shorts-kit skill
Ten skills and a rulebook for narrated vertical shorts and promo films on Remotion, driven by a coding agent
- 141 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs local scripts, rendering and Whisper and writes project files
- The ElevenLabs key lives in .env and is sent to the voice service
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/shorts-kitDetects 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.
- Runs local scripts, rendering and Whisper and writes project files
- The ElevenLabs key lives in .env and is sent to the voice service
This is third-party code. Review the repository files before installing.
What it does
shorts-kit turns a coding agent into a short-video studio. You tell the agent a topic and it follows the skills step by step: facts, a storytelling flow, the script, the voice, the scenes, stills to check, the render, the cover and the caption. You review the finished file and publish it yourself; the kit posts nothing. The box holds ten sk-* skills (sk-pipeline starts shorts and sk-promo starts ads), channel rules in SOUL.md tagged [measured], [default], [craft] and [hard], twenty storytelling flows and a fact ledger: a line does not enter the script until its claim has a verified record, and a linter enforces it. The Remotion library adds word-timed captions, kinetic type, safe zones, music and sound effects, camera moves, maps and a globe. Your own recording or footage can replace the synthesized voice: Whisper transcribes it and fillers and long silences are proposed as cuts. Promos follow agency-style gates: objective and placement, the user's pain, concepts, an animatic on real music, a storyboard and cutdowns of 15 and 6 seconds.
Who it is for. Authors of topic channels on TikTok, YouTube Shorts and Reels who want to assemble narrated clips in code and keep one set of channel rules.
Good fit when
- You need a 9:16 clip on a science or explainer topic with a script built on verified facts
- Narration comes from your own recording, which needs transcribing and cutting
- You need a product ad with an animatic, a storyboard and 15 and 6 second cutdowns
- You need maps with a camera flying from a country to a street and a 3D globe with routes
- The voice and caption rules of the channel should sit in one file the agent reads
Not a fit when
- You need one-off clip without channel rules: the kit is too heavy for that
- The project has no Bun and ffmpeg: assembly and rendering are built on them
- You expect the kit to pick a topic: the README says outright that you choose it
- You need publishing to social networks out of the box: the kit only prepares the file
Example request
Make a short about why the sky is blue: facts first, then the script, voice and render, and write the cover and caption lastLimitations
- Bun, ffmpeg and ffprobe on PATH are required; transcribing your own recording adds whisper.cpp and a 1.6 GB model.
- Voice defaults to free engines, ElevenLabs with ELEVENLABS_API_KEY gives the best quality in two languages; for Vietnamese VieNeu is installed into a separate Python environment.
- The rules and results in the README grew from the author's private pipeline and are defaults you tune to your own channel.
- The kit does not pick the topic: topics outside the channel niche get only hundreds of views, in the author's words.
How to disable. Delete the repository clone folder and the .claude/skills/sk-* directory if you copied the skills into another project. Other data sits in the local .env and Python environment folders.
FAQ
How do I install shorts-kit?
Run git clone https://github.com/howznguyen/shorts-kit.git and bun install in the clone folder. Install Bun and ffmpeg first: brew install bun ffmpeg on macOS.
Which agents does shorts-kit work with?
The skills sit in .claude/skills and work in Claude Code and in any agent that reads AGENTS.md, for example Codex or OpenCode.
Does the kit publish clips itself?
No. The agent prepares the file, cover and caption and you upload it. The README states this as a rule: the kit never posts anything.
Can I use my own voice for narration?
Yes, bun run ingest and bun run cut transcribe the recording with Whisper and propose cutting fillers, retakes and long silences. The words stay yours but each claim still needs a verified fact.
Which voice should I choose?
Free engines are enough to start, and bun run tts retries if an engine stops answering. ElevenLabs gives the best quality but needs a key.
Discussion
No questions or reviews yet.
Related
SkillsNine skills and a Remotion library make short vertical explainer reels in a layered paper-cut style, from strategy to render.
A skill that makes your agent film a short product video: concept, edit, sound and render on Remotion or HyperFrames
The video-explainer skill turns a script into a vertical 9:16 explainer: narration, captions, Remotion and a pre-render review
motion-video-production: a skill for motion videos
motion-video-production
A skill that takes an agent through seven stages for a 15 to 90 second video, a script checking each stage before the next
A Codex skill that turns a script or a voice recording into video with motion graphics, captions and an editable Remotion project.
Skills for faceless video channels: one topic becomes a video with voiceover, subtitles, covers and per-platform copy.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| shorts-kit (this card) | no | 141 | |
| Remotion Agent Skills | no | 6,903 | skills for Remotion itself; shorts-kit adds channel rules, a fact ledger and a promo pipeline |
| claude-faceless-shorts-creator | no | 360 | another faceless shorts skill; this has ten skills, fact checking and maps |
README in short
The page begins with a description of the process and the results of the channel the rules came from, then lists the kit: skills, SOUL.md, storytelling flows, the fact ledger, the Remotion library, maps and globe, graphics and promo gates. Then come requirements, installing Bun, ffmpeg and voice and transcription engines and a sample run with bun run tts example.
README badge
Original SKILL.md
--- name: sk-pipeline description: Orchestrates one narrated vertical short (TikTok, YouTube Shorts, Reels) from idea to upload-ready hand-off files, in the fixed order idea, facts, flow and visual choice, brief, narration, TTS, lint, scenes, still review, render, cover, normalize, encode, hand-off. Use when the user says "make a video about X", "start a new short", "take this idea to a finished video", "what's the next step", "where was I on this video", or asks how the whole pipeline fits together. Also when the user gives a video or audio file (or a folder of clips) to edit: "edit this video", "dựng video này", a .mov/.mp4 path. Points at the skill and the SOUL section that governs each step. --- # sk-pipeline: one video, idea to hand-off **Announce:** "Using sk-pipeline for <id>." ## Route first: short or promo? This skill is for narrated knowledge shorts. If the user wants an **ad, TVC, commercial, product or launch video, teaser, or any landscape (16:9) video**, use `sk-promo` instead; it has its own rules (`docs/promo/README.md`). A short can still be scaffolded with `--format landscape`, but then say plainly that SOUL's rules were written for 9:16 and that components not yet format-aware may misplace content. ## This skill is not the rules The rules live in `SOUL.md` and `docs/soul/`. This skill only fixes the **order** and points at the skill and § for each step. Where it disagrees with a §, the § wins and this file is the one to fix. Do not copy rules into skills: two copies drift and nobody knows which is current. Read `SOUL.md` first (index, three first rules, pipeline order, checklist). It holds this channel's editable defaults; changing them is `sk-improve`'s job. Then open only the § for the step you are on; do not load the whole of `docs/soul/`. Exact commands per step are in `docs/making-a-video.md`. ## The steps | # | Step | Skill | Rules | Evidence on disk before moving on | |---|---|---|---|---| | 0 | If `SOUL.md`'s change log has no entries, the rules were never adapted: offer first-run setup | `sk-improve` | `SOUL.md` | change log has entries, or user declined | | 1 | Idea: one sentence the viewer can repeat after watching | `sk-brief` | §1 | sentence written in the brief | | 2 | Facts: every claim sourced and recorded | `sk-facts` | §9 | `bun run facts` clean | | 3 | Flow + visual choice, image licences checked | `sk-brief` | §2, §5, `docs/flows/`, `docs/visuals/` | `bun run new <id> --flow <X>` done | | 4 | Brief | `sk-brief` | §2, §5 | `briefs/<id>.md` with fact ids | | 5 | Narration | `sk-narration` (polish: `sk-style`) | §1, §3, §3b, §3c | `src/videos/<id>/narration.json` | | 6 | TTS | `sk-narration` | §4 | `voice.json` + `public/audio/<id>/voice.mp3`, listened to |