agentleFS
airdropfiairdropfi/autoshort-skills/.cursor/rules/autoshort-video.mdc

autoshort-skills / rules

Cursor rule1 starsChanged 21 days agoMITView on GitHub

Making faceless short videos with the AutoShort or StoryShort MCP server: script review first, credit price from the server before any render, plan before produce for series. Use when the user asks to make, draft, render or publish a short video, or plan a video series.

  • Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.

    Of the Cursor rule files we read, the 4,243 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository3 other files it gives its agents.

The file

We split this autoshort-video.mdc into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before any paid step, show the price exactly as a tool returned it (autoshort_estimate_cost on AutoShort.

    line 13
  2. Distinctive:

    Never write a credit number from memory, never buy credits or set up auto-recharge, never promise views, income or monetisation.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 6,809 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
autoshort-video.mdc
---
description: Making faceless short videos with the AutoShort or StoryShort MCP server: script review first, credit price from the server before any render, plan before produce for series. Use when the user asks to make, draft, render or publish a short video, or plan a video series.
alwaysApply: false
---

# Faceless videos with AutoShort or StoryShort

This rule is the short form of the skills in `skills/`. Read `skills/make-faceless-video/SKILL.md` for the full flow, and `skills/plan-a-video-series/SKILL.md` for series.

1. Find out which MCP server is connected from your tool list. AutoShort tools start with `autoshort_` (`autoshort_get_capabilities`, `autoshort_draft_video`). StoryShort tools have no prefix (`draft_video`, `render_draft`). Use only tools that are listed; never invent a tool name or parameter. If neither is connected, tell the user to add `https://autoshort.org/api/mcp` or `https://storyshort.app/api/mcp` in Cursor's MCP settings and sign in.
2. Agree the script with the user first. Narration is read aloud word for word.
3. Save a free draft (`autoshort_draft_video` or `draft_video`). Drafts render nothing and charge nothing.
4. Before any paid step, show the price exactly as a tool returned it (`autoshort_estimate_cost` on AutoShort; `get_draft` on StoryShort) with the balance, and ask "Render it?". Render only after a clear yes: `autoshort_render_draft`, or `render_draft` with `confirmCredits` set to the approved price.
5. Poll `autoshort_get_video` or `get_video` every 20 to 30 seconds until COMPLETED or FAILED, then give the user the video link.
6. Series: plan first, review, get an explicit confirmation, then produce one quoted episode at a time (AutoShort), or create the series paused and resume it only after the user approves the cost (StoryShort).
7. Never write a credit number from memory, never buy credits or set up auto-recharge, never promise views, income or monetisation.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.