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.
npx skills add toolbox-playground/super-claudio --skill video-script-and-slidesgit clone --depth 1 https://github.com/toolbox-playground/super-claudioWrote 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/toolbox-playground/super-claudio/video-script-and-slides)<a href="https://agentmods.dev/skills/toolbox-playground/super-claudio/video-script-and-slides"><img src="https://agentmods.dev/badge/skills/toolbox-playground/super-claudio/video-script-and-slides/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/toolbox-playground/super-claudio/video-script-and-slides"><img src="https://agentmods.dev/badge/skills/toolbox-playground/super-claudio/video-script-and-slides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00232 | $0.01107 |
| Opus 5 | $0.00116 | $0.00553 |
| Sonnet 5 | $0.00046 | $0.00221 |
| Haiku 4.5 | $0.00023 | $0.00111 |
Grade A, and why
super-claudio:video-script-and-slides 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 9d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Script and Slides — Material for Self-Recorded Videos
You prepare everything a person needs to record an authentic talking-head video about a topic: a natural spoken script and a local HTML presentation to show on screen. The human records; you research and structure. Warm, direct tone — a creator speaking to their audience, not a corporate ad.
Core Principles
- Real data only. Every number, course, price, or claim comes from internet research with the source verified NOW (fetch the page; confirm it says what you cite). If you can't verify it, don't put it in the material. No invented stats, ever.
- The script serves a human speaker. Talking points and key phrases in natural spoken register — not an essay to memorize. The presenter reads it once and talks over the slides.
- One slide ≈ one minute. A 5-minute video = ~5 content slides. Succinct: big type, few words, one idea per slide. The speaker delivers the details, not the slide.
What the user controls (parse from the request)
| Parameter | Default | Notes |
|---|---|---|
| Topic | required | A sentence or theme; may be part of a series ("Dicas de carreira: …") |
| Duration | 5 min | drives slide count: ~1 slide per minute + cover and closing |
| Language | language of the user's request | script and slides |
| Output dir | ~/Movies/video-talks/<slug>/ |
ask only if the user hints elsewhere |
Pipeline (always in this order)
- Research — WebSearch for real facts; WebFetch/verify every source; collect 4–8 concrete data points with source name + date
- Script — script.md: hook, one section per slide with talking points + timing, transitions, closing CTA
- Slides — slides.html: single local file (HTML+CSS+JS inline), keyboard-only navigation, real SVG logos, data with cited sources
- Publishing kit — youtube.md (title options, full description with chapters and links, hashtags) + capa.html (1–2 thumbnail mockups, 16:9)
- Verify + deliver — open/screenshot slides and thumbnails, check every slide renders, deliver all 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.
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.
- 9d ago First seen · 86 lines · 232 tokens per session scan A d972b90dee80
super-claudio:video-script-and-slides is a skill published in the GitHub repository toolbox-playground/super-claudio (4 stars, last pushed today), licensed MIT. It adds 232 tokens to every session and 1,107 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
pillow
Manipulate images locally using Python and PIL/Pillow. Use when the user asks to resize, crop, rotate, flip, filter, enhance, combine, overlay, watermark, add text to, convert, compress, create, or edit images locally. Also use for thumbnails, borders, color adjustments, transparency, animated GIFs, or extracting…
image-generation
Generate images from text descriptions using AI. Use when the user asks to create, generate, draw, or design an image, illustration, icon, or any visual content.
instrument-maker
Expert-level Traditional Instrument Maker skill with deep knowledge of Chinese and Asian traditional instrument making. Transforms AI into a master luthier with 25+ years of experience in crafting plucked, bowed, and wind instruments. Use when: crafts, instrument-making, traditional-music, woodcraft, acoustic-design.
tattoo-artist
Professional tattoo artist with 15+ years in custom tattoo design, all styles, skin preparation, and health/safety protocols. Use when: crafts, skilled-trades, tattoo, body-art, tattoo-design.
illustrator
Master illustrator with 15+ years in editorial, children's books, advertising, graphic novels, and entertainment concept art. Provides visual concept development, composition guidance, digital painting techniques, and client brief interpretation. Use when users request illustration, digital painting, character design…
livestreamer
Elite livestreamer with 8+ years in gaming, entertainment, and live-commerce streaming. Specializes in audience retention, real-time engagement, monetization, and building sustainable streaming careers.