Cinematic Skill
The agent scripts, voices and draws a narrated documentary in code, with one continuous camera over photos, maps and cards.
- 237 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The agent runs Python scripts and ffmpeg and downloads files from Wikimedia Commons.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/cinematic-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The agent runs Python scripts and ffmpeg and downloads files from Wikimedia Commons.
This is third-party code. Review the repository files before installing.
What it does
The skill teaches a coding agent to build narrated films entirely from code. The agent researches the topic, writes a line-by-line script, records a voice, pulls photos from Wikimedia Commons with their licences and assembles one world under a single camera. Frames are drawn with Skia in Python, so no model generates the video and every render repeats exactly. Stamps, highlighters and rolling counters land on the narrator's word, and a new voice re-times the whole film. After the beat table, the look and a 30 second draft the agent stops for approval.
Who it is for. Creators of history, product or science videos who want controllable editing without a video editor.
Good fit when
- A 90 second documentary about a historical event needs photos from open archives with licences recorded.
- A product launch is explained in an animated film built from your own screenshots and photos.
- A technology explainer is assembled from diagrams, cards and routes on a map.
- The film is re-voiced and the timing of every effect must recalculate by itself.
Not a fit when
- You need live footage or video generated by a neural model.
- The film must come together in minutes without installing Python and ffmpeg.
- Only timeline editing in a graphical editor will do.
Example request
Make a 90 second documentary about the Wright brothers: script, voice, Wikimedia Commons photos and a final mp4.Limitations
Python with `skia-python`, `numpy`, `pillow` and ffmpeg on PATH are required; `check_setup.py` reports what is missing. The `npx skills add` installer needs Node 22.20 or newer. Rendering the 92 second film at 1080p takes about 6 minutes on a 16 GB laptop. The skill refuses non-free files from Wikimedia, yet licences of your own and other images deserve a second look before publishing. The project is built for a single author, so parallel team work on one scene is not covered.
How to disable. Remove the skill from the agent skills folder or run `/plugin uninstall`. If it was installed through `install.sh`, run `./install.sh --uninstall`. Delete `~/.cinematic-skill` and your film projects by hand.
FAQ
Which agents are supported?
Claude Code, Codex, Cursor, Gemini CLI and OpenCode. `npx skills add` installs the skill for agents it finds, and Claude Code and Codex also have plugins.
Where do images come from?
The agent searches and downloads files from Wikimedia Commons, records licences and writes `credits.md`. Your own photos and AI stills are added separately.
Is a paid voice required?
No. The draft is voiced with macOS `say` or espeak-ng. The final voice can be any TTS or a recorded person, and the film re-times to it.
How do I try the example?
Run `python3 new_project.py ~/wright --example` from `skills/cinematic-film/scripts`, then the steps from the Try the example section. They build a film about the first flight.
How long does rendering take?
The 92 second film at 1080p renders in about 6 minutes on a 16 GB laptop. Use `--size 1280x720` for drafts.
Discussion
No questions or reviews yet.
Related
SkillsA director skill for AI video: turns a script into a shot list, keyframes and motion prompts for Runway, Kling and Veo
Two skills for generative video and images: video writes Seedance, Kling and Veo prompts by dramaturgy rules, image picks the model and its syntax
A skill and CLI that let Claude Code or Codex make videos as web pages, with the Studio editor to change the result
Seven AI video skills: promo film planning, scene and fight prompts, acting direction and generation task reliability checks.
A skill that turns an idea, a link or a screen recording into finished video: HeyGen avatar, b-roll, captions and quality checks
A skill that makes your agent film a short product video: concept, edit, sound and render on Remotion or HyperFrames
README in short
Script, voice, images, a Python scene, frame review and a captioned render run as separate steps. Sound effects, an optional score and four caption styles come at the end.
README badge
Original SKILL.md
--- name: cinematic-film description: Makes narrated cinematic films entirely from code, on any subject. One continuous camera glides over one designed world of photos, documents, cards, maps with routes and big numbers, with every stamp, highlight and number landing on the narrator's word, then sound effects, an optional score and burned-in captions. For documentaries and history, product launches, brand and founder stories, science and tech explainers, biographies and true crime. Covers the script, voiceover from any TTS split into timed lines, images (archives with their licences, your own photos, AI stills), a beat table, the scene, self-review stills and a memory-safe parallel render. Use for "make a cinematic video about", "documentary about", "explainer video", "launch film", "Vox-style video", "evidence board animation", or turning a story into a video for X, YouTube or TikTok. --- # Cinematic film A film made this way is one camera move over one world. Every photo, card, clipping, map and number lives on one big board, and the camera travels between them along string, routes and arrows as the story moves. Every visual hit is timed to the word the narrator says. It is all code (Skia in Python), so it renders the same every time, any topic fits, and a new voice re-times the whole film by itself. Built from a 5:22 documentary about Al Capone, then opened up to any subject. The rules here were written from what broke while making it. ## Tools | File | What it does | | --- | --- | | `scripts/check_setup.py` | Checks Python, skia-python, ffmpeg, fonts and memory; says what to install | | `scripts/get_fonts.py` | Fetches open-licensed fonts (Bebas Neue, Homemade Apple) for any text role this machine lacks | | `scripts/new_project.py` | Starts a project from `assets/template/` (a runnable explainer), or the documentary example with `--example` | | `scripts/make_beats.py` | Writes `beats.md`, the table you approve; lints chronology, line length, digits in spoken text | | `scripts/tts_say.py` | Free scratch voice (macOS `say`, espeak-ng, or any TTS command) to time the film before the final voice | | `scripts/split_takes.py` | Cuts whole-section takes into one clip per line and flags suspect cuts | | `scripts/build_narration.py` | Joins the lines into `audio/narration.m4a` and `audio/timing.json`, which the film is built on | | `scripts/fetch_commons.py` | Searches Wikimedia Commons, downloads with licence and credit, refuses non-free files, writes `credits.md` | | `scripts/make_map.py` | Projects public-domain boundaries (any country or region) for the map | | `scripts/prep_assets.py` | Grades every image into one look (black and white, sepia or natural colour); generates the board textures | | `scripts/engine.py` | The film engine: camera, spotlight, items, maps, looks, film finish | | `scripts/render.py` | Stills, contact strips, the cue list, and the parallel MP4 render | | `scripts/build_sfx.py` | Synthesises every sound effect from the cue list (no samples, nothing to license) | | `scripts/mix_soundtrack.py` | Voice, effects and optional music, ducked and loudness-normalised | | `scripts/burn_captions.py` | Burns one of four caption styles into the finished film and writes an SRT | Needs Python 3.9+, `pip install skia-python numpy pillow` (scipy optional) and ffmpeg. Run `scripts/check_setup.py` first; on Linux or Windows, also run `scripts/get_fonts.py` per project. All commands take `--project <folder>`. ## Pick the film | Kind | Look | Images | Typical items | | --- | --- | --- | --- | | History, true crime, investigation | `wall`, `slate` | Archive photos and documents, graded `bw` | Prints, torn clippings, stamps, red string, map routes | | Product launch, brand or founder story | `studio`, `charcoal` | Your product shots and team photos, graded `natural` | Cards, big numbers, counters, arrows | | Science, engineering, how it works | `blueprint`, `paper` | Diagrams, archive or AI stills | Cards, counters, pen marks, maps | | Tech, space, trailers | `night` | Screenshots, renders, AI stills | Big type, counters, routes, cards | Mix freely: the looks are a board and a finish, and every item works on every look. `references/story.md` has a story shape for each kind. ## The rules