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 swyxio/skills --skill latent-space-thumbnail-directorgit clone --depth 1 https://github.com/swyxio/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/swyxio/skills/latent-space-thumbnail-director)<a href="https://agentmods.dev/skills/swyxio/skills/latent-space-thumbnail-director"><img src="https://agentmods.dev/badge/skills/swyxio/skills/latent-space-thumbnail-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/swyxio/skills/latent-space-thumbnail-director"><img src="https://agentmods.dev/badge/skills/swyxio/skills/latent-space-thumbnail-director.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 | $0.00062 | $0.00576 |
| Opus 5 | $0.00031 | $0.00288 |
| Sonnet 5 | $0.00012 | $0.00115 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
latent-space-thumbnail-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 13d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Latent Space Thumbnail Director
Direct and QA Latent Space and FDE thumbnails. Use $imagegen for raster generation or editing. When the user selects $artifact-template-latent-space-fde-thumbnail, use that template as the visual starting point and this skill as the learned editorial and production layer.
Load the relevant guidance
- Read references/preferences.md for every creation, revision, or review.
- Read references/resource-index.md when locating logos, identity references, source pages, or font assets.
- Read references/example-index.md when choosing an art direction, producing variants, or comparing a result with approved work.
Workflow
- Ground the episode from the user's brief and supplied sources. Extract specific tensions, decisions, consequences, or counterintuitive claims; do not invent episode facts.
- Choose one curiosity hook, normally two to six words. Use one headline and at most one supporting visual metaphor.
- Build an explicit coverage list before generation: every requested person exactly once, every participating company exactly once, and no unrequested host.
- Use the official Latent Space logo asset and supplied identity or company references. Do not recreate an unavailable identity or wordmark from memory.
- Generate a 16:9 master with one dominant idea, one hero region, and strong mobile hierarchy. Multiple directions must vary the hook and composition, not merely color.
- Inspect the result at full size and at approximately 320 x 180. Verify headline spelling, count people and companies, check facial fidelity, wardrobe separation, LS x FDE branding, and the bottom-right duration-overlay exclusion zone.
- Repair material defects before delivery. Export a high-resolution master and an upload-ready 1280 x 720 JPG.
Non-negotiables
- Keep the bottom-right duration-overlay zone free of essential content. DAILY belongs before that zone, not at the extreme right edge.
- Do not let several dark shirts merge into the near-black background. Relight or recolor clothing while preserving faces and identity.
- Keep the official LS hex compact in the upper-right with
FDE; prefer Tachyon only when an actual Tachyon font file is available. - Preserve complete guest and company coverage. A sparse composition is not permission to drop people or logos.
- Avoid biographies, dates, paragraph copy, ornamental UI, screenshots, duplicate faces, and tiny badges unless the user specifically requests them.
What ships with it
13 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.
- agents/openai.yaml 277 B
- assets/brand/latent-space-hex-gradient.png 255 KB
- assets/examples/how-do-you-eval-a-voice-safe.jpg 273 KB
- assets/examples/outbound-beats-inbound-safe.jpg 284 KB
- assets/examples/prompts-vs-workflows-safe.jpg 256 KB
- assets/examples/voice-quality-is-solved-safe.jpg 261 KB
- assets/references/stripe-for-agents-legacy.png 777 KB
- assets/references/voice-ai-event-poster.png 825 KB
- assets/references/voice-ai-real-stage-thumbnail.jpg 189 KB
- assets/references/wayfinder-sparse.png 564 KB
- references/example-index.md 2.1 KB
- references/preferences.md 3.7 KB
- references/resource-index.md 1.9 KB
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.
- 13d ago First seen · 33 lines · 62 tokens per session scan A 462044d35d70
latent-space-thumbnail-director is a skill published in the GitHub repository swyxio/skills (160 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 576 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 2026-08-30.
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…