By TriDefenderUpdated 2026-05-18multimodal@clawhub_tridefender/multimodal
Tool Use#文档
According to AlphaMoat, as of 2026-09, GLM Multimodal Analyzer has 1,661 downloads and 0 stars — ranked #4,667 of 5,078 AI skills overall, and #910 of 969 in AI Agent.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| ClawHub ↗ | 44 | 1.5K | - | 2 |
| SkillHub ↗ | 144 | 1.7K | - | — |
Platforms count differently. AlphaMoat’s totals use the higher figure across platforms, not the sum.
An analysis script handles image questions, video summaries and PDF or table content, with thinking and streaming options. The source limits each request to one modality and requires publicly accessible video URLs.
Profile published 2026-10-26
Generated from the skill’s documentation as examples; not results of actual runs.
Compiled from what the skill’s documentation declares; not verified by installing or running it.
ZHIPU_API_KEY environment variable.ZHIPU_API_KEYpythonFrom 2026-09 the figures use the current method (full catalog). Earlier months use the legacy method (only skills with installs, same-name skills merged). The two are not directly comparable, so the chart does not connect them or compute growth across them.
| Month | Downloads | MoM | Stars | Installs |
|---|---|---|---|---|
| 2026-09 | 1.7K | — | - | 144 |
| 2026-08Legacy method | 1.5K | +5.7% | - | 144 |
| 2026-07Legacy method | 1.4K | — | - | 144 |
| 2026-05Legacy method | 1.0K | — | - | 144 |
| 2026-03Legacy method | 493 | — | - | 82 |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
--- name: Multimodal Analyzer slug: multimodal version: 1.0.0 description: 使用GLM-4.6V模型进行多模态内容理解（图片、视频、文档） --- # Multimodal Understanding Skill 使用智谱GLM-4.6V模型理解图片、视频、文档内容。 ## 功能 - 图片理解：OCR、场景分析、物体检测、属性识别 - 视频理解：内容摘要、关键帧分析 - 文档理解：PDF、复杂表格解析 - 深度思考模式：开启后进行深层推理分析 ## 使用方式 ``` 理解这张图片：[图片URL或本地路径] 分析这个视频：[视频URL] 这个PDF讲什么：[PDF URL] ``` ## 技术细节 - 模型：GLM-4.6V (106B, 128K上下文) - API端点：https://open.bigmodel.cn/api/paas/v4/chat/completions - 需要ZHIPU_API_KEY环境变量 ## 限制 - 不支持同时处理图片+视频+文件（只能选一种模态） - 视频URL需要公网可访问 ## 调用脚本 调用 `scripts/analyze.py` 进行分析： ```bash python scripts/analyze.py --type image|video|file --input <url_or_path> --prompt "你的问题" ``` 参数： - `--type`: 输入类型 (image/video/file) - `--input`: URL或本地文件路径 - `--prompt`: 分析提示词 - `--thinking`: 启用深度思考模式 - `--stream`: 流式输出
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude rea
场景驱动+关键词双模式技能发现工具。当用户用自然语言描述场景/需求（如"我想做一个海报""帮我分析股票"），或明确说"安装技能/find skills/找个skill"时，自动从官方内置、本地已安装、SkillHub、虾评、GitHub、ClawHub 六层联合搜索并推荐最合适的技能，支持一键安装。已完全替代官方...
A browser-automation command line skill for AI agents.
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.