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 gabrielmoreira/agent-skills-mirror --skill video-thumbnail-generatorgit clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirrorWrote 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/gabrielmoreira/agent-skills-mirror/video-thumbnail-generator)<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/video-thumbnail-generator"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/video-thumbnail-generator/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/gabrielmoreira/agent-skills-mirror/video-thumbnail-generator"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/video-thumbnail-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.00641 |
| Opus 5 | $0.00024 | $0.00320 |
| Sonnet 5 | $0.00010 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
video-thumbnail-generator 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Thumbnail Generator
Use this skill to create a high-clarity thumbnail or cover image from the actual video content.
Non-Negotiables
-
Use the real video as visual evidence.
- If the thumbnail shows a person, product, UI, frame, or scene from the video, extract or inspect real frames.
- Never invent a generic software interface, fake product screen, or unrelated person.
-
Read style references before recommending styles.
- Use
references/thumbnail-styles.mdandreferences/thumbnail-style-recipes.md. - Only offer style directions supported by those references or by the user's explicit instruction.
- Use
-
Keep text short and readable.
- Usually 2-5 words.
- Avoid thin type, low contrast, small labels, and clutter.
Workflow
- Confirm platform and aspect ratio if missing.
- YouTube / Bilibili: usually 16:9.
- Shorts / TikTok / Douyin: usually 9:16.
- Xiaohongshu / WeChat Channels: usually 3:4.
- Correct ambiguous ratio language gently, especially 4:3 vs 3:4.
- Read project state, transcript, and available media context.
- Inspect candidate frames:
- expressive face
- product or UI clearly visible
- dramatic action moment
- clean composition
- strong lighting or clear subject separation
- Classify the thumbnail job:
- talking-head / opinion / tutorial
- product / software / demo
- cinematic / documentary / art
- entertainment / challenge / reaction
- education / business / concept
- Propose concise title text options.
- Offer 3-6 clearly different style directions.
- Each option should name the composition, not only a channel/style label.
- Exclude weak options.
- Wait for user choice when the direction is not obvious.
- Generate thumbnail options using selected real frames and the selected style.
- Check mobile readability, subject fidelity, product/UI truthfulness, and visual contrast.
- Present results and offer targeted adjustments.
Prompt Shape
[Platform] thumbnail, [aspect ratio / dimensions], [style name].
COMPOSITION: [subject position, scale, background, graphic balance]
REAL REFERENCE: [describe selected frame zone by zone]
TEXT: "[short title]" in [high-contrast style]
STYLE: [one-line style recipe from references]
CONSTRAINTS: readable at mobile size, no fake UI, no watermark, no play button.
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 · 69 lines · 48 tokens per session scan A 77bcf1f26ec6
video-thumbnail-generator is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 641 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…