asset-optimization

asset-optimization is a skill for Claude Code from simiancraft/simiancraft-skills. It costs 241 tokens per session (2,100 once invoked), scanned A, original, MIT.

A procedure for reducing the file size of media and other assets while keeping them suitable for their intended use. It covers files such as images, vectors, animations, video, audio, documents, fonts, and models.

In plain words
What is it for?
Use it to classify assets, select compression tools, optimize files individually or in batches, preserve originals, and measure the resulting size.
Why use it?
It helps limit download and storage costs by choosing an appropriate format and compression method for each file and display context.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the simiancraft-skills plugin — 16 skills, 4 agents shipped together

Good fit Use it to classify assets, select compression tools, optimize files individually or in batches, preserve originals, and measure the resulting size.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/simiancraft/simiancraft-skills/asset-optimization
Install

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.

Any agent
npx skills add simiancraft/simiancraft-skills --skill asset-optimization
Clone the repo
git clone --depth 1 https://github.com/simiancraft/simiancraft-skills

Made for: Claude Code.

Or install simiancraft-skills, the plugin that ships this one along with the rest of its 16 skills, 4 agents.

Wrote 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.

agentmods badge for asset-optimization

README.md
[![agentmods](https://agentmods.dev/badge/skills/simiancraft/simiancraft-skills/asset-optimization/github.svg)](https://agentmods.dev/skills/simiancraft/simiancraft-skills/asset-optimization)
Your own site
<a href="https://agentmods.dev/skills/simiancraft/simiancraft-skills/asset-optimization"><img src="https://agentmods.dev/badge/skills/simiancraft/simiancraft-skills/asset-optimization/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.

agentmods 80×15 button for asset-optimization

Your own site · 80×15
<a href="https://agentmods.dev/skills/simiancraft/simiancraft-skills/asset-optimization"><img src="https://agentmods.dev/badge/skills/simiancraft/simiancraft-skills/asset-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 241 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,100 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00241 $0.02100
Opus 5 $0.00120 $0.01050
Sonnet 5 $0.00048 $0.00420
Haiku 4.5 $0.00024 $0.00210

Measured 10d ago against content hash 8581fe0a1564, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

asset-optimization 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 10d 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.

skills/asset-optimization/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Asset Optimization

The smallest asset that still serves its purpose. Measure the bytes, not the intent.

An asset is a media file whose bytes we shrink without changing what it is for. This skill is a lookup keyed on the asset's kind that decides format, tool, and whether the pass may lose information, so the file ends up as small as it can be while still doing its job on the surface it will be presented on.

Structure. Each kind is an executor under executors/<kind>/, a folder of standardized organs: procedure.md (the how-to, including prerequisites and cross-kind redirects), cookbook.md (curated verbatim recipes), targets.md (surface to format), and expectations.md (measured size data). The cross-cutting references at the root are tools.md (the tool manifest, defined once because one tool serves many kinds), surface.md (which surface), classify.md (how to detect a file's kind), batch.md (repository operation, originals, idempotence, report), and cookbook.md (the recipe rubric and an index of every kind's cookbook). This two-level structure is deliberately heavier than the flat references/ layout of the repo's other skills, because this skill has more orthogonal axes than any sibling: kind, surface, fidelity intent, and tool.

Fidelity intent (decide first; it gates every tool)

Intent Meaning Consequence
Lossless-required a pixel, sample, path, or vertex is load-bearing (design fidelity, a diff, evidence) only lossless tools; never quantize or re-encode lossy
Lossy-acceptable the asset carries an impression, not exact bytes (walkthrough, delivery, thumbnail) lossy tools are in play, tuned to "looks the same to the viewer who judges it"

If compression would change what the asset is for, it is lossless-required by definition. Optimize for "looks exactly the same to the person who will judge it."

Read the full file on GitHub · 133 lines

Files

What ships with it

38 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.

Changes

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.

  1. 10d ago First seen · 133 lines · 241 tokens per session scan A 8581fe0a1564

Subscribe to this mod's changes

asset-optimization is a skill published in the GitHub repository simiancraft/simiancraft-skills (7 stars, last pushed 6d ago), licensed MIT. It adds 241 tokens to every session and 2,100 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.

Related

Other skills, from other repositories

nano-banana-prompting

This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need guidance on prompt structure, or want to optimize their prompts for better results.

NikiforovAll/claude-code-rules · 51 tokens

nano-banana

This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation…

NikiforovAll/claude-code-rules · 73 tokens

jina-image-search

Find and scrape images from the web using Jina AI. Use this skill when the user asks to find images, search for photos, get pictures from Unsplash/Pexels/Pixabay, needs stock photos for presentations, websites, or designs, or mentions finding images online.

adamjali/claude-skills · 61 tokens

speech-generation

Generate text-to-speech audio using the ElevenLabs MCP server's texttospeech tool. Use when the user asks to create voiceovers, narration, audio from text, spoken dialogue, podcast-style audio, audiobook readings, announcements, or voice content. Supports voice selection by name or ID, multiple models (multilingual…

lukaskellerstein/claude-my-marketplace · 87 tokens

visual-planning

ALWAYS use this skill FIRST, before producing or fetching ANY media asset — an image, video/GIF, chart, graph, diagram, infographic, SVG/icon, music, or speech/voiceover — and before any stock-photo search. It is the mandatory pre-generation gate. For a SINGLE asset it runs a short brief — clarify the ask → confirm…

lukaskellerstein/claude-my-marketplace · 271 tokens

media-prompt-craft

Craft effective prompts for AI image/video generation and search queries for stock photo services. Translates design direction and styleguide choices into specific, style-consistent prompts. Use when the user asks to "find images for my site", "generate a hero image", "what kind of images should I use", "create image…

lukaskellerstein/claude-my-marketplace · 112 tokens