image-reading

image-reading is a skill for Claude Code, Codex from jing-hy/picturereader-zcode. It costs 72 tokens per session (2,007 once invoked), scanned A, original, MIT.

An image-reading workflow for examining pictures, identifying subjects, checking text, judging materials, and combining the findings into a description.

In plain words
What is it for?
Use it to describe images, read text in them, inspect specific regions, and compare visual evidence across images.
Why use it?
It provides a structured way to inspect images and distinguish directly observed details from guesses.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/jing-hy/picturereader-zcode/image-reading
Any agent
npx skills add jing-hy/picturereader-zcode --skill image-reading
Clone the repo
git clone --depth 1 https://github.com/jing-hy/picturereader-zcode

Made for: Claude Code, Codex.

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 image-reading

README.md
[![agentmods](https://agentmods.dev/badge/skills/jing-hy/picturereader-zcode/image-reading.svg)](https://agentmods.dev/skills/jing-hy/picturereader-zcode/image-reading)
Your own site
<a href="https://agentmods.dev/skills/jing-hy/picturereader-zcode/image-reading"><img src="https://agentmods.dev/badge/skills/jing-hy/picturereader-zcode/image-reading.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,007 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00072 $0.02007
Opus 5 $0.00036 $0.01004
Sonnet 5 $0.00014 $0.00401
Haiku 4.5 $0.00007 $0.00201

Measured 3d ago against content hash 24ab81cd0249, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

image-reading 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 3d 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/image-reading/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

读图方法论(image-reading)

目标:像多模态模型一样"看"图并输出连贯描述,每个结论可追溯、可验证。 本 skill 由 experience / skill / principle / insight 四层知识构成(按 Gogomoe 知识框架分类,教训均来自对真实图片的实测复盘)。

操作流程(skill)

1. 全局定调(第一轮扫描)

用默认参数(size=40)全图扫描,读四个字段:

  • hue families(最高优先级):按纯色相分族的真实占比。暗调/低饱和场景的 真实颜色只在这里——colors by area 灰白占比高不代表画面灰白。
  • structure:平行条带/对称性(解读见 insights)。
  • texture:rough 高=写实照片;smooth 高=扁平或水面/天空/雾(见 insights)。
  • regions:大结构的位置/大小/颜色。

2. 找主体(全局→局部,主动验证)

  • 颜色异常区、深色大块、相邻竖长色块、小色块密集区px_per_cell 定向放大 (值越小越细:8-12 看轮廓,4-6 看结构,2-3 看细节;区域不够小时工具会提示实际密度,缩小 focus/region 重试)。
  • 放大后按形状解读:头+肩+躯干=人物;弧线+对称明暗=圆柱/球/装置; 竖直细长结构=石柱/塔/杆;交替细条=面板/栅格。
  • 主体可能与背景低对比而"隐形"(见 insights 4)——怀疑处必须放大确认,不能因 regions 未单列就跳过。

3. 文字验证

  • 疑似文字/标识/UI → image_ocr(region/focus 限定)。
  • Windows 引擎读不出但怀疑有字 → engine="paddle" 重试(发光/弯曲/游戏渲染文字)。
  • OCR 结果优先于模型描述(见 insights 3)。

4. 材质判断

image_sample 对小块区域 8×8 取样,看 RGB 分布与 contrast 统计 (平滑渐变=天空/皮肤/水面;高对比条纹=金属/木纹;暗绿 G>R>B=植物/涂装)。

5. 综合描述

输出连贯描述(场景/主体/环境光线/细节),每个结论标注证据等级: 实锤(有像素/OCR/取样数据)vs 推断(基于结构推测,用"看起来像")。 优先引用具体数字;不确定就说不确定,绝不编造。

行为准则(principles)

  1. 证据分级:任何结论标注"实测"或"推断";推断必须说明依据。
  2. 数字优先:用具体指标("蓝色调 74%""对称 80%""OCR 读出 1.00")支撑描述,不用模糊形容词代替。
  3. 先全局后局部:第一轮定调,第二轮定向放大验证,不跳步。
  4. 怀疑即验证:对任何"可能漏掉的主体",用放大/取样/OCR 验证后再下结论。
  5. 不编造:不确定就说明;模型(含多模态)的描述不可直接当作事实(见 insights 3)。

规律性洞察(insights,跨图归纳)

  1. 暗调场景的真实颜色只在 hue families 里:低饱和/暗色调(暮色、雾中、夜景) 会被 14 色色板压成灰黑,colors 的灰白占比是假象——hue families 按纯色相分族不受影响。
  2. 高对称 ≠ 一定人造物:水面倒影/镜像构图也高度对称。区分看:平滑大面积 (水面/天空 smooth 高)+ 水天分界线(上亮下暗、上下镜像)+ 竖直细长结构(石柱) = 湖泊/自然镜像;纹理复杂、颜色单调、几何硬边 = 人造建筑/装置。
  3. 小模型读小字不可靠:多模态小模型对低分辨率文字会幻觉(全图"读出"内容、 裁剪后承认没有);发光/弯曲/艺术字 Windows OCR 也失效——文字一律以 OCR 实读为准
  4. 低对比主体"隐形":暗色物体(如深色服装人物)在暗背景中融入背景黑块, 粗网格和 regions 都不会标出——对深色区域主动放大是唯一可靠发现方式。
  5. 平滑大面积 ≠ 扁平简笔画:水面、天空、雾气、墙面都平滑(smooth 高), 需结合色调/结构/场景判断,不能仅凭 smooth 判定"扁平"。
  6. "像什么"和"是什么"要分开:结构证据(对称/形状/色调)支撑"像什么"; "是什么"需要 OCR/取样/更强证据,不满足时保持推断。
  7. hue families 是场景类型指纹(34 张图训练归纳):
    • cyan 高(>60%)= 水/雾/湖泊/晨雾场景(东方水景、浓雾遗址)
    • green 高(>40%)= 森林/竹林/草地/苔藓
    • orange 或 red 高 = 红披风/暖色服饰人物、火光、晚霞
    • blue 高(>70%)= 夜晚/冷色科幻场景
    • achromatic 高 + rough 高 = 废墟/岩石/暗环境
    • green + yellow 双高 = 翠绿能量带/发光植被/浮空仙境
    • 对称高 + 中央竖直结构 = 中央主体(瀑布/树/大门)居中构图
  8. 多模态模型的颜色描述对"发光/能量"不可靠(训练中反复出现):把实测为 cyan/blue/green 的冷色发光(屏幕光、能量屏障、雾中光柱)系统性说成"粉红/紫色"。 发光元素的颜色一律以 hue 实测为准。
  9. 人物识别信号:orange/red 主调 + 局部暖色小块 + 对称 = 人物服饰候选; 游戏角色常穿红/橙(红披风、红发、暖色战斗服),识别到暖色主调时应主动放大找人物。
  10. 品牌/游戏名/标题文字:多模态模型会猜错("原神""崩坏3"实际是明日方舟终末地), 必须 PaddleOCR 实读(游戏 HUD 底部常带游戏名/参数/水印)。

Read the full file on GitHub · 97 lines

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. 3d ago First seen · 97 lines · 72 tokens per session scan A 24ab81cd0249

Subscribe to this mod's changes

image-reading is a skill published in the GitHub repository jing-hy/picturereader-zcode (2 stars, last pushed 17d ago), licensed MIT. It adds 72 tokens to every session and 2,007 once invoked, about $0.0004 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

vision

Nested swiss-knife reference for image understanding — a decision tree that routes between three paths depending on what the agent has access to: (1) the built-in vision tool if the LLM provider supports image input, (2) the sibling minimax-cli reference if a usable MiniMax preset/key slot is available, or (3) a local…

Lingtai-AI/lingtai · 120 tokens

paper-image-extractor

Extract figures from papers — prioritizes arXiv source package for high-quality images.

LigphiDonk/Oh-my--paper · 21 tokens

glmv-stock-analyst

股票分析与涨跌预测分析。 在用户表达分析、判断或预测意图时触发,如“分析一下腾讯”、“0700最近走势如何”、“XX能不能买”、“预测一下后续走势”、“生成一份分析报告”等; 支持港股、A股、美股,整合多源数据(包括新闻、基本面、技术面、资金流及宏观信息)进行多维综合分析,输出图文结合、包含可视化图表的结构化分析报告。 对于简单查询类需求(如“腾讯当前价格是多少”、“茅台代码是什么”)不触发本skill, 直接通过websearch 能力搜索并总结。 ⚠️ 需要多模态主模型支持(如 glm-5v-turbo),主模型需能读取图片。.

zai-org/GLM-skills · 178 tokens

glmv-web-replication

Frontend visual replication skill. Explores a target website’s publicly visible pages via Playwright MCP or agent-browser, captures screenshots and layout information, then generates a static or client-side frontend replica that approximates the original’s visual appearance and page structure. This skill replicates…

zai-org/GLM-skills · 151 tokens

glm-image-gen

Official skill for generating high-quality images from text prompts using ZhiPu GLM-Image API. Excellent at scientific illustrations, high-quality portraits, social media graphics, and commercial posters. Supports multiple aspect ratios, HD quality, and watermark control. Use this skill when the user wants to generate…

zai-org/GLM-skills · 80 tokens

glmv-pdf-to-ppt

Convert a PDF (research paper, report, or any document) into a polished multi-slide HTML presentation with a structured outline JSON and summary markdown. Trigger this skill when the user mentions making slides or a PPT from a PDF — in Chinese or English.

zai-org/GLM-skills · 58 tokens