Next AI Draw.io
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
Consulting firm-style PowerPoint design system for AI agents. 70 layout patterns, flat design, python-pptx. 麦麸风格PPT设计系统。
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/likaku-mck-ppt-design-skill)MCP servers that connect the AI to services for the same work
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.
Verified React chart generation: select, validate, repair, render, and inspect charts through MCP.
Same kind of work, ordered like the Skills list
| This one Mck-ppt-design-skill | impeccable | diagram-design | frontend-slides | guizang-ppt-skill | |
|---|---|---|---|---|---|
| Maker | likaku | pbakaus | cathrynlavery | zarazhangrui | op7418 |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 346 | 113,042 | 68,296 | 32,579 | 30,091 |
| Last code change | Nov 3, 2026 | Nov 19, 2026 | Nov 19, 2026 | Jun 24, 2026 | Oct 30, 2026 |
| License | Apache-2.0 | Apache-2.0 | MIT | MIT | AGPL-3.0 |
1 skills (instruction sets) by likaku that an AI reads and follows · not an MCP server
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Claude CodeCursor
From the maker’s README and the folders in the repo
GitHub account likaku (person), 15 years old
★ 346 stars, few users so far · code last changed Nov 3, 2026
22 scripts that can run on a computer: scripts/gh_setup.sh, examples/freeform_showcase.py, examples/minimal_example.py, examples/staircase_civilization.py and 18 more
Scripts that go online: mck_ppt/cover_image.py
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 4922199 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Uploading to claude.ai would fail: the description is over 200 characters (990). Use "Let the AI install it" instead
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /Mck-ppt-design-skill or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Put the mck-ppt-design folder at ~/.agents/skills/mck-ppt-design
~ is your home folder ($HOME)
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Copy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick Mck-ppt-design-skill
Checked against official docs Nov 12, 2026 · Source: cursor.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
The text below comes from the maker’s repo, not from PopNx MCP
Showing the first 8,000 characters · Open the full file on GitHub
---
name: mck-ppt-design
description: >-
Create professional, consultant-grade PowerPoint presentations from scratch
using MckEngine (python-pptx wrapper) with McKinsey-style design. Use when
user asks to create slides, pitch decks, business presentations, strategy
decks, quarterly reviews, board meeting slides, or any professional PPTX.
AI calls eng.cover(), eng.donut(), eng.timeline() etc — 62 active layout methods
across 8 categories (structure, data, framework, comparison, narrative,
timeline, team, charts, images, advanced viz, dashboards, visual storytelling),
consistent typography, zero file-corruption issues, BLOCK_ARC native shapes
for circular charts (donut, pie, gauge), production-hardened guard rails
for spacing, overflow, legend consistency, title style uniformity,
dynamic sizing for variable-count layouts, horizontal item overflow
protection, chart rendering, and
AI-generated cover images via Tencent Hunyuan 2.0 with professional cutout,
cool grey-blue tint, and McKinsey-style Bézier ribbon decoration.
---
# McKinsey PPT Design — Harness Framework
> **Version**: 2.4.1 · **Engine**: MckEngine (python-pptx) · **Author**: [likaku](https://github.com/likaku/Mck-ppt-design-skill)
>
> **Required tools**: Read, Write, Bash · **Requires**: `pip install python-pptx lxml`
---
## 常见崩坏模式(每次生成前必读,先于 HARD RULES)
> 告诉 AI 要做什么效果一般,告诉它前人最容易在哪里塌效果更好。
> 以下三种反模式均已在真实执行中被验证,每次必须主动警惕。
### 反模式 1:口头宣布"门禁通过"(最常见)
**错误做法**:
> 「S4 QA 共 7 个 errors,判断均为 engine 设计行为,门禁通过,进入 S5」
**问题所在**:`passed` 是由 AI 口头判断的,不是由程序派生的。无论理由多充分,这句话都是 AI 在给自己写完成证书。
**正确做法**:
1. 执行 `python references/scripts/gate_check.py <pptx路径> <项目目录>`
2. 读取 `<项目目录>/gate_result.json`
3. 只有 `gate_result.json` 中 `"passed": true` 时,才能进入 S5
4. 如果 `"passed": false`,修复 `user_code_errors` 列表中的问题,重新渲染,再次执行 gate_check
---
### 反模式 2:S3 门禁"脑子里过一遍"就算通过
**错误做法**:
> 「S3 内容门禁预检:API 格式正确,字数在限制内,通过,进入 S4」(没有执行任何代码)
**问题所在**:今天真实发生的 3 个 API 格式错误(`four_column`/`matrix_2x2`/`executive_summary` 参数格式),靠脑子过是过不出来的,必须靠代码检查。
**正确做法**:
1. 执行 `python references/scripts/gate_check_s3.py <content.json路径> <项目目录>`
2. 读取 `<项目目录>/gate_s3.json`
3. 只有 `"passed": true` 时,才能进入 S4
4. 如果有 `fail` 项,修正 `content.json`,重新执行 gate_check_s3
---
### 反模式 3:engine_bug 分类作为软话逃生口
**错误做法**:
> 「peer_font_inconsistency 是 engine 内部设计行为,不是用户代码问题,可以放行」
**问题所在**:这个分类本身是正确的,但由 AI 在对话里口头做出,等于把豁免权交给了 AI 自己——而 AI 有动机让自己通过。
**正确做法**:
`gate_check.py` 里有硬编码的 `ENGINE_BUG_WHITELIST` 枚举。只有在白名单里的 error category,才会被豁免。白名单是代码,不是 AI 的判断。如果你认为某类 error 应该加入白名单,修改 `gate_check.py` 里的枚举,而不是口头声明豁免。
---
## HARD RULES(必须遵守,不可绕过)
1. **每次生成必须走五阶段流程**,不允许"一句话直接生成"跳过前置阶段
2. **TaskCreate 驱动进度**:开始前创建5个 task,每阶段完成后立即 TaskUpdate completed
3. **按需加载上下文**:每个阶段只读对应文件,不要全量加载旧版 SKILL.md 里的内容
4. **门禁必须机读化**:S3 和 S4 门禁必须执行对应的 gate_check 脚本,读 JSON 结果,不得口头判断
5. **Self-Refinement 必做**:每次修正 pattern-level 问题后,写入 `experiences/` 对应文件
6. **引擎导入**:已 `pip install mck-ppt` 则直接 `from mck_ppt import MckEngine`;否则把本 skill 目录加入 `sys.path`(WorkBuddy 默认 `~/.workbuddy/skills/mck-ppt-design`,Claude Code 默认 `~/.claude/skills/mck-ppt-design`)。不确定时先跑 `python -m mck_ppt demo` 验证环境
---
## 知识路由(上下文加载索引)
> **在每个阶段开始时,读对应文件**。不要一次性全读。
| 阶段 | 必须读 | 说明 |
|------|--------|------|
| S1 需求 | `references/team/brand-guide.md` | 了解设计约束 |
| S2 结构 | `references/framework/engine-api.md` + `references/layout-matrix.yaml` | 版式选择和能力边界 |
| S3 内容 | `references/framework/guard-rails.md` + `experiences/*.md`(存在时)| 防溢出规则 + 历史踩坑 |
| S4 渲染 | 用到的 `references/layouts/*.md`(只读实际用到的版式)| 版式实现细节 |
| S5 交付 | 无 | — |
**完整路由表**:`references/INDEX.md`
---
## 五阶段生成流程
```
┌─────────┐ ┌─────────────┐ ┌─────────────┐ ┌──────────────┐ ┌──────────┐
│ S1 需求 │──▶│ S2 结构 ⭐ │──▶│ S3 内容 ⭐ │──▶│ S4 渲染+QA ⭐⭐│──▶│ S5 交付 │
│ brief.md│ │ outline.json│ │content.json │ │ .pptx │ │ + 沉淀 │
└─────────┘ └─────────────┘ └─────────────┘ └──────────────┘ └──────────┘
⭐ = 门禁(FAIL 则在本阶段修正,不得跳过)
S3/S4 门禁必须运行 gate_check 脚本,读 JSON 结果 — 不得口头宣布通过
```
### Stage 1: 需求定义
**读文件**:`references/team/brand-guide.md`
**收集信息**:
- 受众(职位/决策角色)
- 目标(决策/汇报/说服)
- 时长(分钟数 → 约 1 分钟/页)
- 关键信息(最多 5 条核心 message)
- 数据来源(有哪些数据可用)
**产出**:在工作目录创建 `ppt-project-{slug}/brief.md`
**门禁**:`audience` + `goal` + `key_messages` 三项非空(AI 自评即可)
---
### Stage 2: 结构设计
**读文件**:`references/framework/engine-api.md`, `references/layout-matrix.yaml`
**任务**:
1. 根据时长确定页数(1分钟/页)
2. 为每张幻灯片选定 `layout`(查 engine-api.md 速查表)
3. 每页写一句核心 `key_point`(完整句子,不是标签)
4. 确认版式在能力边界内(查 layout-matrix.yaml)
**产出**:`ppt-project-{slug}/outline.json`
```json
{
"brief": {"audience": "董事会", "goal": "战略汇报", "duration_minutes": 15},
"slides": [
{"idx": 1, "layout": "cover", "title": "Q1 2026 战略回顾", "key_point": ""},
{"idx": 2, "layout": "toc", "title": "目录", "key_point": ""},
{"idx": 3, "layout": "table_insight", "title": "市场格局三大转变驱动战略重构", "key_point": ""}
]
}
```
**⭐ 门禁 S2**(AI 自评):
- [ ] `cover` 幻灯片存在
- [ ] 幻灯片数量在时长约束内(`count <= duration_minutes * 1.2`)
- [ ] 所有 layout 在 `layout-matrix.yaml` 中有定义
- [ ] Action Title 均为完整句子(len > 10,包含动词)
- [ ] `two_column_text` 数量 ≤ 1
---
### Stage 3: 内容填充
**读文件**:`references/framework/guard-rails.md`, `experiences/*.md`(全部存在的文件)
**任务**:
1. 为每张幻灯片填充具体文案、数字、图表数据
2. 确保每页有 `source` 出处
3. 按 `layout-matrix.yaml` 的 `char_budget` 控制文字量
**产出**:`ppt-project-{slug}/content.json`
**⭐ 门禁 S3**(必须机读化,不得 AI 自评):
```bash
python ~/.workbuddy/skills/mck-ppt-design/references/scripts/gate_check_s3.py \
<项目目录>/content.json <项目目录>
```
读取 `<项目目录>/gate_s3.json`:
- `"passed": true` → 进入 S4
- `"passed": false` → 修正 `content.json` 中 `fail_items` 列出的问题,重新执行
---
### Stage 4: 渲染 + QA
**读文件**:用到的版式对应的 `references/layouts/*.md`
**任务**:
1. 根据 `content.json` 生成 Python 渲染脚本
2. 执行脚本生成 `.pptx`
3. 运行 QA 门禁脚本
**⭐⭐ 门禁 S4**(必须机读化,不得口头宣布通过):
```bash
python ~/.workbuddy/skills/mck-ppt-design/references/scripts/gate_check.py \
<pptx路径> <项目目录>
```
读取 `<项目目录>/gate_result.json`:
- `"passed": true` → 进入 S5
- `"passed": false` → 查看 `user_code_errors`,修复渲染代码,重新渲染,再次执行
**注意**:`engine_bug` 类 errors(`peer_font_inconsistency` 等白名单条目)由脚本自动豁免,不需要 AI 口头判断。
**产出**:`<项目目录>/gate_result.json` + `.pptx`
---
### Stage 5: 交付 + Self-Refinement
**任务**:
1. 读取 `gate_result.json` 确认 `passed: true`(不得在无此文件时声称通过)
2. 交付 `.pptx` 文件
3. **Self-Refinement**:判断本次是否有 pattern-level 修正
**⭐ Self-Refinement 协议**:
```
修正后判断:
ONE-TIME(单次特定调整)→ 不需要沉淀
PATTERN(跨 deck 可重现的问题)→ 必须写入 experiences/
- 溢出类 → experiences/overflow.md
- 图表限制 → experiences/chart-limits.md
- 版式踩坑 → experiences/layout-pitfalls.md
- 中文渲染 → experiences/cjk-issues.md
格式:
## Experience NNN: {title}
**Date**: YYYY-MM-DD
**Problem**: ...
**Root Cause**: ...
**Fix**: ...
**Rule**: ...(门禁层面如何预防)
```
---
## Fast Track(简单需求跳过 S2/S3 门禁)
满足**全部**条件时,AI 可跳过 S2 结构评审和 S3 内容审查:
- 总页数 ≤ 5
- 无数据图表(donut/bar/table 类)
- 用户明确表达"快速"/"马上要"/"简单"
**仍然必须**:S1 需求收集 + S4 QA 门禁(gate_check.py 脚本执行)+ S5 交付
---
## Checkpoint / 断点恢复
当用户说"继续做那个 PPT"时:
```python
import os, json, glob
projects = glob.glob('ppt-project-*/')
for proj in projects:
brief = os.path.exists(f'{proj}brief.md')
outline = os.path.exists(f'{proj}outline.json')
content = os.path.exists(f'{proj}content.json')
gate_s3 = os.path.exists(f'{proj}gate_s3.json')
gate_s4 = os.path.exists(f'{proj}gate_result.json')
pptx = bool(glob.glob(f'{proj}*.pptx'))
if not brief: stage = 1
elif not outline: stage = 2
elif not content: stage = 3
elif not gate_s3: stage = '3-gate' # content 有了但 gate 还没跑
elif not pptx: stage = 4
elif not gate_s4: stage = '4-gate' # pptx 有了但 gate 还没跑
else: stage = 5
print(f"项目 {proj}: 当前处于 Stage {stage}")
```
---
## MckEngine 快速模板
```python
import sys, os
# pip install mck-ppt 后可省略下面两行;skill 目录按实际安装位置调整
sys.path.insert(0, os.path.expanduser('~/.workbuddy/skills/mck-ppt-design'))
from mck_ppt import MckEngine
from mck_ppt.constants import Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.