What is make-ai-short?

A workflow for making looping vertical videos with AI-generated images and video clips, narrated voice-over, sound effects, and timed captions. It uses Remotion, a tool for assembling videos with code.

It helps create 35–40-second portrait shorts for social media, including the character reference, narration, captions, sound effects, compositing, and final render.

It keeps a recurring character visually consistent and checks the loop, timing, and production cost before generating media.

make-ai-short — Skill for Claude Code by hassancs91

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add hassancs91/claude-faceless-shorts-creator --skill make-ai-short

Clone the repo

git clone --depth 1 https://github.com/hassancs91/claude-faceless-shorts-creator

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hassancs91/claude-faceless-shorts-creator/make-ai-short/github.svg)](https://agentmods.dev/skills/hassancs91/claude-faceless-shorts-creator/make-ai-short)

Your own site

<a href="https://agentmods.dev/skills/hassancs91/claude-faceless-shorts-creator/make-ai-short"><img src="https://agentmods.dev/badge/skills/hassancs91/claude-faceless-shorts-creator/make-ai-short/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hassancs91/claude-faceless-shorts-creator/make-ai-short"><img src="https://agentmods.dev/badge/skills/hassancs91/claude-faceless-shorts-creator/make-ai-short.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,726 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00180	$0.01726
Opus 5	$0.00090	$0.00863
Sonnet 5	$0.00036	$0.00345
Haiku 4.5	$0.00018	$0.00173

Measured 12d ago against content hash fd94e873b3ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

make-ai-short scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/make-ai-short/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

make-ai-short — generative shorts, end to end

The pixels come from a video model; Remotion only composites clips + captions. Proven on blue-man #1 "The Door". Sibling of /make-short (100% TSX) — same discipline, plus three gates TSX never needed: cost stated before generating, character locked from character.json, loop pinned via end-frame conditioning.

Run everything from the repo root. Needs FAL_KEY (clips + images) and ELEVENLABS_API_KEY (voice) in .env.

The three iron rules

NEVER generate a character from text twice. ai-shorts/<char>/character.json + character.png is the locked reference. Every still that needs the character is gen_image.py --ref character.png; every clip is image-to-video from a frame that already contains him. If a character sheet doesn't exist yet, making ONE (and getting the user's eye on it) is its own step before anything else.
STATE THE COST BEFORE SPENDING IT. Derived, not quoted: Seedance 1080p audio-off = h×w×24×dur/1024 tokens × $1.2/1M ≈ $0.0583/s (fal pricing API validated 2026-07-14 — see ai-shorts/IDEAS.md for the full table + the Wan/Veo-Lite traps). Always generate_audio:false — voice is ElevenLabs, sound is our SFX pipeline.
Loop by CONSTRAINT, not luck. Shot 1's true frame 0 (extracted from the clip, not the prompt image) is the loop target. The final shot passes it as end_image_url (Seedance/Kling), and the composition settles onto that exact still over the last ~10 frames (LoopSettle pattern in remotion/src/shots/ai-1/Ai1Door.tsx).

Artifact contract

ai-shorts/<name>/
  script.md · beats.json      — same contract as /make-short (vo[] with real word times)
  character.json              — THE LOCKED REFERENCE (+ video_model block = the picked model)
  shots/NN-slug.png           — per-shot START frame (gen_image.py --ref character.png [--ref scene])
  shots/NN-slug.json          — gen_clip sidecar (model, payload, request id)
  shots/upload-urls.json      — fal storage urls (uploads are reusable across re-rolls)
  voice/ · sfx-plan.json · output/                                          [voice/output gitignored]
remotion/src/shots/ai-N/      — composition + vo.gen.ts
media/projects/<name>/        — THE clip copies for staticFile() (committed — pixels are
                                not reproducible; shots/*.mp4 working copies are gitignored)

Read the full file on GitHub · 90 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 90 lines · 180 tokens per session scan A fd94e873b3ec

Subscribe to this mod's changes

make-ai-short is a skill published in the GitHub repository hassancs91/claude-faceless-shorts-creator (232 stars, last pushed 24d ago), licensed MIT. It adds 180 tokens to every session and 1,726 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Creative and media agent-skills ai-video claude content-automation elevenlabs

verticals

AI-native vertical video engine with niche intelligence. Takes a one-line topic and a niche profile, and outputs a finished YouTube Short/Reel/TikTok with AI-generated b-roll, voiceover, burned-in captions, background music, and thumbnail. Supports multiple LLM providers (Claude, Gemini, GPT, Ollama), TTS providers…

rushindrasinha/youtube-shorts-pipeline · 93 tokens

creative-theme-generator

Converts any user input into structured creative themes for AI video generation. Handles: natural language descriptions, keywords, long-form text extraction, partial fields, random generation, and batch test tasks. Outputs standardized 12-field JSON (taskid, type, theme, description, durationsec, creativestyle, tone…

geniusdapeng-collab/super-mickey · 126 tokens

ai-film-studio

AI film production studio with pre-built scripts: analyze inspiration/reference videos (Gemini), write script + storyboard, generate stills (GPT Image 2; Seedream 5 / Nano Banana as fallbacks), video (Gemini Omni 1.1 Flash, FLUX 3 Video, Seedance 2.5/2.0, LTX 2.5/2.3; Veo 3.1 fallback), audio (ElevenLabs), and…

realaman90/ai-film-skills · 214 tokens

make-ai-short