Core Pipeline: Source Document → Create Project → Template Option → Strategist → [Image_Generator] → Executor → Post-processing → Export

[!CAUTION]

🚨 Global Execution Discipline (MANDATORY)

This workflow is a strict serial pipeline. The following rules have the highest priority — violating any one of them constitutes execution failure:

1. SERIAL EXECUTION — Steps MUST be executed in order; the output of each step is the input for the next. Non-BLOCKING adjacent steps may proceed continuously once prerequisites are met, without waiting for the user to say "continue"
2. BLOCKING = HARD STOP — Steps marked ⛔ BLOCKING require a full stop; the AI MUST wait for an explicit user response before proceeding and MUST NOT make any decisions on behalf of the user
3. NO CROSS-PHASE BUNDLING — Cross-phase bundling is FORBIDDEN. (Note: the Eight Confirmations in Step 4 are ⛔ BLOCKING — the AI MUST present recommendations and wait for explicit user confirmation before proceeding. Once the user confirms, all subsequent non-BLOCKING steps — design spec output, SVG generation, speaker notes, and post-processing — may proceed automatically without further user confirmation)
4. GATE BEFORE ENTRY — Each Step has prerequisites (🚧 GATE) listed at the top; these MUST be verified before starting that Step
5. NO SPECULATIVE EXECUTION — "Pre-preparing" content for subsequent Steps is FORBIDDEN (e.g., writing SVG code during the Strategist phase)
6. NO SUB-AGENT SVG GENERATION — Executor Step 6 SVG generation is context-dependent and MUST be completed by the current main agent end-to-end. Delegating page SVG generation to sub-agents is FORBIDDEN
7. SEQUENTIAL PAGE GENERATION ONLY — In Executor Step 6, after the global design context is confirmed, SVG pages MUST be generated sequentially page by page in one continuous pass. Grouped page batches (for example, 5 pages at a time) are FORBIDDEN
8. SPEC_LOCK RE-READ PER PAGE — Before generating each SVG page, Executor MUST read_file <project_path>/spec_lock.md. All colors / fonts / icons / images MUST come from this file — no values from memory or invented on the fly. Executor MUST also look up the current page's page_rhythm (anchor / dense / breathing), page_layouts (which template SVG to inherit, if any), and page_charts (which chart template to adapt, if any). Empty / absent entries are intentional Strategist signals — see executor-base.md §2.1. This rule exists to resist context-compression drift on long decks and to break the uniform "every page is a card grid" default

[!IMPORTANT]

🌐 Language & Communication Rule

• Response language: match the user's input and source materials. Explicit user override (e.g., "请用英文回答") takes precedence.
• Template format: design_spec.md MUST follow its original English template structure (section headings, field names) regardless of conversation language. Content values may be in the user's language.

[!IMPORTANT]

🔌 Compatibility With Generic Coding Skills

• ppt-master is a repository-specific workflow, not a general application scaffold
• Do NOT create .worktrees/, tests/, branch workflows, or generic engineering structure by default
• On conflict with a generic coding skill, follow this skill unless the user explicitly says otherwise

Main Pipeline Scripts

For complete tool documentation, see ${SKILL_DIR}/scripts/README.md.

Template Index

Standalone Workflows

Workflow

Step 1: Source Content Processing

🚧 GATE: User has provided source material (PDF / DOCX / EPUB / URL / Markdown file / text description / conversation content — any form is acceptable).

No source content? When the user supplies only a topic name or requirements without any file or substantive description, run the topic-research workflow first, then return here with its products as input.

When the user provides non-Markdown content, convert immediately:

✅ Checkpoint — Confirm source content is ready, proceed to Step 2.

Step 2: Project Initialization

🚧 GATE: Step 1 complete; source content is ready (Markdown file, user-provided text, or requirements described in conversation are all valid).

Format options: ppt169 (default), ppt43, xhs, story, etc. For the full format list, see references/canvas-formats.md.

Import source content (choose based on the situation):

⚠️ MUST use --move (not copy): all source files — Step 1's generated Markdown, original PDFs / MDs / images — go into sources/ via import-sources --move. After execution they no longer exist at the original location. Intermediate artifacts (e.g., _files/) are handled automatically.

✅ Checkpoint — Confirm project structure created successfully, sources/ contains all source files, converted materials are ready. Proceed to Step 3.

Step 3: Template Option

🚧 GATE: Step 2 complete; project directory structure is ready.

Default — free design. Proceed directly to Step 4. Do NOT query layouts_index.json. Do NOT ask the user an A/B template-vs-free-design question.

Template flow is opt-in. Enter it only when an explicit trigger appears in the user's prior messages:

1. Names a specific template (e.g., "用 mckinsey 模板" / "use the academic_defense template")
2. Names a style / brand reference that maps to a template (e.g., "McKinsey 那种" / "Google style" / "学术答辩样式")
3. Asks what templates exist (e.g., "有哪些模板可以用")

When triggered: read ${SKILL_DIR}/templates/layouts/layouts_index.json, resolve the match (or list options for trigger 3), and copy:

Soft hint (non-blocking). When content is an obvious strong match for an existing template (e.g., academic defense, government report, McKinsey-style deck) AND no template trigger fired, emit a single-sentence notice and continue without waiting:

Note: the library has a template <name> that matches this scenario closely. Say the word if you want to use it; otherwise I'll continue with free design.

Hint, not question — do NOT block. Skip entirely on weak/ambiguous match.

To create a new global template, read workflows/create-template.md

✅ Checkpoint — Default path proceeds to Step 4 without user interaction. If a template trigger fired, template files are copied before advancing.

Step 4: Strategist Phase (MANDATORY — cannot be skipped)

🚧 GATE: Step 3 complete; default free-design path taken, or (if triggered) template files copied into the project.

First, read the role definition:

⚠️ Mandatory gate: before writing design_spec.md, Strategist MUST read_file templates/design_spec_reference.md and follow its full I–XI section structure. See strategist.md Section 1.

Eight Confirmations (full template: templates/design_spec_reference.md):

⛔ BLOCKING: present the Eight Confirmations as a single bundled recommendation set and wait for explicit user confirmation or modification before outputting Design Specification & Content Outline. This is the single core confirmation point — once confirmed, all subsequent steps proceed automatically.

1. Canvas format
2. Page count range
3. Target audience
4. Style objective
5. Color scheme
6. Icon usage approach
7. Typography plan
8. Image usage approach

Optional — split-mode hint (not a ninth confirmation): when Phase A signals point to heavy downstream load — recommended page count is on the long side, source materials are bulky, or topic-research ran with substantial web-fetch accumulation — append a single short suggestion below the eight confirmations:

💡 本次预计生成 ~N 页、源材料体量较大，建议 Step 5 完成后切换至拆分模式：本对话停止，新窗口输入 继续生成 projects/<project_name> 进入 Phase B（SVG 生成 + 导出）。无回应或选择继续 = 默认连续模式。

This is a hint, not a confirmation item — the user may ignore it. When signals are normal, omit the hint entirely. Default behavior remains continuous mode.

If the user provided images, run analysis before outputting the design spec:

⚠️ Image handling: NEVER directly read / open / view image files (.jpg, .png, etc.). All image info comes from analyze_images.py output or the Design Spec's Image Resource List.

Output:

• <project_path>/design_spec.md — human-readable design narrative
• <project_path>/spec_lock.md — machine-readable execution contract (skeleton: templates/spec_lock_reference.md); Executor re-reads before every page

✅ Checkpoint — Phase deliverables complete, auto-proceed to next step:

Step 5: Image Acquisition Phase (Conditional)

🚧 GATE: Step 4 complete; Design Specification & Content Outline generated and user confirmed.

Trigger: At least one row in the resource list has Acquire Via: ai and/or Acquire Via: web. If every row is user or placeholder, skip to Step 6.

Always load the common framework:

Then lazy-load the path-specific reference for each row that actually needs it:

A deck with only ai rows never loads image-searcher.md; a deck with only web rows never loads image-generator.md. A mixed deck loads both, processes each row through its own path, and writes both image_prompts.md and image_sources.json.

Workflow:

1. Extract all rows with Status: Pending and Acquire Via ∈ {ai, web} from the design spec
2. Generate prompts (ai rows) and/or run search (web rows) per image-base.md §2 dispatch table
3. Verify every row reaches a terminal status: Generated (ai success), Sourced (web success), or Needs-Manual

✅ Checkpoint — Confirm acquisition attempted for every row:

Default — auto-proceed to Step 6. Only when the user's Step 4 response explicitly opted into split mode (in reply to the optional hint), output the Phase A hand-off below and stop this conversation:

On acquisition failure, do NOT halt — follow the Failure Handling rule in image-base.md §5: retry once, then mark the row Needs-Manual, report to user, and continue to the checkpoint above.

Step 6: Executor Phase

🚧 GATE: Step 4 (and Step 5 if triggered) complete; all prerequisite deliverables are ready.

Read the role definition based on the selected style:

Only read executor-base + shared-standards + one style file.

Design Parameter Confirmation (Mandatory): before the first SVG, output key design parameters from the spec (canvas dimensions, color scheme, font plan, body font size). See executor-base.md §2.

Pre-generation Batch Read (Mandatory): before the first SVG, batch-read every distinct layout SVG referenced in spec_lock.page_layouts and every distinct chart SVG referenced in spec_lock.page_charts (plus any §VII backup charts). One read per file, up front — do not re-read these during page generation. See executor-base.md §1.0.

Per-page spec_lock re-read (Mandatory): before each SVG page, read_file <project_path>/spec_lock.md and use only its colors / fonts / icons / images, plus the per-page page_rhythm / page_layouts / page_charts lookups (resolves to template SVGs already loaded in the batch read above). Resists context-compression drift on long decks. See executor-base.md §2.1.

⚠️ Main-agent only: SVG generation MUST stay in the current main agent — page design depends on full upstream context. Do NOT delegate to sub-agents. ⚠️ Generation rhythm: generate pages sequentially, one at a time, in the same continuous context. Do NOT batch (e.g., 5 per group).

Visual Construction Phase: generate SVG pages sequentially, one at a time, in one continuous pass → <project_path>/svg_output/

Quality Check Gate (Mandatory) — after all SVGs, BEFORE speaker notes:

• Any error (banned SVG features, viewBox mismatch, spec_lock drift, etc.) MUST be fixed before proceeding — return to Visual Construction, regenerate that page, re-run check.
• warning entries (low-res image, non-PPT-safe font tail, etc.): fix when straightforward, otherwise acknowledge and release.
• Run against svg_output/ (not after finalize_svg.py — finalize rewrites SVG and masks violations).

Logic Construction Phase: generate speaker notes → <project_path>/notes/total.md

✅ Checkpoint — Confirm all SVGs and notes are fully generated and quality-checked. Proceed directly to Step 7 post-processing:

Chart pages? If this deck contains data charts (bar / line / pie / radar / etc.), run the standalone verify-charts workflow before Step 7 to calibrate coordinates. AI models routinely introduce 10–50 px errors when mapping data to pixel positions; verify-charts eliminates that class of error. Skip if no chart pages.

Step 7: Post-processing & Export

🚧 GATE: Step 6 complete; all SVGs generated to svg_output/; speaker notes notes/total.md generated.

🚧 Image readiness GATE (when Step 5 left ai rows in Needs-Manual): every expected file must exist at project/images/<filename> before running 7.1.

If files are missing: PAUSE, list the missing filenames, point the user to images/image_prompts.md (each ### Image N: block is paste-ready for ChatGPT / Gemini / Midjourney) and the required placement project/images/<filename>. Resume Step 7.1 only after all expected files are in place. finalize_svg.py and svg_to_pptx.py do not detect missing files at this layer — proceeding with gaps produces a deck with broken image references.

⚠️ Run the three sub-steps one at a time — each must complete successfully before the next. ❌ NEVER combine them into a single code block or shell invocation.

Canonical three-command pipeline (mirrors references/shared-standards.md §5):

Step 7.1 — Split speaker notes:

Step 7.2 — SVG post-processing (icon embedding / image crop & embed / text flattening / rounded rect to path):

Step 7.3 — Export PPTX (embeds speaker notes by default):

The two products now read from different sources by design: native pptx consumes svg_output/ so the converter can preserve high-fidelity primitives (icon <use> placeholders, image preserveAspectRatio → srcRect, rounded rect rx/ry → prstGeom roundRect). The legacy/preview pptx still consumes svg_final/ because PowerPoint's internal SVG parser cannot handle those primitives. Pass -s output or -s final to force a single source on both products if you need the older single-source behaviour.

Optional animation flags (the defaults already enable rich entrance animations — adjust only when the user asks for something different):

• -t <effect> — page transition. Default fade. Options: fade / push / wipe / split / strips / cover / random / none.
• -a <effect> — per-element entrance animation. Default mixed (auto-vary across the deck). Pass none to disable, or pick a specific effect like fade. Requires top-level <g id="..."> groups (already required by Executor).
• --animation-trigger {on-click,with-previous,after-previous} — Start mode (matches PowerPoint's animation-pane Start dropdown). Default after-previous (click-free cascade; pace via --animation-stagger). Use on-click for presenter-paced reveals, or with-previous for all-at-once.
• --auto-advance <seconds> — kiosk-style auto-play.

Optional recorded narration (only when the user asks for narrated/video export):

Run the standalone generate-audio workflow. The AI picks a narration backend (edge by default, or a configured cloud provider such as ElevenLabs / MiniMax / Qwen / CosyVoice for high-quality or cloned voices), asks the user once (backend + voice + rate/settings + embed-or-not, all with recommended values), then executes notes_to_audio.py and (if chosen) re-exports the PPTX with --recorded-narration audio.

Do NOT call notes_to_audio.py directly without going through the workflow — --voice / --voice-id is required and the workflow produces the locale/provider-aware recommendation that makes the choice meaningful.

Full effect list, anchor logic, and limits: references/animations.md.

❌ NEVER substitute cp for finalize_svg.py — finalize performs multiple critical processing steps ❌ NEVER force -s output for the legacy/preview pptx (PowerPoint's internal SVG parser drops icons and rounded corners). The default auto-split already gives native the high-fidelity source it needs without touching legacy. ❌ NEVER use --only (it suppresses one of the two output files)

Post-export iteration: whenever the user asks to change anything on a generated slide ("改一下", "调字号", "那里看着不对", "把图片换大点"), the visual-edit workflow is available — surface it as an option. If the user describes the change with enough specificity to apply directly ("第 3 页副标题字号改 32"), edit the SVG directly instead; if they're vaguely pointing at "somewhere" on the deck, run the workflow.

Role Switching Protocol

Before switching roles, MUST first read the corresponding reference file. Output marker:

Reference Resources

Notes

• Local preview: "$PI_BUNDLED_PYTHON" -m http.server -d <project_path>/svg_final 8000
• Troubleshooting: on generation issues (layout overflow, export errors, blank images, etc.), check docs/faq.md for known solutions

Distribution

This repository carries the prompt-and-code half of the skill: SKILL.md, references/, workflows/, scripts/, .env.example, requirements.txt.

templates/ is not distributed — neither here nor on the web. It holds three things that cannot go into a public repository as they are:

• templates/icons/ — 11,600+ SVGs vendored from third-party libraries (Tabler, Phosphor, Simple Icons and others) without their licence notices.
• templates/layouts/ — deck layouts, several of them replicated from specific organisations' brand decks, including logo bitmaps.
• templates/charts/ — chart templates that reference the same design specs.

Every reference to templates/… below therefore describes files you supply yourself. Build the directory as templates/{icons,layouts,charts}/ following the paths named in this file and in workflows/create-template.md, which documents the design_spec.md + layouts_index.json format a layout must follow.

https://www.kzgai.cloud/skills/ppt-master hosts a docs-only package (SKILL.md, references/, workflows/, .env.example, requirements.txt) — the site caps a skill at 64 files / 512 KB and accepts text only, so scripts/ is not there either. Read it on the site, install it here.