> For the complete documentation index, see [llms.txt](https://docs.dapta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dapta.ai/dapta-mcp/skills.md).
# Skills Catalog
Skills are the guided workflows that tell Claude how and when to use the tools. You do not invoke them by name. You describe what you want in plain language, and the matching skill activates automatically.
Each skill entry in this catalog follows the same shape:
* **What it does** is a plain-English summary.
* **Use it when** is the situation that triggers it.
* **Try saying** gives copy-pasteable example prompts.
* **You get back** is what you receive.
* **Writes data?** says whether it is read-only or a write that shows a preview first.
* **Behind the scenes** lists the underlying tools, for context.
{% hint style="info" %}
**A note on writes.** Anything that changes your data uses a **preview, then commit** flow: Claude shows you exactly what will change and waits for your confirmation before applying it. The one exception is creating a brand-new voice agent, which is created directly once you have supplied the details.
{% endhint %}
A quick overview of what the skill bundle ships with, also shown in Dapta on the MCP Access page.
***
## The full index
| Skill | What it does |
| -------------------------------- | ----------------------------------------------------------------------------- |
| **Voice agents** | |
| `create-voice-agent` | Build a new voice agent from a template in a few guided steps |
| `voice-agent-config` | Inspect and adjust an agent's settings (speed, interruptions, model, webhook) |
| `voice-agent-variables` | See what data an agent captures and how often fields get filled |
| `voice-agent-ownership` | Confirm a voice agent belongs to your workspace |
| `voice-prompts` | Write or refine voice prompt text (without saving to a live agent) |
| `voice-prompt-improver` | Improve an agent's prompt from real call data and apply it |
| `voice-call-analytics` | Full call performance analysis (rates, outcomes, sentiment, categories) |
| `voice-call-feedback` | Analyze thumbs up and down votes and comments on calls |
| `voice-call-audio` | Pull up call recordings to listen back |
| `voice-dialing-hours-analysis` | Find the best hours and days to dial |
| `voice-lead-intelligence` | Find qualified leads and a conversion funnel from calls |
| `legacy-voice-analytics` | List and search agents and review feature spend |
| **Text & WhatsApp agents** | |
| `create-text-agent` | Create a new text or chat agent from a template |
| `text-agent-searcher` | Search, list, count, and rank your text agents and channels |
| `text-agent-calibrator` | Diagnose and fine-tune a chat agent from recent conversations |
| `text-agent-widget` | Connect, swap, or remove a voice agent on your website chat widget |
| `connect-whatsapp-text-agent` | View WhatsApp lines and prepare a number to connect to an agent |
| `text-prompts` | Read a text agent's prompt, company info, and persona |
| `text-prompt-improver` | Rewrite or refine a text agent's system prompt and apply it |
| **Flow Studio** | |
| `flow-studio-flow-builder` | Design, build, and deploy Flow Studio automations |
| `flow-studio-analytics` | Inspect and report on existing flows (health, versions, integrations) |
| **Sales meetings** | |
| `sales-meeting-analyzer` | Find and analyze recorded sales meetings (summary, action items, tips) |
| **Accounts, identity & billing** | |
| `iam-account-searcher` | Search accounts, users, and workspaces you can access |
| `iam-legacy-mapper` | Map legacy organization IDs to current workspaces and accounts |
| `account-evaluation` | Full account health check with a stage and prioritized action plan |
| `industry-intelligence` | Your industry classification and how peers use Dapta |
| `billing-analytics` | Plan, credit balance, usage, and subscription details |
| **Support** | |
| `customer-support` | Instant answers to common account, billing, and contact questions |
| `create_support_ticket` | Open a tracked support ticket (preview then commit) |
| `support-history` | Retrieve your and your team's past support tickets |
| **Research & docs** | |
| `core-docs` | Search the official Dapta documentation and answer how-to questions |
| `academy-videos` | Suggest the matching Dapta Academy tutorial video |
| `web-search` | Research companies, people, and markets on the public web |
***
## Browse by category
{% content-ref url="/pages/vVHiKaRtWBIR0iKeG6TK" %}
[Voice Agents](/dapta-mcp/skills/voice-agents.md)
{% endcontent-ref %}
{% content-ref url="/pages/jmy7cFt8aRU7eLdwV3tN" %}
[Text & WhatsApp Agents](/dapta-mcp/skills/text-agents.md)
{% endcontent-ref %}
{% content-ref url="/pages/BgAMc53TMK4kNuDr8mB0" %}
[Flow Studio](/dapta-mcp/skills/flow-studio.md)
{% endcontent-ref %}
{% content-ref url="/pages/GXl549L14zb0wDdlTGT4" %}
[Sales Meetings](/dapta-mcp/skills/sales-meetings.md)
{% endcontent-ref %}
{% content-ref url="/pages/WRY69r1HGf5V5xQZSBNt" %}
[Accounts, Identity & Billing](/dapta-mcp/skills/accounts.md)
{% endcontent-ref %}
{% content-ref url="/pages/2UGxXEYpIozbWYhLINOw" %}
[Support](/dapta-mcp/skills/support.md)
{% endcontent-ref %}
{% content-ref url="/pages/4gaqjVivImrmXhwbzSSf" %}
[Research & Docs](/dapta-mcp/skills/research.md)
{% endcontent-ref %}
***
## Looking for the raw actions?
Every skill is built on tools. If you want the full list of the 128 underlying actions grouped by domain, see the reference.
{% content-ref url="/pages/LluK6HAzoklQl1lPYjZu" %}
[Tools Reference](/dapta-mcp/tools-reference.md)
{% endcontent-ref %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.dapta.ai/dapta-mcp/skills.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.