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-readmegit 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-readme)<a href="https://agentmods.dev/skills/renaissance-mind/drawai/drawai-readme"><img src="https://agentmods.dev/badge/skills/renaissance-mind/drawai/drawai-readme/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-readme"><img src="https://agentmods.dev/badge/skills/renaissance-mind/drawai/drawai-readme.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 | $0.00048 | $0.01143 |
| Opus 5.5 | $0.00019 | $0.00457 |
| Sonnet 5.5 | $0.00010 | $0.00229 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
drawai-readme 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DrawAI
读取用户需求、材料和当前项目，明确输入是内容、参考图、完整页面图片还是已有 PPTX。DrawAI 安装一次，Session、Workbench 和 CLI 使用同一套核心、模板、配置与工具。
制作流程
| 技能 | 职责 |
|---|---|
| drawai-readme | 读取材料，检查看图、执行和图像工具，补齐内容需求 |
| drawai-design | 选择参考，确定页序与内容，生成或登记真实页面图片 |
| drawai-image2ppt | 重建或编辑原生对象，导出 PPTX/SVG，检查并交付 |
从材料制作：读取内容 → 选择参考 → 确定页面图片 → 转换 → 检查。已有完整页面图片时直接核对和登记；已有 PPTX 的局部修改进入原生编辑；只选模板时进入模板库。
当前 Agent 与图像来源
最终制作默认由当前会话 Agent 执行，沿用其真实模型、推理配置、认证和工具权限。Claude 会话由当前 Claude 执行，Codex 会话由当前 Codex 执行，其他具备相应能力的宿主同样处理。模型名称或版本未知时继续保留当前 Agent；缺少看图或代码执行能力时说明缺项，不能自行启动另一个 Agent 或转交工作台。
图像生成与最终制作分别选择。用户指定图像 API 或连接时使用该选择；否则优先使用会话本身的图像工具。宿主缺少图像能力时，可使用已配置的 Images API、已有图片或有实际渲染能力的本地排版。外接图像 API 不改变最终制作 Agent。
Images API 连接与 Workbench/CLI 共用。用 drawai config connections --import connections.json 配置，或在 Workbench 设置中新增；用 drawai config image --source api --connection <真实ID> 设默认。执行实际图片生成/编辑时可调用 drawai_image，或 drawai image generate/edit；使用宿主图像工具时直接调用当前宿主提供的工具。
只有用户明确选择另一个 Agent、模型或 DrawAI-Flow 时才改变对应执行选择。用户明确要求另一个 CLI Agent 时，使用 drawai session execute --agent claude|codex --prompt-file <任务文件> --workdir <任务目录>；只有明确指定模型才传 --model。其他宿主可使用 custom 命令适配。执行器沿用所选 Agent 的配置与权限。
规划与提问
用 drawai_plan 或 drawai plan request.json 传入真实会话环境与已知偏好。environment.agent 来自宿主身份；model 与 model_source 来自本轮实际信息，未知时如实记录。规划器保留当前会话，图像来源可为 auto/session/api/local，用户明确选择优先。完整输入和返回契约见 需求确认。执行策略见 执行策略。
只补齐尚缺的参考、页数、比例和实际输入。已经提供的要求直接沿用；默认当前 Agent 的实施方式无需再次询问。明确不要提问或已指定流程时，采用已知信息及合理默认值：页面图像数量或 8 页，已知比例或 16:9。具体缺少的文件、凭据或工具必须暴露。
明确选择 Flow
用户选择 Flow 后，连接同一安装的 Workbench 或明确的远程地址。Session 提交时将规划结果 implementation.flow_agent_settings 作为 drawai_flow.submit.agent_settings，把真实当前 Agent 类型和已知模型参数保留为本任务配置，不覆盖工作台全局配置。执行主机使用自己的认证；不复制当前会话密钥。无法确认当前 Agent 类型时，需要用户提供身份或明确选择工作台已配置 Agent。
用户明确选择工作台 Agent 时传 preferences.implementation_agent="configured"。独立 Workbench/CLI 默认读取共同配置中的执行后端。Flow 提交、执行、查询和导出后，仍须检查实际文件。
核心与交付
工具使用统一安装的 drawai：drawai visual save/verify 管理图像清单，drawai presentation 制作、导出、检查与渲染文档，drawai ppt create/edit 保留现有原生操作计划。Python API 从 pptx_skill 导入；实现只有一份，旧技能脚本是兼容入口。
What ships with it
4 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.
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 · -5 lines · -15 tokens per session 25705f9c616d
- 15d ago First seen · 52 lines · 63 tokens per session scan A 44a40938e660
drawai-readme is a skill published in the GitHub repository Renaissance-Mind/DrawAI (189 stars, last pushed 13d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,143 once invoked, about $0.0002 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.