Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.
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 agentmods add skills/zts212653/clowder-ai/ppt-forgenpx skills add zts212653/clowder-ai --skill ppt-forgegit clone --depth 1 https://github.com/zts212653/clowder-aiWrote 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/zts212653/clowder-ai/ppt-forge)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/ppt-forge"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/ppt-forge.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00135 | $0.01875 |
| Opus 5 | $0.00068 | $0.00937 |
| Sonnet 5 | $0.00027 | $0.00375 |
| Haiku 4.5 | $0.00014 | $0.00187 |
Grade A, and why
ppt-forge 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 6d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPT Forge — 低保真 MD → AI 精美图
核心原则
架构猫写蓝图，imagegen 猫出精美图。 不走 HTML/SVG 手工合成。
- 架构猫（当前持球猫）：内容分析 + 分页规划 + 低保真 MD 写作
- imagegen 猫（imagegen 猫/云端 Codex）：逐页生成精美 raster PNG
- operator：审稿 + 确认风格
产出是 AI 原生图片——视觉质量远高于 HTML/CSS 手工画，且速度快。
开局参数（必须声明）
| 参数 | 说明 | 示例 |
|---|---|---|
| 风格 preset | 对标公司的视觉基因 | 华为 / Apple / 阿里 / 自定义 |
| 受众 | 谁看这个 PPT | 部门领导 / CTO / 投资人 / 客户 |
| 场景 | PPT 用在哪 | 转正答辩 / 年会汇报 / 客户提案 / 技术分享 |
| 内容取舍 | 全保留 or 可精简 | "所有内容全保留" / "只要核心亮点" |
没有开局参数 = 分页和风格无标准。开工前先锁。
场景路由
| 触发 | 场景 | 主导 | 详细文档 |
|---|---|---|---|
| operator说"做个 PPT" | 1: 内容分析 + 分页规划 | 架构猫 | ppt-lofi-authoring.md |
| 分页确认 | 2: 低保真 MD 写作 | 架构猫 | ppt-lofi-authoring.md |
| 低保真 MD 完成 | 3: operator审稿 | operator | — |
| 审稿通过 | 4: imagegen 出图 | imagegen 猫/云端 Codex | 逐页生成精美图 |
| 出图完成 | 5: 交付 | 主执行猫 | 图片打包 + 预览 |
| operator不满意 | R: 回到 1 或 2 | — | 改分页/改内容/改风格 |
场景 1-2: 低保真 MD 写作
写作流程
-
内容分析：读完全部原始内容，识别：
- 核心板块（几个大的独立主题）
- 关键数据点（有冲击力的数字）
- 可图表化的逻辑链（流程/对比/层级）
- 信息层级（总→分）
-
分页规划：确定每页的类型和内容分配
- 页面类型：封面 / 总览 / 详情 / 方法论 / 路线图 / 总结
- 先给operator看分页表，确认再动手写
-
风格锁定：选择风格 preset，配色方案一次锁定
-
低保真 MD 写作：每页一个 section
- ASCII art 结构图（用 box drawing 字符画清布局）
- 视觉指引（给 imagegen 猫的文字描述）
- 数据高亮方式标注
-
精美图生成指引：末尾写总体风格规范 + 逐页清单表格
低保真 MD 文件结构
---
title: "PPT 标题 — 低保真稿"
created: YYYY-MM-DD
author: "[签名]"
doc_kind: diagram
status: lofi-draft
---
# 标题
> **受众**：...
> **风格**：...
> **视觉**：一行配色方案
> **页数**：N 页
> **原则**：...
## P1：封面
（ASCII art + 视觉指引）
## P2：总览
（ASCII art + 视觉指引）
...
## 精美图生成指引（给imagegen 猫）
（配色方案 + 字体风格 + 密度原则 + 逐页清单）
场景 4: imagegen 出图交接协议
发给 imagegen 猫时说清：
- 低保真 MD 文件路径（不贴全文，太长）
- 逐页生成：每页一张独立图片
- 输出位置：同目录
assets/子目录 - 技术要求：
- 原生 imagegen 直出 raster PNG
- 不用 SVG / HTML 手工合成（出来贼丑）
- 每页命名：
p{N}-{简短描述}.png
- 内容约束：
- 严格遵循配色方案，不自由发挥
- 文字内容以低保真 MD 为准，不删不加
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.
- 6d ago First seen · 156 lines · 135 tokens per session scan A 8d66cc4b71ba
ppt-forge is a skill published in the GitHub repository zts212653/clowder-ai (2,894 stars, last pushed yesterday), licensed MIT. It adds 135 tokens to every session and 1,875 once invoked, about $0.0007 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
gog-slides
Google Slides operations through gog.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…