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 greg-prospyr/thumbcraft-skills --skill thumbnail-creatorgit clone --depth 1 https://github.com/greg-prospyr/thumbcraft-skillsWrote 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/greg-prospyr/thumbcraft-skills/thumbnail-creator)<a href="https://agentmods.dev/skills/greg-prospyr/thumbcraft-skills/thumbnail-creator"><img src="https://agentmods.dev/badge/skills/greg-prospyr/thumbcraft-skills/thumbnail-creator/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/greg-prospyr/thumbcraft-skills/thumbnail-creator"><img src="https://agentmods.dev/badge/skills/greg-prospyr/thumbcraft-skills/thumbnail-creator.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 | $0.00062 | $0.01385 |
| Opus 5 | $0.00031 | $0.00692 |
| Sonnet 5 | $0.00012 | $0.00277 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
thumbnail-creator 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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thumbnail Creator
Generate professional YouTube thumbnails using AI. This skill connects to the Thumbnail Creator API to create thumbnails, analyze videos, manage creative assets, and generate SEO content.
Setup
Before using this skill, ensure you have:
- A Thumbnail Creator account at https://app.thumbcraft.io
- An API key from Settings → Developers → API Keys
MCP Configuration (Recommended)
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"thumbnail-creator": {
"url": "https://app.thumbcraft.io/api/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
REST API
Base URL: https://app.thumbcraft.io/api/v1
All requests require the header:
Authorization: Bearer YOUR_API_KEY
Available Tools
Thumbnail Generation
generate_thumbnail
Create a thumbnail from a text description.
Parameters:
prompt(required): Detailed description of the thumbnailyoutube_url(optional): YouTube URL for contextstyle_id(optional): Apply a saved styleface_ids(optional): Array of face IDs to includebrand_id(optional): Brand ID for colors/logoaspect_ratio(optional): "16:9" (default) or "9:16"
Best practices for prompts:
- Be specific about composition, colors, and emotions
- Mention text overlays explicitly if needed
- Describe the main subject's expression and pose
- Include background details
Example:
Generate a thumbnail with a surprised man looking at a giant golden trophy.
Bold yellow text says "I WON". Dark gradient background with sparkles.
Photorealistic style, dramatic lighting.
analyze_video
Analyze a YouTube video and get 5 thumbnail concepts with prompts.
Parameters:
youtube_url(required): Full YouTube URL
Returns: Video summary and 5 thumbnail concepts with:
- Title and description
- Ready-to-use generation prompt
- Emotional hook explanation
What ships with it
2 files 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.
- 12d ago First seen · 210 lines · 62 tokens per session scan A 54ad113cdf2d
thumbnail-creator is a skill published in the GitHub repository greg-prospyr/thumbcraft-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 62 tokens to every session and 1,385 once invoked, about $0.0003 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.