glm-vision SKILL.md skillA

glm-vision from noah-1106/skills_repo is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add noah-1106/skills_repo/glm-vision@git:20260908.5db9d66

Pins git:20260908.5db9d66 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
noah-1106/skills_repo
Path
skills/glm-vision/SKILL.md
Versions recorded
1
Latest version
git:20260908.5db9d66, committed Sep 8, 2026
Size
2,966 bytes
Repository stars
32
License
MIT

智谱 GLM-5.3-flash 视觉理解 CLI。输入图片(本地路径 / URL / 多图)+ 提问,输出文字或 JSON 分析。模型、端点、API Key 全部走 config.json 可换。用于截图理解、图表解读、图片问答、OCR 式提取。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# glm-vision 视觉理解

## 场景

- 截图/界面理解(UI 描述、元素识别、转代码前置分析)
- 图表/数据图解读
- 图片内容问答、信息提取(--json 结构化输出)
- 多图对比(≤5 张)

## 触发条件

用户给出图片(路径或 URL)并要求理解、描述、分析或提取信息时。

## 输入

- 图片:本地路径(自动转 Base64)或 URL(智谱服务端拉取);jpg/png/webp/gif,单张 ≤10MB
- **视频**:本地文件(mp4/mov/avi/mkv/webm,≤50MB,自动转 Base64)或 URL 直传
- 提问:`--prompt`(默认"详细描述这张图片的内容")
- `--json`:要求模型只输出合法 JSON
- `--max-tokens N`:覆盖 config(reasoning 也占此预算,复杂问题适当调大)
- `--download`:图片 URL 强制本地下载转 Base64(智谱服务端拉取国外源失败时用)

## 步骤

1. 确认图片路径/URL 有效
2. `python3 scripts/glm_vision.py <图片...> [--prompt "..."] [--json]`
3. stdout 取结果;stderr 看诊断(--show-usage 可打印 token 用量与延迟)

## 判断标准

- 输出为空 → stderr 会有明确错误(401 key / 429 限流 / 空回答提示加大 max_tokens)
- 多图 >5 张会提示质量风险

## 输出

stdout:模型回答文本(或 JSON 字符串)。错误写 stderr 且退出码非 0。

## 异常处理

| 症状 | 处理 |
|---|---|
| 401 | key 无效 → 检查 config.json 或环境变量 GLM_VISION_API_KEY |
| 429 | 限流(实测上限约 5 QPS)→ 间隔 1-2s 重试 |
| 1210 图片解析错误 | 图片文件损坏或非图片(先 magic bytes 验证);或 URL 是国外源智谱拉不动 → 加 --download |
| URL 图报"type 参数非法" | 智谱服务端拉取该 URL 失败的误导性报错(多为国外源)→ 加 --download 本地下载 |
| 空回答 | max_tokens 被 reasoning 吃满 → 加大 max_tokens |

## 实测边界(2026-09-02)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add noah-1106/skills_repo/glm-vision@sha256:b8096822f921b3f3

The line at the top of this page pins the label git:20260908.5db9d66, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_65xhgr2givzdhr3t.svg)](https://markdownregistry.com/a/art_65xhgr2givzdhr3t)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 8, 2026.

versioncommittedcommitsizeaudit
git:20260908.5db9d66 latest2026-09-08 5db9d66 2,966 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2966 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

noah-1106/skills_repo · 32 stars · license MIT · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_65xhgr2givzdhr3t
GET https://markdownregistry.com/api/v1/resolve?ref=noah-1106/skills_repo/glm-vision
GET https://markdownregistry.com/api/v1/blob/b8096822f921b3f3a93731c4d5901065cb43ba21c57fea12667e73d62d038ddd

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from noah-1106/skills_repo

baidu-hot-cn SKILL.md skill
noah-1106/skills_repo · skills/baidu-hot-cn-1/SKILL.md · 百度热榜监控 | Baidu Hot Topics Monitor. 获取百度热搜榜、搜索趋势、关键词热度 | Get Baidu trending searches, trends, keyword popularity…
git:20260315.1f042ba · audit A · 32 stars
coze_workflow SKILL.md skill
noah-1106/skills_repo · skills/coze-workflow-1.1.3/SKILL.md · Coze Workflow Executor | Coze 工作流执行技能 Execute Coze workflows with workflow_id and parameters. 接收参数调用工作流,返回执行结果。 Pure…
v1.1.3 · audit A · 32 stars
douyin-hot-trend SKILL.md skill
noah-1106/skills_repo · skills/douyin-hot-trend-1/SKILL.md · 抖音热榜获取技能 | Douyin Hot List Fetcher 获取抖音热榜/热搜榜数据 | Get Douyin hot list/trending data 包含热门视频、挑战赛、音乐等多领域热门内容 | Includes…
v1.0.1 · audit A · 32 stars
ec_creator SKILL.md skill
noah-1106/skills_repo · skills/ec_creator/SKILL.md · Execution Card Linter & Validator with Auto-Fix | 执行卡片检查与自动修复工具 A validation and correction tool for creating…
v1.1.0 · audit A · 32 stars
geopulse SKILL.md skill
noah-1106/skills_repo · skills/geopulse/SKILL.md · 自托管的 AI 品牌可见性监测系统(完整前后端,skill 内自带)。监测品牌在 AI 引擎(DeepSeek/智谱/通义/Kimi 等)回答中的可见率、声量份额、引用深度(提名/描述/推荐)、四维热力图(品牌词/场景词/对比词/选购词),…
git:20260907.8ec6508 · audit A · 32 stars
glm-asr SKILL.md skill
noah-1106/skills_repo · skills/glm-asr/SKILL.md · 智谱 GLM-ASR-2512 语音转文本 CLI。输入音频文件(wav/mp3,≤25MB,≤30秒),输出转录文本,支持热词表(专有名词/项目代号提升识别率)与上下文提示。模型、端点、API Key 全部走 config.json…
git:20260907.32b6c64 · audit A · 32 stars
image_gen_coze SKILL.md skill
noah-1106/skills_repo · skills/image-gen-coze-1.1.3/SKILL.md · Image Generation via Coze | 基于 Coze 的图像生成技能 Generate images using Coze workflows. 使用 Seedream 4.5 model. Handles…
v1.1.3 · audit A · 32 stars
longtask_system SKILL.md skill
noah-1106/skills_repo · skills/longtask_system/SKILL.md · 长程任务执行管理系统 | Long-running Task Execution Management System 通过状态文件驱动,将长任务拆分为子任务,由守护进程按顺序触发执行,确保每步完成后再执行下一步。 State-file…
v1.2.2 · audit A · 32 stars
minimax-av SKILL.md skill
noah-1106/skills_repo · skills/minimax-av/SKILL.md · MiniMax 全模态理解 CLI,双子命令。transcribe:音频转文本(asr-1.0,8 种格式 ≤50MB/≤500s,支持 SRT/VTT 字幕与说话人分离时间戳);understand:视觉理解(MiniMax-M3…
git:20260908.5ebc0ca · audit A · 32 stars
rss_fetcher SKILL.md skill
noah-1106/skills_repo · skills/rss_fetcher/SKILL.md · 统一的RSS采集与管理系统 | Unified RSS Feed Fetcher and Manager 支持增量抓取、自动去重、自动标签、源健康监控、HTML报告生成 Incremental fetching, auto-dedup…
v1.1.0 · audit A · 32 stars
scribe SKILL.md skill
noah-1106/skills_repo · skills/scribe/SKILL.md · 本地录音转写工具:音频/视频文件 → 带时间戳的文字稿(TXT/SRT/JSON),可选说话人标记。 每当用户提到以下场景,务必使用本技能(即使没提工具名): -…
git:20261012.f64d7db · audit A · 32 stars
skills-hub SKILL.md skill
noah-1106/skills_repo · skills/skills-hub/SKILL.md · Discover, search, install, and update skills from the ClawHub marketplace for the user's ExFlower environment. Use when…
git:20260830.7e1f962 · audit A · 32 stars

Every file in noah-1106/skills_repo

Browse by kind, by grade A, or by owner.