story-new
Skill4 starsChanged 3 months agoMITView on GitHub
Create a new story video from a context. Writes story.json, gets the script approved, then generates the Sarvam voiceover and FLUX 2 artwork and renders the mp4.
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- paoloirrera/ccgraphtheir own version, first seen Aug 4, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- paoloirrera/ccgraph★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- story-renderSkill
- story-setupSkill
- story-tellingSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
If no arguments, ask what the video is about, how long it should be, and where it will be published.
- Distinctive: line 25
Check the pipeline is present, since the skills can be installed without it:
- Very specific: line 31
If missing, run the story-setup skill first.
- Very specific: line 34
Read the story-telling rules before writing anything: rules/story-formats.md to pick the shape, rules/narration.md for the script, …
- Distinctive: line 41
Write the narration from the context:
- Distinctive: line 45
Every fact traceable to the given context, nothing invented
- Distinctive: line 47
Write the image prompts:
- Very specific: line 50
Never name a real person. If the user supplied reference photos, add them to references and set reference on those images, putting the …
- Distinctive: line 68
Verify before reporting: check the output exists and read its real duration rather than assuming the planned one.
- Very specific: line 75
When the user wants no review step and has OPENAI_API_KEY set:
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill 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.
Files
Turn a context into a finished narrated video.
Arguments
Parse $ARGUMENTS as: slug context seconds orientation
$0= slug, lowercase and hyphenated, e.g.big-bull. Becomes the folder underpublic/and, in PascalCase, the composition id$1= context: a file path, a URL already fetched, or the text itself$2= length in seconds. Default 60$3=landscapeorvertical. Defaultlandscape
If no arguments, ask what the video is about, how long it should be, and where it will be published.
Instructions
Check the pipeline is present, since the skills can be installed without it:
test -f cli/generate.ts && test -f src/Root.tsx && echo present || echo missingIf missing, run the
story-setupskill first. It fetches the project, installs dependencies, creates.envand verifies the keys. Everything below runs from the project root.- Read the
story-tellingrules before writing anything:rules/story-formats.mdto pick the shape,rules/narration.mdfor the script,rules/images.mdfor the prompts,rules/pitfalls.mdfor the checklist. - Pick the format from
rules/story-formats.mdand start from the matching template inrules/assets/<format>/story.json. Copy it topublic/<slug>/story.jsonand changeslugandcompositionIdfirst. - Write the narration from the context:
- Scene count is roughly seconds divided by ten, clamped 3 to 10
- 24 to 32 words per scene
- Numbers spelled as words; digits only on
statcards - Every fact traceable to the given context, nothing invented
- Note any contradiction in the source and say which reading was used
- Write the image prompts:
- Scene direction only. The house style lives in
style.artPrompt - Two images per scene for movement, one for a calmer feel
- Never name a real person. If the user supplied reference photos, add them
to
referencesand setreferenceon those images, putting the likeness clause first in the prompt - Image ids unique across the whole story, and
outro.imageIdmust be one of them
- Scene direction only. The house style lives in
- Show the narration to the user and wait for approval. Voices and images cost money; a wrong fact caught here is free.
- Generate:
This writes voices, images and the measurednpm run generate -- --slug <slug>durationInFramesback intostory.json. Existing files are skipped, so reruns are cheap. - Preview or render:
npm run studio npx remotion render <CompositionId> out/<slug>.mp4 --codec h264 - Verify before reporting: check the output exists and read its real duration rather than assuming the planned one.
- Report scene count, total duration, image count, output path and size, plus any assumption made about an ambiguous fact.
Fully automatic alternative
When the user wants no review step and has OPENAI_API_KEY set:
npm run story -- --slug big-bull --context ./article.md --seconds 60 --renderThis drafts with OpenAI, generates, and renders in one pass. Quality of facts
is lower than a hand-written story.json, so prefer the reviewed path for
anything that will be published.
Formats
| Format | Template | Length | Scenes |
| Biography | assets/biography/story.json | 60s | 6 |
| Concept explainer | assets/explainer/story.json | 60s | 6 |
| Vertical short | assets/reel/story.json | 30s | 3 |
| Numbered list | assets/listicle/story.json | 60s | 6 |
| News or event | assets/news/story.json | 45s | 5 |
| Myth versus fact | assets/myth-buster/story.json | 45s | 5 |
Example usage
/story-new big-bull ./article.md 60 landscape
/story-new repo-rate "Explain the repo rate to a first time borrower" 30 vertical
/story-new fed-cut ./notes/fed.md
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
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.

