpoint.

An Elaichi toolbox is a named set of tools for one job, built from your connected apps. Each tool in it can be renamed and re-described for the model, given defaults or frozen values the AI cannot change, and switched on or off. A toolbox can also carry a skill: written guidance, up to 10,000 characters, on how to use its tools well. Share it with a person, a team or the whole organization, or publish it as a template others stamp their own copy from. Because it lives in Elaichi rather than in one chatbot, every client connected to it is served the same tools and the same guidance.

- **1** toolbox, served the same way to every AI client
- **10,000** characters of written guidance a toolbox can carry
- **3** share levels: view, use and edit
- **0** credentials a teammate needs to run it

## How a team’s AI setup usually grows

- Each person connects the apps they need in the AI client they prefer, and picks their own tools from everything those apps offer.
- The know-how for a task, which tool to use, which account and which fields to fill, lives in each person’s own prompts.
- When the process changes, each person updates their own setup.

## One kit, built once, the same everywhere

- Build a toolbox for the job: choose the tools, rename and describe them so the model picks the right one, set defaults, and freeze the values that must not change.
- Write a skill beside it: plain guidance on when and how to use the tools. Every edit is kept in a version history, and Elaichi flags the skill when tools are added, removed or renamed under it.
- Share it with a person, a team or the whole organization. Teammates run its tools without holding a credential, and their own roles and restrictions still apply to every call.
- Each person connects their AI client to the toolbox once. Claude, ChatGPT, Cursor and any other MCP client are served the same tools and the same guidance from one endpoint.

## For teams that want AI to do the job the same way

- **Team leads:** You know how the work should be done, and want every teammate’s AI to start from the same tools and the same instructions.
- **Operations and enablement:** You roll out a way of working and want it to land the same in Claude, ChatGPT and Cursor, without writing it up once per client.
- **IT and platform owners:** You want the tools a team relies on built and owned in one place, with roles, restrictions and the audit log still in force.

## What it looks like in practice

### One deal-review kit for the whole team

*Sales.* A sales manager builds a deal-review toolbox from Salesforce reads and the Slack tool that posts to the team’s deals channel, with the channel frozen. The skill spells out how the team reviews a deal. Reps open it from ChatGPT or Claude and start from the same tools and the same steps.

Connectors: [Salesforce](https://elaichi.ai/connectors/salesforce/), [Slack](https://elaichi.ai/connectors/slack/)

### Escalations written up the same way every time

*Support.* A support lead builds an escalation toolbox from Zendesk and Jira: read the ticket, then open an issue in the engineering project, with the project frozen. The skill lists what every escalation must include, so an issue reads the same whichever agent and whichever client filed it.

Connectors: [Zendesk](https://elaichi.ai/connectors/zendesk/), [Jira](https://elaichi.ai/connectors/jira/)

### A template every squad stamps its own copy from

*Engineering.* A platform team publishes an incident-response template with Sentry, Jira and Notion tools and a skill for the first hour of an incident. Each squad stamps its own toolbox from it, maps its own connections and gets a copy of the skill to adapt. Later edits to the template never change a squad’s copy.

Connectors: [Sentry](https://elaichi.ai/connectors/sentry/), [Jira](https://elaichi.ai/connectors/jira/), [Notion](https://elaichi.ai/connectors/notion/)

## How to set it up

1. **Pick the tools.** Create a toolbox and add the tools the job needs from your connected apps, including synthetic tools that chain several steps. Switch off anything the team should not use.
2. **Shape them for the model.** Rename a tool and rewrite its description so the model knows when to reach for it, set default values, and freeze the values that must never change.
3. **Write the skill.** Add written guidance on how to use the toolbox, up to 10,000 characters. Edits are versioned, and the skill is flagged when tools are added, removed or renamed under it.
4. **Share it and connect.** Share the toolbox at use with a person, a team or the organization, or share a template so teams stamp their own. Each person then connects their AI client to the toolbox once.

## Three ways to standardize how a team uses AI

| | Prompts passed around | Each AI client’s own connectors | An Elaichi toolbox |
|---|---|---|---|
| Tools in reach | Everything each person connected | Whatever each person attached in that client | The tools the toolbox holds |
| How tools are described | As each app ships them | As each app ships them | Renamed and described for the job |
| Values that must not change | Repeated in every prompt | Whatever the client’s settings offer | Frozen; the AI cannot change them |
| The know-how | Shared in chats and docs | Set up again in each client | A versioned skill that travels with the toolbox |
| A second AI client | Bring the prompts over | Set it up again in that client | Connect it to the same toolbox |
| Updating it for everyone | Re-shared by hand | Changed client by client | Edit the toolbox once |

## Details that matter

- **Guidance, not permission:** A skill grants nothing. Elaichi serves it with a fixed notice that it is the owner’s guidance, not instructions from Elaichi or the user, and every call still runs under the person’s own role and restrictions.
- **A rename cannot slip a restriction:** Restrictions check the catalog tool’s own name and operation, so renaming a tool or overriding its schema inside a toolbox never gets it past a block.
- **Templates copy once:** A toolbox stamped from a template gets its own copy of the entries and the skill. Later edits to the template never change it, so a team’s working copy changes only when the team changes it.
- **Where the guidance shows up:** Elaichi names a toolbox’s skill in its server instructions and offers it as a resource to any client connected to chosen toolboxes. A client connected to All my tools is offered neither, and whether a client passes server instructions to its model is the client’s choice.

## Further reading

- [Lock AI agent tool arguments, like a wire's payee](https://elaichi.ai/blog/frozen-parameters-wire-transfer-receiver/)
- [Claude and ChatGPT connectors vs one MCP endpoint](https://elaichi.ai/blog/elaichi-vs-native-ai-connectors/)
- [MCP endpoint per team, per person or per company?](https://elaichi.ai/blog/one-endpoint-vs-per-team-endpoint/)
- [The MCP context window problem, and a fix](https://elaichi.ai/blog/context-window-problem-mcp-tools/)
- [Connect company apps to Claude and ChatGPT](https://elaichi.ai/blog/connect-company-apps-to-claude-and-chatgpt/)

## Frequently asked questions

### What is a toolbox in Elaichi?

A named set of tools for one job, built from your connected apps. Each tool in it can be renamed and re-described, given defaults or frozen values, and switched on or off, and the toolbox can carry a skill: written guidance on how to use it.

### What is a skill?

Owner-written markdown guidance on how to use a toolbox’s tools, up to 10,000 characters. It is kept in a version history, flagged when tools are added, removed or renamed under it, and served with a notice that it is guidance and grants no access.

### Does a toolbox work the same in Claude, ChatGPT and Cursor?

Elaichi serves the same tools, frozen values and skill to every client connected to the toolbox, from one endpoint. Each client’s own model still decides how to use them, and whether a client passes Elaichi’s instructions to its model is the client’s choice.

### How does my AI client get the skill?

Connect the client to chosen toolboxes on Elaichi’s consent screen. Elaichi then names those toolboxes’ skills in its server instructions and offers each one as a resource the client can read. A client connected to All my tools is not offered skills.

### Can I stop the AI from changing a value, like a channel or a project?

Yes. Freeze it in the toolbox entry. Frozen values are merged in when the tool runs, so the AI cannot change them. The model may still see the value; it just cannot override it.

### Do teammates need their own access to the apps behind a toolbox?

No. Someone you share it with at use runs its tools through the connections pinned in it, without access of their own to those connections. Their own role and restrictions still apply to every call.

### What is the difference between sharing a toolbox and sharing a template?

Sharing a toolbox gives people that same toolbox, so your edits reach them. Sharing a template lets each person or team stamp their own copy, with their own connections and a copy of the skill, and later template edits do not reach copies already made.

### Can’t I do this with Claude’s or ChatGPT’s own connectors?

Each client’s own connectors are set up per person, inside that client, with the tools each app ships. A toolbox is built once in Elaichi, so the same chosen tools, frozen values and guidance reach every client a teammate connects, under one set of roles and restrictions and one audit log.

## Related use cases

- [Context sharing across teams](https://elaichi.ai/use-cases/context-sharing/)
- [Connect once, use across every LLM](https://elaichi.ai/use-cases/connect-once/)
- [Governance](https://elaichi.ai/use-cases/governance/)

See also [Product](https://elaichi.ai/product/) and [Security](https://elaichi.ai/security/), or [start a trial](https://app.elaichi.ai/signup).