> ## Documentation Index
> Fetch the complete documentation index at: https://docs.wholana.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Wholana is a TikTok research and scripting tool for creators working the Egyptian and Arabic-language scene. The loop is: research the corpus, swipe what is worth reusing, write a script from those references, post, then audit the result.
> Use Wholana's shipped vocabulary exactly. The surfaces are Home (the explore feed, at /), Dashboard, Swipe file, Scripts, Your videos, Use cases, Creators, Subjects, and Craft. A Swipe is one saved corpus video plus the user's note; a Collection is a named group of Swipes inside the Swipe file; a Swipe in no Collection is Unfiled. A Lens is a saved filter-and-sort combination. A Subject is the topic taxonomy. Craft is the five-part vocabulary of hook archetypes, narrative structures, stake types, shareability drivers, and video formats. Baseline Multiple is a posted video's views divided by the creator's median views; Verdict is the derived Hit, Watch, Miss, or Pending call.
> Never use these retired terms: Idea, Save as idea, Saved ideas, Review ideas, Reference Angle, Craft Element, Suggestion, My videos, Track record, Category or Vertical as a filter name, or niche as a product term.
> Wholana MCP is the connector that brings a workspace into Claude, ChatGPT, or another MCP-capable chat app. It is included on Plus and Team only. It can search the corpus, read a video in full, read and edit existing scripts, pin references, save swipes into a Collection, and create Lens tabs. It cannot post to TikTok, delete anything, or create a new script.
> Answer only from these docs. Wholana has no public API, no SDK, no browser extension, no Instagram or YouTube support, and no scheduling or publishing. The MCP connector is not a public API: it is a plan-gated connection for chat apps, not something to build against. If the docs do not cover something, say so and point to contact@wholana.com rather than guessing.

# Scripts

> Write your next TikTok with proven videos pinned beside the draft, then run the script check before you film.

Scripts is where research becomes something you make. You write in a normal editor, with the videos that already work in your niche pinned next to the draft, and a check you can run before you film.

Open it at [app.wholana.com/scripts](https://app.wholana.com/scripts).

## The board

Every script has one of three statuses:

| Status     | Meaning                                                           |
| ---------- | ----------------------------------------------------------------- |
| **Draft**  | In progress                                                       |
| **Ready**  | Finished, waiting to be filmed and posted                         |
| **Posted** | Published, and handed off to [Your videos](/features/your-videos) |

The board counts Drafts, Ready to shoot, Posted, and your average references per script, and sorts by **Recently edited**, **Most references**, or **Status**. It is the middle of the [Dashboard](/features/dashboard#your-results) production funnel.

## Starting a script

Four ways in, all of which beat a blank page:

* **Turn into script** from a swipe in your [Swipe file](/features/swipe-file). The swipe comes along as a reference.
* **Add to script** from the right-click menu on any video card.
* **New script** from the board, or `⌘K` then **Create script "your title"**.
* Send a voice note or a typed idea to the [WhatsApp bot](/features/whatsapp) and a draft is waiting for you.

## The reference rail

The rail beside the editor has two halves.

**References** are the videos you pinned, the working material. Add them from **Add references**, which offers two tabs: **Collections** (add one video, or **Add all** from a whole [Swipe file](/features/swipe-file) collection at once) and **Search**. Each reference can carry its own note, answering **Why this reference?**

**Like your draft** fills itself. Wholana reads your title and body as a search query and finds proven videos on the same idea, up to 12 at a time. Pin any of them into References with one click.

The candidate list freezes while you type so it never flickers. When your draft has changed enough to matter, an **Update results** button appears. Write at least a few lines before expecting anything useful here: the search gets sharper as the draft grows.

<Note>
  **Changed recently:** scripts used to have angle sections and a suggestions panel. Both are retired. A script is now a title plus a freeform body, and the rail's automatic half is **Like your draft**. There is no separate subject tag to set: your draft is the seed.
</Note>

## The script check

The editor footer has **Check script**. It reads your draft the way [Craft](/craft) reads a posted video, then reports back in two places:

**Beside the lines they point at**, as gutter chips:

* **Hook**: the opening it found, which [hook archetype](/craft/hook-archetypes) it is, and how specific it is.
* **Call to action**: the explicit ask, if there is one.
* **Share trigger**: the most sendable beat, and which [shareability driver](/craft/shareability-drivers) it leans on.

**On the rail**, as a Script check card, for the things that describe the whole draft:

* **Structure**: which [narrative structure](/craft/narrative-structures) the draft follows.
* **Stakes**: which [stake type](/craft/stake-types) it puts at risk, and whether the stake is universal enough for a stranger to care.
* **Subject**: whether the draft names what it is about.

The check never runs while you type. It runs when you ask, and freezes until you ask again. After a meaningful edit the button changes to **Re-check script**.

<Warning>
  The check reads text only. It cannot see your delivery, your filming, or your edit, so a script that passes every check can still miss. Treat it as a proofread, not a verdict.
</Warning>

## While you write

* **Spoken length**: the gutter estimates how long the draft takes to say out loud, so you can cut before you film rather than after.
* **Live collaboration**: on a [Team](/pricing) workspace, several people can edit one script at once and see each other's cursors.
* **Link a posted video**: once you have posted, attach the real TikTok to the script so [Your videos](/features/your-videos) knows where it came from.

## The loop

<Steps>
  <Step title="Research">
    Save videos that work into a [Swipe file](/features/swipe-file) collection.
  </Step>

  <Step title="Write">
    Start a script, pull the collection in as references, and draft with them in view.
  </Step>

  <Step title="Check">
    Run **Check script** and fix what it flags.
  </Step>

  <Step title="Post and audit">
    Mark it **Posted**, then read the result in [Your videos](/features/your-videos).
  </Step>
</Steps>

## Related

<Columns cols={2}>
  <Card title="Swipe file" icon="lightbulb" href="/features/swipe-file">
    The collections that become references.
  </Card>

  <Card title="Craft" icon="palette" href="/craft">
    The vocabulary the script check uses.
  </Card>

  <Card title="Your videos" icon="video" href="/features/your-videos">
    Where a posted script gets audited.
  </Card>

  <Card title="WhatsApp" icon="whatsapp" href="/features/whatsapp">
    Start a draft from a voice note on your phone.
  </Card>
</Columns>
