mirror of
https://github.com/ningzimu/codex-ppt-skill.git
synced 2026-09-14 20:06:52 +08:00
feat: 个人风格库外部持久化、文档站补全与 ClawMama 徽标 (#83)
* feat(codex-ppt): 支持个人风格库外部持久化并完善文档
【新功能】
- 自定义风格改存 ${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/,
更新或重装 skill 不再丢失(#81)
- 取消风格登记步骤,改为目录扫描自动发现,同名时个人风格优先
- 生成收尾时主动提示可将自定义风格保存到个人风格库
【文档】
- 文档站新增「风格与个人风格库」页,补全工作流收尾阶段、
安装方式和图片模糊 FAQ
- 移除已失效的 codex-gpt-image 组合方案,改为引导使用
gpt-image-2 API 生成高分辨率图像
- README 新增 ClawMama 徽标(#75)
* docs(changelog): 补充 Unreleased 变更记录
This commit is contained in:
@@ -4,11 +4,21 @@ Release notes are generated from this file. Keep changelog entries in English.
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Features
|
||||
|
||||
- Store user custom styles in `${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/` outside the skill install so they survive skill updates and reinstalls, with automatic discovery and same-name priority over built-in styles. (#83)
|
||||
- Proactively offer to save custom or adapted deck styles to the personal style library in the final report. (#83)
|
||||
|
||||
### Improvements
|
||||
|
||||
- Make the Party-and-Government Red style more adaptable by replacing fixed layout and motif prescriptions with content-driven visual guidance. (#82)
|
||||
- Make the Teaching Courseware style more adaptable across disciplines by removing example-specific subject matter, fixed module counts, and repetitive card-grid assumptions. (#82)
|
||||
|
||||
### Documentation
|
||||
|
||||
- Add a styles page to the documentation site and expand workflow, installation, and FAQ coverage. (#83)
|
||||
- Replace the deprecated codex-gpt-image pairing tip with guidance to use the gpt-image-2 API for higher-resolution slides, and add a ClawMama badge to the README. (#83)
|
||||
|
||||
## 0.5.4
|
||||
|
||||
### Features
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Codex PPT Skill
|
||||
|
||||
[](README_en.md) [](https://ningzimu.github.io/codex-ppt-skill/#/) [](https://clawhub.ai/ningzimu/codex-ppt) [](https://github.com/ningzimu/codex-ppt-skill/stargazers) [](https://github.com/ningzimu/codex-ppt-skill/forks)
|
||||
[](README_en.md) [](https://ningzimu.github.io/codex-ppt-skill/#/) [](https://clawhub.ai/ningzimu/codex-ppt) [](https://app.clawmama.run/skills/5lak48/hermes?utm_source=github&utm_medium=issue&utm_campaign=skill_outreach_ningzimu_codex_ppt_skill) [](https://github.com/ningzimu/codex-ppt-skill/stargazers) [](https://github.com/ningzimu/codex-ppt-skill/forks)
|
||||
|
||||
一个面向 Codex 的 PPT 生成 skill,也可在 Claude Code、OpenClaw、Hermes Agent 等支持 `SKILL.md` 的 agent 中使用;在这些非 Codex 环境中通常需要配置 `gpt-image-2`、第三方生图 API 或 OpenAI 兼容格式的生图接口。它把文章、报告、论文、课程笔记等内容转换成“整页图片式”的演示文稿:先规划大纲和视觉风格,再生成每页幻灯片图片,最后用本地脚本组装为 `.pptx`。
|
||||
|
||||
@@ -29,7 +29,7 @@
|
||||
|
||||
建议大家在走通自己常用的路线之后,让 AI 帮你改一下这个 skill,把你的偏好固定下来,省得每次都重新选择。比如固定使用内置生图或固定使用某个 API,固定是否使用子 agent,固定常用输出目录、风格、页数节奏等。
|
||||
|
||||
另外,如果你在做 PPT 的过程中遇到了自己喜欢的版式或排版,无论是这个 skill 做出来的,还是从别的地方找到的 PPT 风格图片,都可以让 AI 加到这个 skill 的 `references/` 里,逐步形成你自己的风格库。Skills 本质上是非常个性化的流程,鼓励大家在使用这个 skill 的基础上,按自己的偏好持续调优,让它更适配自己的工作流。
|
||||
另外,如果你在做 PPT 的过程中遇到了自己喜欢的版式或排版,无论是这个 skill 做出来的,还是从别的地方找到的 PPT 风格图片,都可以让 AI 保存到你的个人风格库(`~/.codex-ppt-skill/references/`)里,逐步沉淀自己的风格。个人风格库存放在 skill 安装目录之外,更新或重装 skill 都不会丢失。Skills 本质上是非常个性化的流程,鼓励大家在使用这个 skill 的基础上,按自己的偏好持续调优,让它更适配自己的工作流。
|
||||
|
||||
关于 skills 如何设计和使用,可以参考 [good-skill-design.pptx](assets/good-skill-design.pptx)。这个 PPT 也是用本 skill 做的,采用的是手绘技术解释风;内容基于 Claude 在设计 skills 方面的最佳实践文章 [The Complete Guide to Building Skills for Claude](https://resources.anthropic.com/hubfs/The-Complete-Guide-to-Building-Skill-for-Claude.pdf)。祝大家玩得愉快!
|
||||
|
||||
@@ -42,7 +42,7 @@
|
||||
- 低门槛输入:文章、报告、论文、课程笔记、Markdown、大纲、PDF、Word 等材料都可以作为起点。
|
||||
- 内置 12 种 PPT 风格参考:包括清爽专业、科研答辩、党政红、教学课件、电子墨水杂志、手绘技术解释、仪表盘、麦肯锡等;不会写提示词也可以先从内置风格开始,尤其推荐手绘技术解释风。
|
||||
- 支持自定义风格复刻:可以上传喜欢的图片、PDF 或 PPT/PPTX,让 agent 先分析配色、版式、字体和视觉元素,再按该风格生成新 PPT。
|
||||
- 可沉淀个人风格库:生成满意后,可以把当前风格保存到 skill 的 `references/` 目录,下次直接复用,让这个 skill 越用越贴合你的偏好。
|
||||
- 可沉淀个人风格库:生成满意后,可以把当前风格保存到个人风格库(`~/.codex-ppt-skill/references/`),下次直接复用;风格库存放在 skill 安装目录之外,更新 skill 不会丢失,同名时个人风格优先于内置风格。
|
||||
- 多 agent 并发生成:样张确认后,支持一个子 agent 负责一页,并对文字清晰度、风格一致性和内容完整性做自检,发现问题及时返修。
|
||||
- 支持指定图片插入:可以要求某一页必须放入论文原图、实验结果图、截图、架构图等素材,并让页面围绕这些图片适配主题和版式。
|
||||
- 自动生成演讲稿:会生成 `speech.md`,并在组装 PPTX 时写入每页备注,方便直接演示或二次修改。
|
||||
@@ -203,12 +203,12 @@ skill 会按以下流程执行:
|
||||
|
||||
## 使用技巧
|
||||
|
||||
- 默认脚本分辨率是 2K 16:9 横屏。这个设置主要适用于你自己提供第三方 `gpt-image-2` API 或 OpenAI 兼容中转站的 API/CLI fallback 场景;如果生成的幻灯片图片比较模糊,尤其是文字较多的页面,可以让 AI 改用 4K 分辨率生成。Codex 会员默认会优先使用内置生图工具,内置工具目前不能手动指定图片分辨率。如果你不想额外购买第三方 `gpt-image-2` API,但又想用会员身份生成 4K 级别的高清 PPT,可以组合使用 [ningzimu/codex-gpt-image](https://github.com/ningzimu/codex-gpt-image) skill;它会使用会员登录,并以 API 方式调用 `gpt-image-2` 生图,再配合 Codex PPT 生成高清页面。
|
||||
- Codex 会员默认会优先使用内置生图工具,其生成的图片分辨率比较低,且目前不能手动指定分辨率。如果需要更高分辨率的图像,需要改用 `gpt-image-2` API 的方式生成(即 API/CLI fallback,提供 API key、base URL 和模型名)。API/CLI fallback 场景下,脚本默认分辨率是 2K 16:9 横屏;如果生成的幻灯片图片仍然比较模糊,尤其是文字较多的页面,可以让 AI 改用 4K 分辨率生成。
|
||||
- 如果只是不满意某一页的内容、排版、配色或文字表达,可以直接让当前 agent 针对这一页做细致修改,不需要整套 PPT 重新生成。
|
||||
|
||||

|
||||
|
||||
- 你也可以提供喜欢的 PPT 风格参考,可以是一张截图、多张截图,或完整 PPT/PDF。建议先让当前 agent 分析参考材料的配色、版式、字体和视觉元素,再按这个风格生成新 PPT。生成满意后,也可以让 agent 把这套风格保存到本技能的 `references/` 目录里,方便以后复用。
|
||||
- 你也可以提供喜欢的 PPT 风格参考,可以是一张截图、多张截图,或完整 PPT/PDF。建议先让当前 agent 分析参考材料的配色、版式、字体和视觉元素,再按这个风格生成新 PPT。生成满意后,也可以让 agent 把这套风格保存到个人风格库(`~/.codex-ppt-skill/references/`)里,方便以后复用,且不会因更新 skill 而丢失。
|
||||
- 如果需要插入论文原图、实验结果图、截图或架构图,可以在大纲中指定这些图片对应的页码和用途。
|
||||
|
||||
## QA
|
||||
@@ -226,7 +226,7 @@ Telegram:[CodexPPT](https://t.me/CodexPPT)
|
||||
## 我的其他项目
|
||||
|
||||
- [image-to-editable-ppt-skill](https://github.com/ningzimu/image-to-editable-ppt-skill):把幻灯片截图、PDF 页面或图片版 PPTX 重建为可编辑 PowerPoint,适合在 `codex-ppt` 生成整页图片后继续做可编辑化。
|
||||
- [codex-gpt-image](https://github.com/ningzimu/codex-gpt-image):通过 Codex OAuth / 会员登录调用 `gpt-image-2` 的生图 skill,可和 `codex-ppt` 组合,用会员身份生成更高清的 PPT 页面。
|
||||
- [codex-gpt-image](https://github.com/ningzimu/codex-gpt-image):通过 Codex OAuth / 会员登录调用 `gpt-image-2` 的生图 skill。
|
||||
- [handdrawn-tech-illustrations](https://github.com/ningzimu/handdrawn-tech-illustrations):面向中文技术内容的手绘配图 skill,可以把技术文章、产品笔记、截图、大纲或粗略想法生成正文配图、概念解释图、微信公众号封面和小红书封面;风格强调亲和、轻卡通、中文可读和适中的信息密度。
|
||||
- [awesome-ai-ppt](https://github.com/ningzimu/awesome-ai-ppt):精选的 AI PPT 相关开源项目,按 HTML-first、图片生成式、PPTX-native、转换与自动化基础设施等工作流分类,关注能帮助 agent 或开发者创建、编辑、转换、检查 PPT 的 GitHub 仓库。
|
||||
- [claude-code-lens](https://github.com/ningzimu/claude-code-lens):Claude Code 本地观测工具,用来查看 API 流量、日志、prompt 和工具调用,适合排查 agent 实际在做什么。
|
||||
|
||||
+6
-6
@@ -1,6 +1,6 @@
|
||||
# Codex PPT Skill
|
||||
|
||||
[](README.md) [](https://ningzimu.github.io/codex-ppt-skill/#/) [](https://clawhub.ai/ningzimu/codex-ppt) [](https://github.com/ningzimu/codex-ppt-skill/stargazers) [](https://github.com/ningzimu/codex-ppt-skill/forks)
|
||||
[](README.md) [](https://ningzimu.github.io/codex-ppt-skill/#/) [](https://clawhub.ai/ningzimu/codex-ppt) [](https://app.clawmama.run/skills/5lak48/hermes?utm_source=github&utm_medium=issue&utm_campaign=skill_outreach_ningzimu_codex_ppt_skill) [](https://github.com/ningzimu/codex-ppt-skill/stargazers) [](https://github.com/ningzimu/codex-ppt-skill/forks)
|
||||
|
||||
A Codex skill for generating PowerPoint decks. It can also be used in Claude Code, OpenClaw, Hermes Agent, and other agents that support `SKILL.md`; these non-Codex environments usually require configuring `gpt-image-2`, a third-party image API, or an OpenAI-compatible image generation endpoint. It turns articles, reports, papers, course notes, and other source materials into image-based presentations: first plan the outline and visual style, then generate each full-slide image, and finally assemble the images into a `.pptx` file with a local script.
|
||||
|
||||
@@ -29,7 +29,7 @@ This skill is meant to provide a solid PPT generation workflow. To stay broadly
|
||||
|
||||
After you have a route working, consider asking an AI assistant to edit this skill and lock in your own preferences, such as your preferred image backend, whether to use subagents, output directory conventions, visual styles, or slide pacing. That way you do not need to make the same choices every time.
|
||||
|
||||
If you find a layout or visual style you like while making decks, whether it was generated by this skill or found elsewhere, you can ask AI to add it to this skill's `references/` directory and gradually build your own style library. Skills are highly personal workflows; tune this one around your own habits so it becomes more useful for your actual work.
|
||||
If you find a layout or visual style you like while making decks, whether it was generated by this skill or found elsewhere, you can ask AI to save it into your personal style library at `~/.codex-ppt-skill/references/` and gradually build your own collection. The personal style library lives outside the skill install directory, so updating or reinstalling the skill never loses it. Skills are highly personal workflows; tune this one around your own habits so it becomes more useful for your actual work.
|
||||
|
||||
For a basic introduction to skill design and usage, see [good-skill-design.pptx](assets/good-skill-design.pptx). That deck was also made with this skill, using the hand-drawn technical explainer style, and is based on Claude's skill design best-practices article [The Complete Guide to Building Skills for Claude](https://resources.anthropic.com/hubfs/The-Complete-Guide-to-Building-Skill-for-Claude.pdf).
|
||||
|
||||
@@ -42,7 +42,7 @@ For a basic introduction to skill design and usage, see [good-skill-design.pptx]
|
||||
- Low setup effort: articles, reports, papers, course notes, Markdown files, outlines, PDFs, and Word documents can all be used as starting material.
|
||||
- 12 built-in PPT style references: includes clean professional, scientific defense, Party-and-Government Red, Teaching Courseware, e-ink magazine, hand-drawn technical explainer, dashboard, McKinsey style, and more. The hand-drawn technical explainer style is a strong starting point if you do not want to write prompts.
|
||||
- Supports custom style replication: provide a favorite image, PDF, or PPT/PPTX, and the agent can analyze its color, layout, typography, and visual system before generating a new deck in that style.
|
||||
- Builds a reusable personal style library: once you like a deck style, ask the agent to save it into this skill's `references/` directory so future decks can reuse it directly.
|
||||
- Builds a reusable personal style library: once you like a deck style, ask the agent to save it into `~/.codex-ppt-skill/references/` so future decks can reuse it directly; the library lives outside the skill install, survives skill updates, and a personal style with the same name takes priority over the built-in one.
|
||||
- Supports parallel subagent generation: after the sample slide is approved, one subagent can handle one slide and self-check readability, style consistency, and content completeness before reporting issues for repair.
|
||||
- Supports required image insertion: assign paper figures, experiment charts, screenshots, architecture diagrams, or other images to specific slides, and the generated page will adapt the layout and theme around them.
|
||||
- Generates speaker notes: creates `speech.md` and writes the notes into each slide during PPTX assembly, making the deck easier to present or revise.
|
||||
@@ -203,12 +203,12 @@ The skill follows this workflow:
|
||||
|
||||
## Usage Tips
|
||||
|
||||
- The default script resolution is 2K 16:9 landscape. This setting mainly applies when you provide a third-party `gpt-image-2` API or OpenAI-compatible proxy and use API/CLI fallback; in that path, ask the AI to switch to 4K if slide images look blurry, especially on text-heavy pages. Codex subscribers use the built-in image generation tool by default, and that built-in tool does not currently expose a manual resolution setting. If you do not want to buy a third-party `gpt-image-2` API but still want 4K-level decks with your subscription, combine this skill with [ningzimu/codex-gpt-image](https://github.com/ningzimu/codex-gpt-image), which uses your member login and calls `gpt-image-2` through an API-style workflow before pairing with Codex PPT for high-resolution slide generation.
|
||||
- Codex subscribers use the built-in image generation tool by default; its output resolution is relatively low, and it does not currently expose a manual resolution setting. If you need higher-resolution images, switch to generating via the `gpt-image-2` API (the API/CLI fallback path, configured with an API key, base URL, and model name). In the API/CLI fallback path, the default script resolution is 2K 16:9 landscape; if slide images still look blurry, especially on text-heavy pages, ask the AI to switch to 4K.
|
||||
- If you are unhappy with one specific slide's content, layout, colors, or wording, ask the current agent to refine that slide in detail instead of regenerating the whole deck.
|
||||
|
||||

|
||||
|
||||
- You can also provide PPT style references you like — a single screenshot, multiple screenshots, or a full PPT/PDF. Ask the current agent to analyze the colors, layout, typography, and visual elements first, then generate a new deck in that style. Once the result looks good, you can ask the agent to save the style into this skill's `references/` directory for future reuse.
|
||||
- You can also provide PPT style references you like — a single screenshot, multiple screenshots, or a full PPT/PDF. Ask the current agent to analyze the colors, layout, typography, and visual elements first, then generate a new deck in that style. Once the result looks good, you can ask the agent to save the style into your personal style library at `~/.codex-ppt-skill/references/` for future reuse; it will not be lost when the skill is updated.
|
||||
- If you need to include paper figures, experiment charts, screenshots, or architecture diagrams, specify the target slide and role for each image in the outline.
|
||||
|
||||
## QA
|
||||
@@ -226,7 +226,7 @@ Telegram: [CodexPPT](https://t.me/CodexPPT)
|
||||
## More Projects
|
||||
|
||||
- [image-to-editable-ppt-skill](https://github.com/ningzimu/image-to-editable-ppt-skill): Rebuild slide screenshots, PDF pages, or image-based PPTX files into editable PowerPoint decks, useful after `codex-ppt` generates image-based slides.
|
||||
- [codex-gpt-image](https://github.com/ningzimu/codex-gpt-image): A `gpt-image-2` image generation skill powered by Codex OAuth / member login, which can be paired with `codex-ppt` to generate higher-resolution PPT pages with your subscription.
|
||||
- [codex-gpt-image](https://github.com/ningzimu/codex-gpt-image): A `gpt-image-2` image generation skill powered by Codex OAuth / member login.
|
||||
- [handdrawn-tech-illustrations](https://github.com/ningzimu/handdrawn-tech-illustrations): A hand-drawn illustration skill for Chinese technical content. It turns technical articles, product notes, screenshots, outlines, or rough ideas into article illustrations, concept explainer graphics, WeChat cover images, and Rednote covers, with a friendly, light-cartoon, Chinese-readable style and moderate information density.
|
||||
- [awesome-ai-ppt](https://github.com/ningzimu/awesome-ai-ppt): A curated list of open-source AI PPT projects, organized by workflows such as HTML-first, image-first, PPTX-native, conversion, and automation infrastructure, focused on GitHub projects that help agents or developers create, edit, convert, or inspect PPT decks.
|
||||
- [claude-code-lens](https://github.com/ningzimu/claude-code-lens): A local observability tool for Claude Code API traffic, logs, prompts, and tool calls, useful for understanding what an agent is actually doing.
|
||||
|
||||
+3
-1
@@ -18,6 +18,7 @@ Codex PPT 是一个面向 Codex 的 PPT 生成 skill,也可在 Claude Code、O
|
||||
- [设计理念](design.md):为什么采用图片式 PPT、阶段确认和双 skill 分工的设计。
|
||||
- [安装与配置](installation.md):Codex、OpenClaw、Claude Code、Hermes Agent 的安装方式,以及 API/CLI fallback 配置。
|
||||
- [标准工作流](workflow.md):从大纲确认、风格确认、后端确认、样张确认到整套生成和组装的完整流程。
|
||||
- [风格与个人风格库](styles.md):12 种内置风格预览、仿照参考材料复刻风格,以及把满意的风格保存到个人风格库长期复用。
|
||||
- [常见问题](faq.md):可编辑性、API key、样张、素材插入、单页修改等高频问题。
|
||||
- [示例提示词](prompts.md):文章转 PPT、论文答辩、管理层汇报、指定风格、修改单页等可直接复用的提示词。
|
||||
|
||||
@@ -25,8 +26,9 @@ Codex PPT 是一个面向 Codex 的 PPT 生成 skill,也可在 Claude Code、O
|
||||
|
||||
- 图片式 PPT 生成:每一页都是完整 16:9 幻灯片图片,适合追求强视觉表达和统一风格的场景。
|
||||
- 分阶段确认流程:先确认大纲、视觉风格、图片生成方式和样张,再生成整套 PPT,减少返工。
|
||||
- 内置多种风格:支持手绘技术解释风、科研答辩风、清爽专业风、数据仪表盘风、电子墨水杂志风等方向。
|
||||
- 内置 12 种风格:包括手绘技术解释风、科研答辩风、清爽专业风、麦肯锡风格、党政红风格、教学课件风等方向,参见[风格与个人风格库](styles.md)。
|
||||
- 支持参考材料仿风格:可以阅读用户提供的 PPT、PDF 或截图,理解每页图片风格后再仿照生成。
|
||||
- 可沉淀个人风格库:满意的风格可以保存到 `~/.codex-ppt-skill/references/`,存放在 skill 安装目录之外,更新 skill 不丢失,后续制作直接按名字复用。
|
||||
- 支持指定素材入页:可以把论文原图、实验结果图、架构图或截图指定到具体页面中使用。
|
||||
- 支持多 agent 环境:除 Codex 外,也可在 Claude Code、OpenClaw、Hermes Agent 等支持 `SKILL.md` 的 agent 中使用。
|
||||
- 自动组装 PowerPoint:生成 `outline.md`、每页图片、`speech.md`,并最终组装为 `.pptx` 文件。
|
||||
|
||||
@@ -3,5 +3,6 @@
|
||||
* [设计理念](design.md)
|
||||
* [安装与配置](installation.md)
|
||||
* [标准工作流](workflow.md)
|
||||
* [风格与个人风格库](styles.md)
|
||||
* [常见问题](faq.md)
|
||||
* [示例提示词](prompts.md)
|
||||
|
||||
+7
-1
@@ -32,6 +32,12 @@
|
||||
|
||||
确认模型可用后,再让 AI 针对具体问题修改,例如风格不统一、文字太小、页面太挤、配色不好看、插图不贴合主题等。建议先重新生成 1 页样张,满意后再继续整套生成。
|
||||
|
||||
## Q:生成的幻灯片图片比较模糊怎么办?
|
||||
|
||||
Codex 会员默认使用内置生图工具,其生成的图片分辨率比较低,且目前不能手动指定分辨率。如果需要更高分辨率的图像,需要改用 `gpt-image-2` API 的方式生成(即 API/CLI fallback,配置 API key、base URL 和模型名,参见[安装与配置](installation.md))。
|
||||
|
||||
API/CLI fallback 场景下,脚本默认分辨率是 2K 16:9 横屏。如果图片仍然模糊,尤其是文字较多的页面,可以让 AI 改用 4K 分辨率生成。
|
||||
|
||||
## Q:为什么要先确认大纲?
|
||||
|
||||
因为 PPT 的返工成本主要来自结构问题。先确认页数、标题、顺序和每页要点,可以避免后面图片都生成完了才发现内容方向不对。
|
||||
@@ -54,4 +60,4 @@
|
||||
|
||||
## Q:可以保存自己的风格吗?
|
||||
|
||||
可以。把喜欢的 PPT 截图、PDF 或完整 PPT 交给 agent 分析,生成满意后,可以让 agent 把这套风格整理进 `references/` 目录,形成自己的风格库。
|
||||
可以。把喜欢的 PPT 截图、PDF 或完整 PPT 交给 agent 分析,生成满意后,可以让 agent 把这套风格保存到个人风格库(`~/.codex-ppt-skill/references/`)。风格库存放在 skill 安装目录之外,更新或重装 skill 都不会丢失;如果与内置风格同名,个人风格优先。详见[风格与个人风格库](styles.md)。
|
||||
|
||||
@@ -21,6 +21,15 @@ npx -y skills@latest add ningzimu/codex-ppt-skill \
|
||||
|
||||
安装后重启 Codex,让新 skill 生效。
|
||||
|
||||
也可以从 [GitHub Releases](https://github.com/ningzimu/codex-ppt-skill/releases) 下载 `codex-ppt-skill-v*.zip`,解压后把其中的 `codex-ppt` 文件夹放到 `~/.codex/skills/codex-ppt`,然后重启 Codex。
|
||||
|
||||
如果你在本地开发这个仓库,可以把 skill 目录软链接到 Codex skills 目录,方便实时调试修改:
|
||||
|
||||
```bash
|
||||
mkdir -p ~/.codex/skills
|
||||
ln -s /path/to/codex-ppt-skill/skills/codex-ppt ~/.codex/skills/codex-ppt
|
||||
```
|
||||
|
||||
## OpenClaw 安装
|
||||
|
||||
```bash
|
||||
@@ -49,6 +58,8 @@ npx -y skills@latest add ningzimu/codex-ppt-skill \
|
||||
--global
|
||||
```
|
||||
|
||||
常见目标目录:Claude Code 使用 `~/.claude/skills/codex-ppt`,Hermes Agent 使用 `~/.hermes/skills/codex-ppt`。本地开发时同样可以用软链接替代复制。
|
||||
|
||||
## 生图模型配置
|
||||
|
||||
如果你没有 `gpt-image-2` 模型的使用权限,就无法使用该 skill。该 skill 强依赖 `gpt-image-2` 生图模型。
|
||||
|
||||
+2
-2
@@ -38,8 +38,8 @@
|
||||
第 6 页信息太密,标题不够清楚。请只重新生成第 6 页,保持整套 PPT 的风格不变,把内容拆成更清晰的三段结构。
|
||||
```
|
||||
|
||||
## 保存风格到 skill
|
||||
## 保存风格到个人风格库
|
||||
|
||||
```text
|
||||
这套 PPT 的视觉风格我很喜欢。请把它整理成 codex-ppt 的一个新 reference,保存到 references/ 目录,方便以后复用。说明里包含配色、字体气质、版式规则、插画/图表风格和适用场景。
|
||||
这套 PPT 的视觉风格我很喜欢。请把它保存到 codex-ppt 的个人风格库里,方便以后复用。说明里包含配色、字体气质、版式规则、插画/图表风格和适用场景。
|
||||
```
|
||||
|
||||
@@ -0,0 +1,59 @@
|
||||
# 风格与个人风格库
|
||||
|
||||
Codex PPT 的视觉风格来自两个地方:随 skill 发布的**内置风格**,以及存放在你本机、更新 skill 也不会丢失的**个人风格库**。
|
||||
|
||||
## 内置风格
|
||||
|
||||
skill 内置 12 种风格参考,不会写提示词也可以直接从这里开始。制作 PPT 时直接说风格名即可,例如:
|
||||
|
||||
```text
|
||||
请使用 codex-ppt skill,把这份材料做成 10 页 PPT,使用内置的「手绘技术解释风」。
|
||||
```
|
||||
|
||||
| 清爽专业风 | 创意杂志风 |
|
||||
| --- | --- |
|
||||
|  |  |
|
||||
| 电子墨水杂志风 | 数据仪表盘风 |
|
||||
|  |  |
|
||||
| 复古扁平插画风 | 手绘技术解释风 |
|
||||
|  |  |
|
||||
| 手绘白板风 | 温暖手工风 |
|
||||
|  |  |
|
||||
| 科研答辩风 | 麦肯锡风格 |
|
||||
|  |  |
|
||||
| 党政红风格 | 教学课件风 |
|
||||
|  |  |
|
||||
|
||||
风格是一套视觉系统(配色、字体气质、版式密度、插画语言),不是固定模板;同一套风格下,每页版式会根据内容角色变化,不会每页长得一样。
|
||||
|
||||
## 仿照参考材料的风格
|
||||
|
||||
如果内置风格不满足需求,可以提供自己喜欢的风格参考:一张截图、多张截图,或完整 PPT/PDF。建议先让 agent 分析参考材料的配色、版式、字体和视觉元素,再按这个风格生成新 PPT:
|
||||
|
||||
```text
|
||||
请使用 codex-ppt skill 生成 PPT。视觉风格参考我上传的这份 PDF。请详细阅读我提供材料中的每一页图片,确保了解其风格,然后仿照其风格进行生成。
|
||||
```
|
||||
|
||||
注意:默认只仿风格、不复用内容。除非你明确要求,参考材料里的文字和数据不会被搬进新 PPT。
|
||||
|
||||
## 个人风格库
|
||||
|
||||
如果生成的 PPT 风格你很满意,无论是调出来的自定义风格,还是从参考材料复刻的风格,都可以让 agent 保存下来,以后直接复用:
|
||||
|
||||
```text
|
||||
这套 PPT 的视觉风格我很喜欢,请保存到个人风格库。
|
||||
```
|
||||
|
||||
保存机制的几个要点:
|
||||
|
||||
- **存放位置**:个人风格库位于 `~/.codex-ppt-skill/references/`(可通过 `CODEX_PPT_HOME` 环境变量改变位置),在 skill 安装目录**之外**。更新或重新安装 skill 时,个人风格不会被覆盖或丢失。
|
||||
- **自动发现**:保存后无需任何登记。之后制作 PPT 选择风格时,agent 会自动扫描个人风格库,把你的风格和内置风格一起列出来。
|
||||
- **同名优先**:如果个人风格和某个内置风格同名,以你的个人风格为准。你也可以利用这一点定制内置风格:保存一个同名的调整版即可覆盖默认效果。
|
||||
- **复用方式**:以后直接说风格名即可,例如「用『深色数据科技风』生成这份 PPT」。
|
||||
|
||||
生成完成后,如果这套 deck 用的是自定义或调整过的风格,agent 也会在最终报告里主动提示你可以保存。使用未修改的内置风格时无需重复保存。
|
||||
|
||||
## 相关页面
|
||||
|
||||
- [示例提示词](prompts.md):指定内置风格、仿照参考风格、保存风格的完整提示词。
|
||||
- [常见问题](faq.md):风格跑偏、页面不满意时的处理方式。
|
||||
+15
-10
@@ -30,14 +30,7 @@ agent 会生成 `outline.md`,通常包括:
|
||||
|
||||
## 阶段 3:确认视觉风格
|
||||
|
||||
agent 会给出 2-3 个风格方向,例如:
|
||||
|
||||
- 清爽专业风
|
||||
- 科研答辩风
|
||||
- 创意杂志风
|
||||
- 电子墨水杂志风
|
||||
- 数据仪表盘风
|
||||
- 手绘技术解释风
|
||||
agent 会给出 2-3 个风格方向并推荐一个。候选风格来自 12 种内置风格(清爽专业风、科研答辩风、手绘技术解释风、麦肯锡风格、党政红风格、教学课件风等)和你的个人风格库,也可以基于你提供的截图、PDF 或 PPT 复刻风格。完整风格预览参见[风格与个人风格库](styles.md)。
|
||||
|
||||
选择风格后,整套 PPT 应保持统一视觉语言,但每页版式可以根据内容变化。
|
||||
|
||||
@@ -59,6 +52,18 @@ agent 会给出 2-3 个风格方向,例如:
|
||||
|
||||
样张通过后,再批量生成整套。
|
||||
|
||||
## 阶段 6:批量生成与组装
|
||||
## 阶段 6:批量生成
|
||||
|
||||
样张确认后,agent 会逐页生成 `origin_image/slide_XX.png`,再生成 `speech.md`,最后用 `assemble_ppt.py` 组装成 `.pptx`。
|
||||
样张确认后,agent 会逐页生成 `origin_image/slide_XX.png`。在支持子智能体的环境中,会由一个子智能体负责一页并行生成,加快多页产出;所有页面沿用样张确认的同一风格和同一生图后端。
|
||||
|
||||
## 阶段 7:质量检查与修复
|
||||
|
||||
组装前,agent 会逐页检查文字清晰度、与大纲的一致性、内容截断、风格统一性、多余页码和元素重叠等问题。发现严重问题的页面会用更严格的提示词重新生成,局部小问题优先用图片编辑能力定向修复。
|
||||
|
||||
## 阶段 8:演讲稿与组装
|
||||
|
||||
生成 `speech.md` 演讲稿,然后用 `assemble_ppt.py` 组装成 `.pptx`,演讲稿会自动写入每页 PPT 的备注区。
|
||||
|
||||
## 阶段 9(可选):保存风格
|
||||
|
||||
如果这套 PPT 用的是自定义或调整过的风格,agent 会在最终报告里提示你可以把风格保存到个人风格库,以后直接按名字复用。参见[风格与个人风格库](styles.md)。
|
||||
|
||||
@@ -117,8 +117,9 @@ Do not mark a step complete from chat alone; use real files or script-recorded s
|
||||
- Use the final report checklist in `docs/project-assembly-and-reporting.md`.
|
||||
- Include paths, slide count, backend used, recorded-result status, and any limitations or blockers.
|
||||
|
||||
13. Save reusable styles when requested.
|
||||
13. Save reusable styles.
|
||||
- If asked to save the current deck style or a supplied image/PDF/PPT/PPTX style, read `docs/style-library.md`.
|
||||
- If the final deck used a custom or adapted style, proactively offer to save it in the final report, per `docs/project-assembly-and-reporting.md`. User custom styles are stored in `${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/`, outside the skill install.
|
||||
|
||||
## Subagent Dispatch
|
||||
|
||||
@@ -150,7 +151,7 @@ Subagents must not edit `outline.md`, `deck_spec.json`, other slide jobs, `origi
|
||||
- `docs/image-model-configuration.md`: API key, base URL, model, `.env`; read only when config is needed.
|
||||
- `docs/project-assembly-and-reporting.md`: project directory, notes, assembly, final report, prompting principles.
|
||||
- `prompts/slide-worker.md`: slide subagent handoff template.
|
||||
- `references/*.md`: visual style references.
|
||||
- `references/*.md`: built-in visual style references. User custom styles live in `${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/` and take priority over built-in styles with the same name.
|
||||
|
||||
## Documentation and Updates
|
||||
|
||||
|
||||
@@ -70,11 +70,18 @@ If the user has not provided a clear style, prefer a multiple-choice question: o
|
||||
|
||||
After the user chooses a style, create one final style direction and keep the visual identity consistent across all slide prompts. Keep color palette, typography, texture, icon/illustration language, and overall mood stable. Do not reuse the same layout on every page.
|
||||
|
||||
The `references/` directory contains optional style references. Use them as inspiration, not as rigid templates. Adapt the style to the topic and audience.
|
||||
Reusable style references come from two locations:
|
||||
|
||||
- Built-in styles: the skill's `references/` directory, listed below. They ship with the skill and update with it.
|
||||
- User custom styles: `${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/*.md`. They live outside the skill install so they survive skill updates and reinstalls.
|
||||
|
||||
Before offering or using reusable styles, list the user custom style directory (if it exists) and merge its `*.md` files with the built-in list below. User custom styles are discovered by scanning that directory; they are never registered in this document. If a user custom style has the same filename as a built-in style, the user custom file takes priority and replaces the built-in one.
|
||||
|
||||
Use style references as inspiration, not as rigid templates. Adapt the style to the topic and audience.
|
||||
|
||||
Important: a deck should have one coherent visual identity, not one repeated composition. Treat each reference as a style system: stable palette, typography, icon language, texture, and visual mood; variable page layout chosen from the slide's content role. `layout_blueprints` are candidate starting points only. Do not apply the same blueprint to every slide.
|
||||
|
||||
Available references:
|
||||
Available built-in references:
|
||||
|
||||
- `references/清爽专业风.md`
|
||||
- `references/创意杂志风.md`
|
||||
@@ -89,7 +96,7 @@ Available references:
|
||||
- `references/党政红风格.md`
|
||||
- `references/教学课件风.md`
|
||||
|
||||
When adding a reusable style to the library, also add its `references/{style_name}.md` file to this list.
|
||||
This list only tracks built-in styles shipped with the skill. Do not add user custom styles here; they are saved to `${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/` via `docs/style-library.md` and discovered by directory scan, so they need no registration.
|
||||
|
||||
Example style confirmation:
|
||||
|
||||
|
||||
@@ -138,6 +138,7 @@ Report:
|
||||
- Confirm which image backend was used and that every non-sample slide result was recorded with `record_slide_result.py`.
|
||||
- Confirm that speaker notes from `speech.md` were written into the PPT, if applicable
|
||||
- Any slides that were regenerated, blocked, or still have known limitations
|
||||
- If the deck's style is custom or noticeably adapted (extracted from user references, tuned during sampling, or otherwise not an unmodified built-in style), end with a one-sentence tip that the style can be saved to the personal style library for future reuse, for example: "如果你喜欢这套风格,可以说「保存这个风格」,我会把它存入个人风格库(`~/.codex-ppt-skill/references/`),以后可以直接复用,更新 skill 也不会丢失。" If the user agrees, read `docs/style-library.md`. Skip this tip when the deck used an unmodified built-in style.
|
||||
|
||||
## Prompting Principles
|
||||
|
||||
|
||||
@@ -4,6 +4,8 @@ Read this when the user asks to save a finished deck style, a sample-slide style
|
||||
|
||||
The goal is to save a reusable visual system, not the current deck's private content.
|
||||
|
||||
User custom styles are saved to `${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/`, outside the skill install directory, so they survive skill updates and reinstalls. Never write user custom styles into the skill's own `references/` directory; that directory is reserved for built-in styles shipped with the skill.
|
||||
|
||||
## When To Use
|
||||
|
||||
Use this workflow when the user says things like:
|
||||
@@ -14,7 +16,7 @@ Use this workflow when the user says things like:
|
||||
- Turn this image/PDF/PPT/PPTX style into a built-in reference.
|
||||
- Save the style from the finished deck.
|
||||
|
||||
If the user only wants to use a style once, extract a temporary style description for the current deck instead of writing a new `references/` file.
|
||||
If the user only wants to use a style once, extract a temporary style description for the current deck instead of writing a new style file.
|
||||
|
||||
## Inspect The Visual Source
|
||||
|
||||
@@ -49,16 +51,18 @@ Do not save private or one-off content as style:
|
||||
- Do not save the user's original article text, business data, personal information, customer names, private project names, paper results, exact quotes, or slide copy.
|
||||
- Do not save source images or screenshots as required dependencies of the style file.
|
||||
- Do not preserve identifiable logos or brand names unless the user explicitly asks for a reusable brand style.
|
||||
- Do not make the style depend on files outside `references/`.
|
||||
- Do not make the style depend on external files; the style file must be self-contained.
|
||||
|
||||
## Name The Style
|
||||
|
||||
Name the file:
|
||||
|
||||
```text
|
||||
references/{style_name}.md
|
||||
${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/{style_name}.md
|
||||
```
|
||||
|
||||
Create the directory first if it does not exist.
|
||||
|
||||
Naming rules:
|
||||
|
||||
- Prefer a short Chinese style name, usually 2-8 Chinese characters or a concise Chinese phrase.
|
||||
@@ -67,11 +71,11 @@ Naming rules:
|
||||
- Avoid vague names like `我的风格1`, `好看风`, or `新风格`.
|
||||
- Good examples: `深色数据科技风`, `极简发布会风`, `柔和学术插画风`, `高密度咨询风`.
|
||||
|
||||
If the target filename already exists, ask whether to overwrite, merge, or choose a new name.
|
||||
If the target filename already exists in the user style directory, ask whether to overwrite, merge, or choose a new name. If the filename matches a built-in style in the skill's `references/`, tell the user the custom file will take priority over the built-in style with the same name, and confirm that is intended before saving.
|
||||
|
||||
## Write The Style File
|
||||
|
||||
Match the existing `references/*.md` structure:
|
||||
Match the structure of the built-in files in the skill's `references/`:
|
||||
|
||||
# {style_name}
|
||||
|
||||
@@ -137,23 +141,15 @@ Match the existing `references/*.md` structure:
|
||||
|
||||
The JSON should be directly reusable as a slide generation style brief. Keep it descriptive enough for future agents, but avoid embedding task-specific content.
|
||||
|
||||
## Make The Style Discoverable
|
||||
## Discovery
|
||||
|
||||
After writing `references/{style_name}.md`, update `docs/outline-style-and-sample.md`.
|
||||
|
||||
Add the new file to the `Available references` list:
|
||||
|
||||
```markdown
|
||||
- `references/{style_name}.md`
|
||||
```
|
||||
|
||||
That list is what future style confirmation steps read before offering or using reusable style references.
|
||||
No registration step is needed. Future style confirmation steps scan `${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/` and merge its files with the built-in style list, so the saved file is discoverable automatically. Do not edit `docs/outline-style-and-sample.md` or any other file inside the skill for a user custom style.
|
||||
|
||||
## Final Response
|
||||
|
||||
Report:
|
||||
|
||||
- The new style name.
|
||||
- The saved `references/{style_name}.md` path.
|
||||
- That `docs/outline-style-and-sample.md` was updated.
|
||||
- The saved file path under `${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/`.
|
||||
- That the style is stored outside the skill install, so it survives skill updates and reinstalls.
|
||||
- A one-sentence note on how to request it later, for example: "以后可以说:用「深色数据科技风」生成这份 PPT。"
|
||||
|
||||
Reference in New Issue
Block a user