Borrowing it
Nothing to install: this file belongs to TheSmokeDev/taskchad-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TheSmokeDev/taskchad-os/master/.claude/skills/video-director/SKILL.mdgit clone --depth 1 https://github.com/TheSmokeDev/taskchad-osWrote 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.
[](https://agentmods.dev/skills/thesmokedev/taskchad-os/video-director)<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/video-director"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/video-director/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.
<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/video-director"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/video-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 30 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 31 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 321 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 32 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00225 | $0.05643 |
| Opus 5 | $0.00112 | $0.02821 |
| Sonnet 5 | $0.00045 | $0.01129 |
| Haiku 4.5 | $0.00022 | $0.00564 |
Grade A, and why
video-director 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Director
Turn a one-line ask into a finished, deterministic MP4: HTML/CSS + data attributes rendered frame-by-frame in headless Chrome and encoded with FFmpeg. This skill DIRECTS the pipeline; the mechanics live in the HyperFrames helper skills (referenced by name below) and are not duplicated here.
Prerequisites
- Node 18+ (
npx hyperframes, CLI 0.6.x or newer) and ffmpeg + ffprobe on PATH. - The HyperFrames helper skills installed: run
npx hyperframes skills(ornpx skills add heygen-com/hyperframes), then restart the agent session. You get:hyperframes(compositions),hyperframes-cli(init/lint/preview/render),hyperframes-media(local TTS via Kokoro, transcribe, background removal),hyperframes-registry(the catalog: 70+ transition blocks and 15 caption styles to install instead of hand-rolling),website-to-hyperframes(URL capture), plus animation skills (gsap,css-animations,three,lottie,animejs,waapi). - Optional for voiceover:
edge-tts(free neural voices, needs network) or Kokoro throughhyperframes-media(fully local). - Optional for a recurring character: any image tool that supports image EDITS with a reference image (for example, the Codex CLI image tool).
Step 1: Brief intake
Collect (ask only for what is missing; sensible defaults otherwise):
topic / niche: e.g. "World Cup group-stage hype video for my fan page"
kind: event recap | brand promo | product launch | explainer
| hype reel | surprise me (sets pacing + duration default)
audience + platform: e.g. "football fans" -> 16:9 (or 9:16 vertical, 1:1)
duration target: e.g. 30-45s (hype ~20s, promo/launch ~30s, explainer ~45s)
tone (3 adjectives): e.g. electric, communal, cinematic
brand inputs: a URL | palette + fonts | "pick for me"
imagery treatment: stylized art | real photos from their site | pure CSS
scenes (ask; photos only when a source site exists)
recurring character: yes/no (if yes: describe or provide a base image)
claims source: where facts come from (site, changelog, press page)
CTA / payoff: what the last frame asks (follow, visit, star, subscribe)
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.
- 6d ago First seen · 405 lines · 225 tokens per session scan A 52e99b74ab98
video-director is a skill published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 3d ago), licensed MIT. It adds 225 tokens to every session and 5,643 once invoked, about $0.0011 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 2026-09-03.
Other skills, from other repositories
repurpose-talk
Use when the user just gave a talk, panel, fireside chat, keynote, workshop, podcast, or webinar and wants content made from it — triggers like "I just gave a talk", "the panel is done", "just finished speaking", "turn my talk into LinkedIn posts", "repurpose this recording/transcript into posts, notes, or clips", or…
pptx
A guide for turning a paper, outline, or structured text into a PowerPoint presentation. It covers an 8–12-slide structure, concise slide points, and generation of a .pptx file.
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
image-generation
Generate images from text prompts (and optionally edit/remix input images). Use when the user asks to create, generate, draw, render, or edit an image, illustration, logo, icon, diagram, or photo.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
image-gen
Generate images from text prompts via DashScope/Qwen. Use when creating, drawing, or illustrating images.