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 IAPro-Community/Orquestrador-Maestro --skill skill-optimize-imagesgit clone --depth 1 https://github.com/IAPro-Community/Orquestrador-MaestroWrote 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/iapro-community/orquestrador-maestro/skill-optimize-images)<a href="https://agentmods.dev/skills/iapro-community/orquestrador-maestro/skill-optimize-images"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-optimize-images/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/iapro-community/orquestrador-maestro/skill-optimize-images"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-optimize-images.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 | $0.00049 | $0.00496 |
| Opus 5 | $0.00024 | $0.00248 |
| Sonnet 5 | $0.00010 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
skill-optimize-images 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 11d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Otimizar imagens para web
Core Workflow
- Inspect the source image and identify its format, dimensions, color profile, transparency, orientation, and current file size. Preserve the original and work on a derivative.
- Confirm the intended placement when it is not obvious: blog hero, article thumbnail, social card, logo, inline content, or responsive site asset. If no dimensions are provided, infer them from the target layout and state the assumption.
- Choose the smallest suitable output set:
- AVIF for modern browsers and strongest compression.
- WebP for broad browser compatibility.
- JPEG for photographic fallback images.
- PNG only when lossless detail or transparency is required.
- Resize to the largest useful display size, avoid upscaling, preserve aspect ratio, correct orientation, and strip unnecessary metadata. Keep transparency when it is part of the design.
- Compress while checking visual quality at 100% and at the rendered size. Prefer responsive variants (
srcset/sizes) when the asset will be used on a site. - Produce predictable filenames, report dimensions, formats, quality, and before/after file sizes, and identify the recommended HTML/CSS delivery pattern when relevant.
- Validate that the output opens correctly, has no visible artifacts, retains required transparency, and meets the target size/performance goal.
Guardrails
- Never overwrite the source unless the user explicitly requests destructive replacement.
- Do not remove credits, copyright, or licensing metadata when it is required by the project; remove only metadata that is unnecessary or privacy-sensitive.
- Do not claim visual improvement without inspecting the result. For decorative or editorial images, do not alter the subject or meaning unless requested.
- Keep output names and paths portable; do not expose private local paths in generated documentation.
Verification
- Compare source and derivative dimensions, format, byte size, and visual quality.
- Open or render each final derivative when possible.
- For a website change, check responsive rendering and confirm the asset is referenced by the intended path.
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.
- 11d ago First seen · 41 lines · 49 tokens per session scan A cd04af7d087c
skill-optimize-images is a skill published in the GitHub repository IAPro-Community/Orquestrador-Maestro (42 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 496 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
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
clawd-animation-lite
A lightweight generator for short, 1–3 second pixel animations featuring Clawd, the Claude Code mascot, shown as a small coral-orange crab. It creates a complete HTML file that can be opened in a browser.
clawd-animation
A generator for self-contained HTML pixel animations featuring Clawd, the pixel-style crab mascot of Claude Code. It turns a natural-language scene into a short looping browser animation with a background, character actions, props, and effects.
atlas-cloud-media
Generate Atlas Cloud images and videos through its asynchronous media API with schema-first model selection and credential-safe polling.
wechat-publisher
A publishing workflow for WeChat Official Accounts, the platform used to publish articles to WeChat followers, covering images, drafts, publishing, and article extraction.
HTMLPPT.skill
A workflow for turning a designed HTML page or existing web project into a multi-page presentation that runs in a browser. It keeps later slides consistent with the first page's visual style.