Planners Ppt Hell logo

Planners Ppt Hell

Community
thePlannerIvan
planners-ppt-hell

制作与持续修改 SVG 页面工作台,从逐页内容稿或 video-idea-system 的 visual-plan.json 与素材出发,输出可编辑 PPT 或固定版本的视频画面快照。用于直接材料或生产包的页面制作、返修、视觉参考复用及需人工确认的模板提炼入库。

Overview

PublisherthePlannerIvan
Repositoryplanners-ppt-hell
Skill nameplanners-ppt-hell
Stars
240
Forks
25
Bundled files
404
LicenseAGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 404 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by thePlannerIvan on GitHub. Read the source before you install it.

Installation

Install the Planners Ppt Hell AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/thePlannerIvan/planners-ppt-hell/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/thePlannerIvan/planners-ppt-hell.git \
  .claude/skills/planners-ppt-hell
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Planners Ppt Hell in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Planners Ppt Hell on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Planners Ppt Hell is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Planner's PPT Hell

由阿祖不看 TVC 创建与维护。https://demyth.info · Lawyif@163.com。 署名保留在 Skill 与工作台,不加入客户 PPT、SVG 或 PNG。

SVG 工作台持续存在。用户改字与模型候选共用版本存储;PPT 与视频快照是可重复输出,不是项目终态。普通页面没有批准门;模板入库保留独立的当前包人工确认。

1. 接收

职责与接口见 架构。读 00_pipeline_controller.md,初始化或恢复同一项目。 幻灯片可接收 Bypage 逐页稿,也可从用户材料、已有稿件或需求直接整理内容;按复杂度调用 Bypage,不把它设为前置门。见 02_content_stage.md。 视频可适配 visual-plan.json 与 assets,也可直接接收上屏稿或材料;已有 screen ID 保持不变。见 03_video_route.md。 沿用 Bypage 的 canonical 来源索引和已绑定的事实核查;内容改写后的核查时机与范围见内容输入文档,不把原 audit 扩大为新页面已核查。 结束条件:来源可读、稳定页面身份可定位、资产已登记且没有静默遗漏。

2. 定方向

一次确认画幅与视觉来源,用户已指明的直接执行。共同秩序写入 _internal/01_content/design_direction.md。 通用判断读 style_system.md;选择信息关系时读 layout_taxonomy.md。模板含义以 模板契约 为准;开画前读取所选模板或视频风格文档并实际查看样张;没有模板时查看本次参考,具体构图由当前内容决定。 幻灯片复用参考、选择库模板或提炼入库时读 01_template_intake.md;只有入库分支需要模板人工确认。 结束条件:方向和画幅明确,必要的源参考已经实际查看。

3. 工作台

读 04_svg_stage.md。模型可以通过 store CLI 新增或删除页面;新增页提交完整 candidate 与 page 元数据,删除页提交 page_key、base_revision 与 base_order。已有页先 checkout 当前页,编辑返回的候选,再提交 author=model、candidate、base_revision。_internal/02_svg_source 是可重建兼容视图,不是生成脚本写入位置。 读取 notes、protected 与待办 tasks;冲突时保留候选并重新读取。遗漏用户操作会被拦下,明确改写范围只来自浏览器任务授权。 用 check --summary 批量检查本轮页面,再逐页查看当前 PNG、记录实际 inspect。打开工作台与反馈恢复见 07_visual_review.md;反馈不是批准,未完成反馈不阻止独立输出。运行在 DSH 时用 review_open 自动加载同一工作台到侧栏;非 DSH 自动启动或复用 planners-review-core 本地宿主。两路共用同一份 Workbench Store、草稿和命令回执。 结束条件:本轮提交有保存回执,技术问题与实际看图结果可查。工作台可继续修改,没有永久 COMPLETE。

4. 输出

网页先保存末次输入、页序和页面集合并提交 snapshot;宿主唤醒携带确切 snapshot.path。运行 python scripts/orchestrate/ppt_pipeline.py <project> export --snapshot <snapshot.json绝对路径> 消费选定版本;指定无效路径直接报错。未指定路径时,export 才固定当前页面、页序与资产。 控制器校验冻结画面。slides 的 PPT、notes 与转换报告在 _internal/06_ppt_output/<snapshot_id>/;export 的 output_path 指向实际输出,根 final_deck.pptx 只是最新兼容副本。video 返回不可变 snapshot.json 给 Video Craft。 PPT 用实际渲染预览运行 export-inspect --snapshot <同一snapshot.json> --previews <实际PNG...> --note "<工具与发现>",绑定该次输出,不要求工作台停止编辑。没有渲染工具就报告未复核,保留 EXPORT_VERIFY;快照校验范围见 项目契约。 视频只保留不可变快照、页序、SVG、资产与 notes;元素 id、步骤钩子、脚本绑定都是可选增强,不要求。报告 content_delta / changed_needs_check;它们不证明新文本与已录音语义一致。动效与合成规范归 Video Craft。 结束条件:输出的快照与文件可定位、技术结果已报告、实际复核工具及限制清楚。随后仍可回到工作台。

按需读取

分支上下文
SVG 特性、缺图或转换错误svg_rules.md;PPT 再读 svg_to_ppt_rules.md
版本、候选、反馈恢复或输出溯源project_contract.md
新模板包制作、审阅、替换入库template_package.md
视频风格选择(本 Skill 自维护风格文档)03_video_route.md;选 editorial-archive 再读 video_style_editorial_archive.md
新视频风格提炼08_video_style_extraction_sop.md
工程维护与验证ARCHITECTURE.md;命令参数以各脚本 --help 为准

运行后迭代

任务后内部自检,仅明确纠正或多次复现的通用缺陷列为候选,项目反馈留在项目;没有可复用发现不增加日志。 改之前读 架构;候选记 GOTCHAS 的现象、原因、行为修正、证据、状态与 module;实际升级记 维护历史 的变化、原因、影响与移除项。 Skill 改动先确认,冻结候选测试,完成后统一发布;候选验收阶段不改正式来源或 runtime。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 140 more files.

Frequently asked questions

What does the Planners Ppt Hell AI skill do?

制作与持续修改 SVG 页面工作台,从逐页内容稿或 video-idea-system 的 visual-plan.json 与素材出发,输出可编辑 PPT 或固定版本的视频画面快照。用于直接材料或生产包的页面制作、返修、视觉参考复用及需人工确认的模板提炼入库。

Why use Planners Ppt Hell on TypingMind?

Because you install it once and use it with any model. Planners Ppt Hell is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Planners Ppt Hell in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/thePlannerIvan/planners-ppt-hell/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Planners Ppt Hell?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Planners Ppt Hell?

As many as you like. As long as a model supports skills, you can use Planners Ppt Hell with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Planners Ppt Hell AI skill free?

Yes. It is published on GitHub by thePlannerIvan under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇