Local-first AI presentation production for Chinese office work: turn source material into editable PPTX decks or magazine-style Web Decks, then use DeckIR planning, rendered review, safe repair briefs, page recipes, no-text generated visual layers, and formal delivery audits to keep the result usable in real office workflows.
v4.3.0 · English · 中文 README · Docs · Agent Bridge · Agent Skill
Open Web Experience · Benchmark Wall · v4.3 Rendered Review Loop · v4.3.0 Notes · Skill Market Distribution
Most AI PPT tools can make something that looks finished. Office teams need something they can trust, edit, audit, and revise.
| Need | What Ultimate PPT Master gives you |
|---|---|
| Turn messy source material into slides | A local handoff folder with source markdown, DeckIR page map, evidence refs, and an Agent-ready brief. |
| Keep PowerPoint editable | PPTX output keeps real text, shapes, tables, charts, notes, logos, QR codes, and traceable image sources. |
| Avoid repetitive AI layouts | page recipes and scripts/audit_visual_recipes.py prevent repeated title-card grids and body-slide raster shortcuts. |
| Review before revising | v4.3 writes review-findings.json, repair-plan.json, and user-approved revision-brief.md for the second pass. |
| Stay local-first | The Bridge writes project files on localhost; private source material is not uploaded unless the user explicitly chooses that route. |
Source material
-> Web Experience / Desktop / Bridge
-> DeckIR storyboard + source-map evidence boundary
-> page recipes + editability/raster policy
-> editable PPTX or magazine Web Deck
-> rendered review findings
-> safe repair plan
-> revision-brief.md for the approved second pass
-> formal delivery audits
Core artifacts:
storyboard.json: DeckIR page map with page roles, recipe IDs, evidence refs, raster policy, and editability targets.source-map.json: traceable source claims used by the deck.planning-report.json: route recommendation, fallback status, and planner notes.review-findings.json: rendered-review issues with severity, risk level, repair target, and suggested command.repair-plan.json: low-risk repair candidates; default path is dry-run.revision-brief.md: second-generation brief created only after explicit safe apply.quality-report.json: merged delivery, planning, and rendered-review status.
v4.3 makes the review step actionable without making it dangerous. scripts/review_rendered_deck.py inspects the generated project and writes findings. scripts/apply_review_plan.py --safe-only --dry-run shows what would be applied. --apply only writes planning hints, reports, Agent instructions, and revision-brief.md; it does not rewrite source.md, business facts, or final body claims.
Read the workflow: Rendered Review Loop v4.3. Release: v4.3.0.
git clone https://github.com/kdnsna/ultimate-ppt-master-skill.git
cd ultimate-ppt-master-skill
npm run setup
npm run doctor
npm run bridgeThen open the Web Experience. The v4.1 console still gives one primary next action at a time: prepare the brief, add source material, connect locally, and deliver the handoff project.
| Need | Best route | Output |
|---|---|---|
| Formal report, consulting deck, training deck, editable business material | Editable PPTX | PowerPoint deck with editable text, shapes, charts, tables, notes, and quality checks. |
| Talk, showcase, demo day, editorial presentation | Web Deck | Single-file browser deck with stronger visual rhythm and shareable HTML. |
| Both formal handoff and browser preview | Dual delivery | Separate PPTX and Web projects with shared source and aligned structure. |
| Layer | Release | What it protects |
|---|---|---|
| Rendered review and repair brief | v4.3 Rendered Review Loop | Review after rendering, propose low-risk repairs, generate revision-brief.md only after confirmation. |
| AI planning | DeckIR AI Planning Workflow v4.2 | scripts/ai_storyboard.py, storyboard.json, evidence refs, editability targets, and no-key fallback. |
| Simplified Web console | Simplified Web Console v4.1 | Four-step console, one primary next action, grouped previews, lower first-screen complexity. |
| Hybrid-editable generation | Hybrid-Editable Visual Workflow v4.0 | page recipes, no-text generated visual layers, editable PPTX body content, formal raster policy. |
| Public proof surface | Quality Workbench v2.5 | Benchmark Wall, synthetic proof packs, Design Doctor reporting, and release checks. |
Historical release notes: v4.2.0, v4.1.0, v4.0.0, v3.0.0.
The Benchmark Wall keeps public synthetic proof packs visible before anyone installs the project.
| Proof | Link |
|---|---|
| Stable proof matrix | Quality Workbench v2.5 |
| Rendered review release | Release Notes - v4.3.0 |
| DeckIR AI planning pack | Release Notes - v4.2.0 |
| Hybrid-editable release | Release Notes - v4.0.0 |
| Skill marketplace readiness | Skill Market Distribution |
Copyable marketplace prompt:
Use $ultimate-ppt-master to turn my source material into a quality-checked PPTX or Web Deck with a visual review report.
Expert users can install the Skill directly:
bash -lc 'set -e; dir="$HOME/.codex/skills/ultimate-ppt-master"; if [ -d "$dir/.git" ]; then git -C "$dir" pull --ff-only; else git clone https://github.com/kdnsna/ultimate-ppt-master-skill.git "$dir"; fi; cd "$dir"; npm run setup'Guide: Agent Setup. Local connector: Agent Connect Bridge.
| Need | Read |
|---|---|
| Try the web front door | Web Experience |
| Connect browser, local files, and Agents | Agent Connect Bridge |
| Install and invoke the Skill | Agent Setup |
| Choose PPTX vs Web Deck vs Desktop | Choosing a Workflow |
| Configure provider keys locally | Model and Provider Setup |
| Review v4.3 repair flow | Rendered Review Loop v4.3 |
| Understand DeckIR AI planning | DeckIR AI Planning Workflow v4.2 |
| Understand the v4.0 visual contract | Hybrid-Editable Visual Workflow v4.0 |
| Review release maintenance | Release and Maintenance |
| Debug setup or generation issues | Troubleshooting |
Full map: docs/README.md. Chinese map: docs/zh-CN/README.md.
npm run audit:docs
npm run audit:web-console
npm run audit:presets
npm run audit:quality
npm run audit:market
npm run test:node
npm run test:bridge
npm run test:worker
npm run build:web
npm run build:desktop
git diff --checkThe README promise must stay tied to executable checks. If a capability is advertised here, it should have a doc, script, test, audit, or public proof artifact.