ppt-orchestra-skill
- Repo stars 12,348
- License Proprietary. LICENSE.txt has complete terms
- Author updated Live
- Author repo skills
- Domain
- Data
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @MiniMax-AI · Proprietary. LICENSE.txt has complete terms
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- macOS · Linux · Windows
- Runtime requirements
- Node.js · Python
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: ppt-orchestra-skill
description: Plan and orchestrate multi-slide PowerPoint creation from scratch. Use before generating a full…
category: data
runtime: Node.js / Python
---
# ppt-orchestra-skill output preview
## PART A: Task fit
- Use case: Plan and orchestrate multi-slide PowerPoint creation from scratch. Use before generating a full deck with subagents: classify each slide type, enforce visual variety, set typography/spacing rules, and run text-based QA to catch content issues..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Typography / Spacing / Avoid (Common Mistakes)” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Plan and orchestrate multi-slide PowerPoint creation from scratch. Use before generating a full deck with subagents: classify each slide type, enforce visual variety, set typography/spacing rules, and run text-based QA to catch content issues.”.
- **02** When the source has headings, the agent prioritizes “Typography / Spacing / Avoid (Common Mistakes)” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “Typography / Spacing / Avoid (Common Mistakes)”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: ppt-orchestra-skill
description: Plan and orchestrate multi-slide PowerPoint creation from scratch. Use before generating a full…
category: data
source: MiniMax-AI/skills
---
# ppt-orchestra-skill
## When to use
- Plan and orchestrate multi-slide PowerPoint creation from scratch. Use before generating a full deck with subagents: c…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Typography / Spacing / Avoid (Common Mistakes)” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "ppt-orchestra-skill" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Typography / Spacing / Avoid (Common Mistakes)
rules -> SKILL.md triggers / order / output contract
runtime -> Node.js / Python | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
} Slide Page Types (Standard)
For slide-by-slide generation (one JS file per slide), classify every slide as exactly one of these 5 page types. This keeps structure consistent and prevents "random layout drift".
- Cover Page
- Use for: opening + tone setting
- Content: big title, subtitle/presenter, date/occasion, strong background/motif
- Table of Contents
- Use for: navigation + expectation setting (3–5 sections)
- Content: section list (optional icons / page numbers)
- Section Divider
- Use for: clear transitions between major parts
- Content: section number + title (+ optional 1–2 line intro)
- Content Page (pick a subtype)
- Text: bullets/quotes/short paragraphs (still add icons/shapes)
- Mixed media: two-column / half-bleed image + text overlay
- Data visualization: chart + 1–3 key takeaways + source
- Comparison: side-by-side columns/cards (A vs B, pros/cons)
- Timeline / process: steps with arrows, journey, phases
- Image showcase: hero image, gallery, or visual-first layout
- Summary / Closing Page
- Use for: wrap-up + action
- Content: key takeaways, CTA/next steps, contact/QR, thank-you
Layout options:
- Two-column (text left, illustration on right)
- Icon + text rows (icon in colored circle, bold header, description below)
- 2x2 or 2x3 grid (image on one side, grid of content blocks on other)
- Half-bleed image (full left or right side) with content overlay
Data display:
- Large stat callouts (big numbers 60-72pt with small labels below)
- Comparison columns (before/after, pros/cons, side-by-side options)
- Timeline or process flow (numbered steps, arrows)
Visual polish:
- Icons in small colored circles next to section headers
- Italic accent text for key stats or taglines
Typography
Choose an interesting font pairing — don't default to Arial. Pick a header font with personality and pair it with a clean body font.
| Header Font | Body Font |
|---|---|
| Georgia | Calibri |
| Arial Black | Arial |
| Calibri | Calibri Light |
| Cambria | Calibri |
| Trebuchet MS | Calibri |
| Impact | Arial |
| Palatino | Garamond |
| Consolas | Calibri |
| Element | Size |
|---|---|
| Slide title | 36-44pt bold |
| Section header | 20-24pt bold |
| Body text | 14-16pt |
| Captions | 10-12pt muted |
Spacing
- 0.5" minimum margins
- 0.3-0.5" between content blocks
- Leave breathing room—don't fill every inch
Avoid (Common Mistakes)
- Don't repeat the same layout — vary columns, cards, and callouts across slides
- Don't center body text — left-align paragraphs and lists; center only titles
- Don't skimp on size contrast — titles need 36pt+ to stand out from 14-16pt body
- Don't default to blue — pick colors that reflect the specific topic
- Don't mix spacing randomly — choose 0.3" or 0.5" gaps and use consistently
- Don't style one slide and leave the rest plain — commit fully or keep it simple throughout
- Don't create text-only slides — add images, icons, charts, or visual elements; avoid plain title + bullets
- Don't forget text box padding — when aligning lines or shapes with text edges, set
margin: 0on the text box or offset the shape to account for padding - Don't use low-contrast elements — icons AND text need strong contrast against the background; avoid light text on light backgrounds or dark text on dark backgrounds
- NEVER use accent lines under titles — these are a hallmark of AI-generated slides; use whitespace or background color instead
Compiling Slides
After all slide JS files are generated in slides/, create slides/compile.js to compile them into a single PPTX:
// slides/compile.js
const pptxgen = require('pptxgenjs');
const pres = new pptxgen();
pres.layout = 'LAYOUT_16x9';
const theme = {
primary: "22223b", // dark color for backgrounds/text
secondary: "4a4e69", // secondary accent
accent: "9a8c98", // highlight color
light: "c9ada7", // light accent
bg: "f2e9e4" // background color
};
for (let i = 1; i <= 12; i++) { // adjust count as needed
const num = String(i).padStart(2, '0');
const slideModule = require(`./slide-${num}.js`);
slideModule.createSlide(pres, theme);
}
pres.writeFile({ fileName: './output/presentation.pptx' });
Run with: cd slides && node compile.js
QA (Required)
Assume there are problems. Your job is to find them.
Your first render is almost never correct. Approach QA as a bug hunt, not a confirmation step. If you found zero issues on first inspection, you weren't looking hard enough.
Content QA
python -m markitdown output.pptx
Check for missing content, typos, wrong order.
When using templates, check for leftover placeholder text:
python -m markitdown output.pptx | grep -iE "xxxx|lorem|ipsum|this.*(page|slide).*layout"
If grep returns results, fix them before declaring success.
Verification Loop
- Generate slides → Extract text with
python -m markitdown output.pptx→ Review content - List issues found (if none found, look again more critically)
- Fix issues
- Re-verify affected slides — one fix often creates another problem
- Repeat until a full pass reveals no new issues
Do not declare success until you've completed at least one fix-and-verify cycle.
Dependencies
pip install "markitdown[pptx]"- text extractionnpm install -g pptxgenjs- creating from scratch
Decide Fit First
Design Intent
How To Use It
Boundaries And Review