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 skills add Renaissance-Mind/DrawAI --skill drawai-image2pptgit clone --depth 1 https://github.com/Renaissance-Mind/DrawAIWrote 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/renaissance-mind/drawai/drawai-image2ppt)<a href="https://agentmods.dev/skills/renaissance-mind/drawai/drawai-image2ppt"><img src="https://agentmods.dev/badge/skills/renaissance-mind/drawai/drawai-image2ppt/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.
<a href="https://agentmods.dev/skills/renaissance-mind/drawai/drawai-image2ppt"><img src="https://agentmods.dev/badge/skills/renaissance-mind/drawai/drawai-image2ppt.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00070 | $0.01580 |
| Opus 5.5 | $0.00028 | $0.00632 |
| Sonnet 5.5 | $0.00014 | $0.00316 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
drawai-image2ppt 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 12d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DrawAI Image2PPT
在 DrawAI 插件中使用时，先阅读 drawai-readme，沿用已经确认的模式。输入是 drawai-design 确定的页面图像，或用户直接提供的完整页面图像。本阶段负责实际 PPT 构建、原生对象编辑、导出、检查与制作源交付。使用同一 DrawAI 安装中的 Python API／CLI；技能目录内脚本保留兼容调用。
输入与模式
先验证 drawai.visual-deck.v1 清单，按保存的页序与原图处理：
drawai visual verify visual-deck.json
只提供图片时先登记清单；已有可编辑 PPTX 的明确局部修改可直接进入原生编辑流程。模板和视觉设计需要改变时回到 drawai-design 更新输入，不暗中改动已确定的内容。
| 模式 | 执行方式 |
|---|---|
| DrawAI-Flow | 将图像提交现有 Workbench，由其配置的流程、处理器与模型完成解析、素材处理、重建和导出，工作台显示实际阶段进度 |
| Skill | 在当前会话看图、编写和执行本地重建代码，调用本技能工具包创建与检查 PPT，不启动另一个 Agent 进程处理视觉理解 |
Session 最终制作默认由当前 Agent 实施，沿用真实模型、推理配置和工具权限。模型版本未知时仍保留当前 Agent；看图或执行能力缺失时报告问题。图像可以使用宿主工具或外接 API，图像来源不会改变最终制作 Agent。仅用户明确指定其他 Agent 或 Flow 时切换相应执行方式。
DrawAI-Flow
先确认 Workbench 可连接、所需处理器与 Agent 配置可用。默认 Workbench 与 API 共用 http://127.0.0.1:8890；使用当前安装配置的实际地址。启动和首次模型准备遵循仓库运行文档，不重建 Studio 项目服务。
有 drawai_flow 时使用以下操作：
status不带批次 ID，检查当前连接与实际健康信息。- Session 提交传入规划结果
implementation.flow_agent_settings作为本任务agent_settings；用户明确选择工作台 Agent 时按 configured 处理。submit传入visual_manifest，上传经过验证的页面图像，返回本任务的排队批次与 Workbench 地址；提交本身不代表转换成功。 - 用户指定在工作台手动操作时打开该入口继续。用户要求直接制作或已经确定执行流程时调用
start，执行本任务的批次，随后用status查看真实进度。出现失败或等待素材审阅时处理实际原因；不要把请求发送成功当成成品。 - 全部页面完成后调用
export，传入本任务的batch_id和新的output_path，下载完整 PPTX，再按下述文件验收检查。
只有使用本任务提交结果中的批次 ID 才能启动或导出。DRAWAI_WORKBENCH_API_URL 与 DRAWAI_WORKBENCH_UI_URL 配置服务地址；本地 Python 路径可用 DRAWAI_PYTHON 指定。没有 MCP 时，可在 Workbench 上传相同图像并执行，或使用现有 REST API／CLI 完成同一流程。
当前会话 Skill
查看每页原图与已知文字、数据，拆分文字、形状、连线、表格、图表和复杂局部素材。简单结构用原生对象；照片、复杂插画与纹理可用局部原图裁剪。需要可编辑的内容按对象重建，不能把整页图像当成最终 PPT 背景。
保持确定的画布、相对位置、样式、分组与层叠顺序。有真实原始数据时使用数据构建图表；只有曲线图片时记录无法恢复的精确数据与近似。用户 PPTX 模板的格式要求通过实际模板解析与原生结构处理。
文档使用 presentation.document.v1，以 pt 作为位置、尺寸、字号与线宽单位；96 DPI 下像素坐标统一乘 0.75。可写文档 JSON，或用 Python 构造页面对象。将重建与修改的实现、素材处理和导出源保存在任务目录。
drawai presentation export deck.document.json --pptx output/v1/deck.pptx --svg-dir output/v1/svg --report output/v1/export.json
What ships with it
37 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.
- agents/openai.yaml 258 B
- assets/demo/agent_workflow.png 1277 KB
- assets/demo/demo_figure.png 80 KB
- assets/demo/formula.svg 20 KB
- assets/rebuildable-deck/assets/src/line_chart.py 2.1 KB runs code
- assets/rebuildable-deck/build.py 7.5 KB runs code
- assets/rebuildable-deck/data/metrics.csv 67 B
- assets/rebuildable-deck/requirements.txt 19 B
- LICENSE 11 KB
- references/code-map.md 4.7 KB
- references/document-api.md 16 KB
- references/export-capabilities.csv 229 KB
- references/export-capabilities.md 178 KB
- references/implementation-capabilities.csv 82 KB
- references/implementation-capabilities.json 179 KB
- references/implementation-capabilities.md 76 KB
- references/pptx-inventory/schema-inventory.json 5415 KB
- references/pptx-inventory/schema-properties.csv 2404 KB
- references/pptx-inventory/schema-sources.json 21 KB
- references/pptx-standard.md 12 KB
- references/property-catalog.json 614 KB
- references/research-sources.md 7.5 KB
- references/template-analysis.md 265 B
- references/visual-assets.md 5.0 KB
- references/workflows.md 10 KB
- scripts/build_capability_matrix.py 20 KB runs code
- scripts/build_v2_demo.py 23 KB runs code
- scripts/check_document.py 21 KB runs code
- scripts/check_workflows.py 21 KB runs code
- scripts/check.py 7.8 KB runs code
- scripts/example.py 6.5 KB runs code
- scripts/ppt.py 516 B runs code
- scripts/pptx_skill/__init__.py 451 B runs code
- scripts/requirements.txt 65 B
- scripts/research_pptx.py 6.9 KB runs code
- scripts/update_implementation_matrix.py 3.0 KB runs code
- scripts/visual_deck.py 343 B runs code
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.
- 12d ago Changed · +3 tokens per session 8ec7064d4dff
- 14d ago First seen · 67 lines · 67 tokens per session scan A 4ea0d491674d
drawai-image2ppt is a skill published in the GitHub repository Renaissance-Mind/DrawAI (189 stars, last pushed 13d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,580 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.