taskchad-os: Skill for Claude Code

.claude/skills/video-processor/SKILL.md

video-processor is a skill for Claude Code from TheSmokeDev/taskchad-os. It costs 136 tokens per session (5,072 once invoked), scanned A, original, MIT.

A video and image production toolkit for creating transcripts, subtitles, chapters, thumbnails, and social-media graphics.

In plain words
What is it for?
Use it to transcribe clips, create SRT subtitle files and chapters, generate YouTube thumbnails, and make LinkedIn or other social graphics.
Why use it?
It brings common video publishing tasks into one workflow, from understanding footage to preparing images for different platforms.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is TheSmokeDev/taskchad-os's own configuration. It tells Claude Code how to work on taskchad-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything taskchad-os configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run thumbnail.py "my video concept" -o ./custom-folder/.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/TheSmokeDev/taskchad-os/master/.claude/skills/video-processor/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/TheSmokeDev/taskchad-os

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.

agentmods badge for video-processor

README.md
[![agentmods](https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/video-processor.svg)](https://agentmods.dev/skills/thesmokedev/taskchad-os/video-processor)
Your own site
<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/video-processor"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/video-processor.svg" alt="Measured on agentmods" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,072 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00136 $0.05072
Opus 5 $0.00068 $0.02536
Sonnet 5 $0.00027 $0.01014
Haiku 4.5 $0.00014 $0.00507

Measured 3d ago against content hash ff5a4f4ffa7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

video-processor 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 3d 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/video-processor/SKILL.md · 608 lines

How it starts

The opening of the file, as written. The whole thing — 608 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Processor

Process video files for YouTube content creation and generate social media graphics. This skill provides four main capabilities:

  1. Transcription & Chapters: Convert video clips into timestamped transcripts, SRT subtitles, and AI-generated YouTube chapters
  2. YouTube Thumbnail Generation: Create AI-powered YouTube thumbnails with face references and style matching
  3. LinkedIn Post Images: Generate professional LinkedIn infographics and post images
  4. Generic Image Generation: Create custom images for any platform with flexible dimensions and prompts

When to Use This Skill

Use this skill when the user:

  • Wants to transcribe video files or clips
  • Needs to generate YouTube chapters
  • Wants to regenerate chapters from existing transcripts
  • Wants to create YouTube thumbnails
  • Wants to create LinkedIn post images or infographics
  • Wants to generate images for other platforms (Instagram, Twitter, Facebook, etc.)
  • Mentions face swapping for thumbnails
  • Asks about providing face or style references for graphics

Choosing the Right Image Generation Tool

The skill provides three image generation scripts. Choose based on platform and requirements:

Use thumbnail.py (YouTube thumbnails) when:

  • User mentions "YouTube", "thumbnail", or "video thumbnail"
  • 16:9 aspect ratio requested
  • Dramatic, eye-catching style with faces desired
  • Default: 1920x1080

Use linkedin-post.py (LinkedIn infographics) when:

  • User mentions "LinkedIn", "LinkedIn post", or "business infographic"
  • Square format infographic requested
  • Professional, dark theme, no faces
  • Default: 1200x1200

Use image-gen.py (generic) when:

  • Custom dimensions specified (Instagram, Twitter, Facebook, etc.)
  • Platform is not YouTube or LinkedIn
  • User explicitly requests flexible/custom tool
  • User provides full prompt with specific style requirements
  • Required parameter: --dimensions WIDTHxHEIGHT

Priority: Always prefer thumbnail.py or linkedin-post.py when the use case matches. Use image-gen.py as fallback for other platforms or custom requirements.

Read the full file on GitHub · 608 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 3d ago First seen · 608 lines · 136 tokens per session scan A ff5a4f4ffa7a

Subscribe to this mod's changes

video-processor is a skill published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 14d ago), licensed MIT. It adds 136 tokens to every session and 5,072 once invoked, about $0.0007 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.