Easyslides

Academic PPTX Skill

Generate and edit academic/research PPTX presentations with native editable DrawingML shapes.

EasySlides is a project-backed skill. This file is the agent entrypoint and task router; real deck generation depends on the full repository: scripts/, workflows/, templates/, references/, tests, and local runtime dependencies. Installing only SKILL.md is enough for routing guidance, but not enough to generate or validate PPTX files.

Read ARCHITECTURE.md for the layer model and capability paths. Read INSTALL.md for minimal skill, full local runtime, and developer installation modes.

Route Authority

Before choosing an implementation path, read workflows/routing.md. It owns deterministic route selection for main generation, raw PPTX template fill, native PPTX enhancement, reusable template creation, slide-image reconstruction, audio, preview, and chart verification. The workflow registry is workflows/index.md.

Before selecting a route, invoke the clarification gate in skills/easyslides-clarify/SKILL.md. If the request leaves more than one reasonable interpretation that would affect the route, story, page count, template, visible wording, or visual fidelity, ask the user to choose from explicit options. Do not write a deck plan or generate slide files while a blocking choice remains unanswered.

Core Capabilities

1. Create from scratch: Source content → SVG pages → DrawingML shapes → editable PPTX
2. Edit existing PPTX: Unpack → edit XML → validate → repack
3. HTML/JSX authoring path: Use HTML/JSX as an experimental upstream authoring layer, then normalize into EasySlides-compatible SVG or shape IR before the existing DrawingML backend
4. Academic scenario/template system: Scenario-first academic planning with template-extensible output. The official template set is academic_general, academic_scqa, defense_leftnav, defense_topnav, literature_minimal, nsfc_defense, and thu_speech; templates/template_policy.json is authoritative.
5. 71 visualization templates: Charts, infographics, diagrams, strategic frameworks, and tables
6. 11,635 icons: Six SVG icon families for consistent academic and business visuals, with lucide preferred for new generic icons and emoji replacement
7. Template Asset Bank: Convert many real PPTX templates into exact-reuse slide modules for manual-template-substitution quality
8. PPT Master Page Recipe Library: whole-page SVG layout archetypes with fixed regions, text slots, diversity rules, and strict SVG slot measurement
9. Card Component Library: 13 fixed-size card styles plus PPT Master-style visual recipes with slot capacity contracts, agent selection rules, prompt skeletons, and PPTX preview export
10. PPT Master compatibility mode: Strict serial Strategist/Executor workflow, hand-written SVG pages, native DrawingML export, rebuildable backups, and gate checks via scripts/ppt_master_pipeline.py
11. Native PPTX template fill route: Raw PowerPoint templates route to workflows/template-fill-pptx.md instead of the SVG pipeline.
12. Native PPTX enhancement route: Finished decks route to workflows/native-enhance-pptx.md for notes/audio/timing/transition patches without visible-slide regeneration.
13. Confirmation page: Package deck-plan assumptions with scripts/confirm_ui.py before visual execution when the user wants a reviewable confirmation page.
14. Visual review package: Render or reuse slide PNGs through scripts/visual_review.py to produce a review manifest, local HTML page, and contact sheet.
15. Brand presets: Register reusable palette/typography/logo inputs with scripts/create_brand.py under templates/brands/.
16. Clarification gate: Resolve result-affecting ambiguity through explicit user choices before route selection and execution.

Backend-Centered Architecture

EasySlides has one production backend: normalized SVG/shape IR converted to editable DrawingML/PPTX by the local scripts/svg_to_pptx/ pipeline. Multiple authoring frontends may feed that backend, but do not introduce a second production PPTX backend unless a dedicated spike proves better editable output, Office compatibility, and lower maintenance cost.

Path A: Create from Scratch (SVG → DrawingML → PPTX)

When no template PPTX exists, use the SVG-to-DrawingML pipeline:

Source Content → Project Init → Strategist (Deck Plan + Design Spec) → SVG Generation → Quality Check → Export PPTX

Key advantage: Every SVG element becomes an editable DrawingML shape — text is selectable, colors are changeable, shapes are movable.

Path B: Edit Existing PPTX (XML Unpack/Edit/Repack)

When a template PPTX exists:

Template PPTX → Unpack XML → Edit Content → Clean Orphans → Validate → Repack PPTX

Key advantage: Preserves all template formatting, animations, and layout structure.

If the user asks to improve the look of an existing PPTX while preserving slide count, order, and visible wording, route through workflows/beautify-pptx.md. That route currently supports inspection plus a conservative native theme-color patch; stronger layout repair must not silently restructure the deck through the main generation path.

Path C: HTML/JSX Authoring (Experimental Upstream)

When the source is a rendered HTML page, dashboard, report, or SVG-heavy technical slide, use HTML/JSX only as an authoring and measurement layer:

HTML/JSX source -> browser measurement / component declarations -> normalized SVG or shape IR -> EasySlides validation -> DrawingML export

Key advantage: HTML/JSX is easier for LLMs to author for complex layouts, component reuse, dashboards, and architecture diagrams. The output still flows through the EasySlides checker and DrawingML backend.

Boundary: @artifact-kit/pptxgenjs-jsx and html-to-pptx-skill may be used as references or in isolated spikes, but they are not main-path dependencies of EasySlides. Prefer integrating their DOM measurement and JSX authoring ideas upstream of the existing SVG/DrawingML backend.

Use workflows/html-jsx-authoring.md when evaluating this path.

Path D: PPT Master Compatibility Mode

When the user explicitly asks to reproduce PPT Master, use the PPT Master workflow, or prioritize PPT Master-style SVG execution, follow workflows/ppt-master-compat.md.

This mode keeps EasySlides' local converter stack but mirrors PPT Master's operating contract:

Source -> project init -> Strategist design_spec/spec_lock -> optional images
-> Executor hand-writes SVG pages sequentially -> svg_quality_checker
-> validate_svg_text_slots -> notes/total.md -> ppt_master_pipeline export
-> editable PPTX

The Executor must write SVG pages directly into svg_output/; do not create a batch script that generates all pages. Use references/ppt-master-compat.md for execution rules, templates/page_layouts/ppt-master-page-recipes-manual.md for whole-page layout selection, and templates/cards/assembly-manual.md for nested card selection.

For a large library of PPTX templates, prefer the Template Asset Bank harness:

PPTX templates → pptx_template_import.py workspaces → template_asset_bank.json → exact slide-module reuse

Use workflows/template-asset-bank.md and scripts/template_asset_bank.py when the goal is to mimic manual template substitution: fixed geometry, fixed decorative structure, and only text/image/chart data replaced.

Path E: Slide Image Reconstruction

When the source of truth is a slide screenshot, exported slide PNG, or AI mockup image, use workflows/slide-image-to-editable-pptx.md. This is an upstream analysis and QA contract for the existing EasySlides backend: first classify every visible source-image element into Layer A visual assets, Layer B native structure, or Layer C editable text; then assemble through SVG/shape IR and DrawingML export.

This path explicitly forbids full-slide screenshot backgrounds, baked text in image assets, and dirty rectangular crops. Validate the Phase 1 element inventory with scripts/slide_image_inventory.py, then validate the final deck with scripts/validate_image_reconstruction_pptx.py alongside the normal text layout and render-diff gates.

Use scripts/project_manager.py init <name> --kind slide_image_reconstruction and scripts/image_reconstruction_pipeline.py init/qa as the standard project facade for this path. Default QA mode is faithful-practical: editable text, native structure, and split-asset safety are blocking gates, while source-vs-render pixel difference is measured and reported for inspection. Use --mode pixel-strict only when near-pixel source matching is required. Complex raster illustrations that become ugly as vectors should use preserve_source_frame; closed/circular source assets should use masked source assets with clipping checks.

Path F: Native PPTX Template Fill

When the user provides a raw PowerPoint template and asks to fill it with new material or a new topic, route to workflows/template-fill-pptx.md. This path preserves the source deck as a native slide library and patches cloned slides directly through OOXML. Do not convert the raw PPTX template into SVG for a one-off fill request.

Path G: Native PPTX Enhancement

When the user provides a finished PPTX and asks only for speaker notes, narration audio, auto-advance timings, or page transitions, route to workflows/native-enhance-pptx.md. This path is append-oriented and must not regenerate or rewrite visible slide content.

Path H: Visual Review and Brand Presets

When the user asks for a confirmation page or checklist before visual execution, route to workflows/confirm-ui.md. When the user asks for a visual self-check, shareable preview, or review page for an existing deck, route to workflows/visual-review.md. When the user asks to create, register, or inspect a reusable brand palette/logo, route to workflows/create-brand.md.

Academic Scenario-First Template Contract

Use scenario first, template second for academic work. In plain terms: scenario first, template second. The academic scenario defines the argument structure, evidence obligations, audience state, and page roles; the template route defines visual containers, geometry, palette, chrome, and reusable slide modules.

• A template route is not a scenario: template route is not a scenario. Do not infer "thesis defense" just because a defense-looking template is selected, and do not infer "literature report" just because a literature-style shell is available.
• The built-in scenario ids are seed profiles for routing, not a closed taxonomy. If the user's academic use case is not an exact match, select the nearest profile and record scenario_variant in deck_plan.json and design_spec.md.
• Preserve the selected profile's hard and required rules, then explicitly note which recommended or relaxable rules change for the scenario_variant.
• When no matching visual template exists, do not force a defense or literature-report template. Use free academic design, a general academic pack, a domain pack, or a user-provided template path while keeping source traceability, citation retention, text fit, and PPTX deliverability intact.
• When academic_general or academic_scqa is selected, read references/academic-orchestration.md and apply Audience-State-Transfer plus SCQA before selecting layouts. These templates are for audience-facing academic orchestration, not developer-facing production notes.

Source Material Policy

Before planning or generating a deck, classify the user's input:

• No supplied source materials: if the user gives only a topic, requirements, or a request to research before making the PPT, run workflows/topic-research.md. You may gather web text and download relevant openly licensed images as PPT assets, then import the research document and image folder as source materials with provenance.
• Provided mature source materials: if the user supplies a journal paper, thesis/dissertation, mature report, existing deck, or similar file/URL with substantive text, figures, tables, or captions, treat that material as the source of truth. Build from its claims, structure, figures, tables, captions, and user-provided assets. Do not replace extracted figures, invent substitute evidence visuals, change the source claims, or add outside material unless the user explicitly asks; any added generic background/icon must remain decorative and never stand in for source evidence.

Path A: Create from Scratch

Step 1: Requirements & Project Init

python scripts/project_manager.py init <project_name> --format ppt169
python scripts/project_manager.py import-sources <path> <files...> --move

Supported source formats: PDF, DOCX, XLSX, PPTX, URL, Markdown.

MinerU PDF Preprocessing: When importing PDFs, the system automatically tries MinerU for structural extraction before falling back to PyMuPDF. MinerU provides richer output: Markdown with figure/table identification, layout JSON, and extracted images — enabling better PPTX generation with automatic figure extraction.

To enable MinerU: set MINERU_API_TOKEN environment variable or create a .mineru_token file in the project root.

Paper-Report Intake

For single-paper report decks, run the paper-report intake after importing sources and before Strategist writes the final deck plan:

python scripts/paper_intake.py <project_path> --json

The intake reads <project_path>/sources/, Markdown converted from the PDF, MinerU/PyMuPDF-side manifests when present, and <project_path>/images/. It drafts deck_plan.json with a source_map for the main paper plus extracted figures, then validates the draft with scripts/deck_plan_contract.py. Strategist should treat the output as a traceable starting point: verify the paper title, figure captions, claims, and slide roles before writing the final design_spec.md and spec_lock.md.

Single-Paper Literature-Report Flow Selection

Before deriving the outline for single_paper_report, read references/literature-report-flow-selection.md.

If the user provides a page outline, speaking script, learning notes, or slide-by-slide plan, that structure is the primary story contract. Preserve the user's page order and speaking logic, then use the paper/SI to verify claims and source figures. Do not replace the user's structure with an automatic long-form literature-report flow unless the user explicitly asks for a rebuild.

If no outline or script is provided, choose or present two flow options:

• paper_ppt_concise: concise, figure-first 6-10 slide paper report inspired by xiao634zhang/paper-ppt-skill.
• literature_report_deep_dive: 20+ slide deep literature-report planning flow inspired by fangyuanopus/literature-report-ppt-builder, with figure_source_manifest, deck_order_map, and page_briefs before visual execution.

Both options still use EasySlides' editable SVG/shape-IR -> DrawingML backend as the production path.

Scenario Profiles and Rule Layers

Before the confirmation step for academic decks, load the scenario profile catalog from references/scenario_profiles.json.

python scripts/scenario_profiles.py --list --json
python scripts/scenario_profiles.py --profile <profile_id> --json

Seed academic profiles are single_paper_report, multi_paper_review, thesis_defense, proposal_or_fund, lab_progress, workshop_training, and conference_talk. Pick the nearest profile from the source material, audience, and occasion, then state it as a recommendation during confirmations. If the deck is an academic scenario outside these seeds, keep the nearest profile as the rule base and record a scenario_variant rather than squeezing the deck into defense or literature-report wording.

Chinese NSFC Proposal Defense

When the user asks for a Chinese National Natural Science Foundation proposal defense and selects nsfc_defense, activate scenario_id: nsfc_grant_cn. This is a user-facing intent, not a request for the user to learn plan fields: the agent records the scenario contract internally and keeps the conversation in natural language.

For a full deck, organize the argument as: (1) rationale and scientific question, (2) three research contents and their technical route, and (3) innovation, feasibility, and implementation plan. Every page must have one declared narrative responsibility, and the template binds that responsibility to a reviewed content variant. A table-of-contents page is optional; never add one merely because the template has a TOC shell.

Ask with explicit choices before generation only when the request leaves a result-affecting decision unresolved, such as whether this is a project application or a progress defense, whether the user wants a full or concise deck, or whether supplied material may be supplemented by external research. Do not ask the user for grant_role, body_variant_id, coordinates, or other implementation details.

Apply rule layers in this order:

• hard_rules: always enforce; source faithfulness, traceability, citations, text fit, template geometry integrity, and PPTX deliverability.
• required_rules: enforce for the selected scenario unless the user changes the scenario.
• recommended_rules: default guidance such as action titles or ghost-deck checks; apply when useful, but let templates and content needs override.
• relaxable_rules: soft defaults that can yield to venue, template, or teaching/activity format.

Templates control visual containers; scenario profiles control content organization. Template colors, title treatment, page chrome, icon style, and layout density may override profile recommendations only when allowed by template_may_override; they must not override protected items in template_must_not_override.

Deck Plan Contract

After confirmations and before spec_lock.md, write deck_plan.json as the page-level academic story contract:

python scripts/deck_plan_contract.py <project_path>/deck_plan.json --json

Each slide entry must include page, role, action_title, claim, evidence_sources, layout_id, rhythm, and speaker_note. Use action_title for the page's conclusion sentence, claim for the supported statement, and evidence_sources for source-map references such as paper pages, figure/table ids, extracted images, datasets, or user-provided assets. The validated deck plan feeds design_spec.md, spec_lock.md page_rhythm, and later QA gates.

After the deck plan passes, freeze the execution handoff as deck_execution_lock.json:

python scripts/deck_execution_lock.py <project_path>/deck_plan.json --write <project_path>/deck_execution_lock.json --json

The execution lock records the per-page layout_id, rhythm, evidence refs, body variant selection, declared slots, template palette, and required gates. Executor must re-read deck_execution_lock.json together with spec_lock.md before each page. If either file disagrees with the current deck plan, validate with scripts/deck_execution_lock.py --validate and fix the plan before SVG authoring.

When the selected template has body_variants.json, every executable content slide must use a verified body variant in layout_id, provide content_shape, and fill slot_payload with exactly the slots declared by that variant. The scripts/deck_plan_contract.py report includes body_variant_status from scripts/body_variant_adapter.py; body_variant_contract, template_tokens, text_capacity, svg_quality_checker, preview_render, pptx_roundtrip, and visual_measure_gate are blocking gates before SVG authoring. Do not let Executor bypass this by writing arbitrary SVG into a template body canvas.

For managed template packages, compile the canonical sources before rendering:

python scripts/easyslides.py template-compile templates/layouts/<template_id> --write --json
python scripts/easyslides.py slide-compile <project_path>/deck_plan.json --template <template_id> --out <project_path>/slide_ir.json --svg-out <project_path>/svg --pptx-out <project_path>/exports/<deck>.pptx --json

Treat template_package.json, layouts.json, body_variants.json, component_catalog.json, and qa_policy.json as owned sources. Treat compiled/template_ir.json, compiled/template.lock.json, flattened contracts, status files, and registries as generated projections. A composable body variant must bind each required component-local slot to a declared variant slot and resolve every instance to a named region or explicit placement. If several variants score equally and the user intent is unclear, block execution and ask the user to choose; do not silently pick the first variant. A template may expose open_component_composition for an explicitly requested arrangement, but that route accepts only registered local components inside the declared body canvas and never permits global or cross-template assets.

When the selected template exposes a LOGO slot, resolve it from user-provided assets and source-material image folders before SVG generation. Prefer an actual institutional, laboratory, project, or paper-source logo. If no suitable logo is available, keep the template's built-in degree-cap icon fallback; when a real logo is inserted, replace the full LOGO group or hide the fallback drawing.

Academic QA Gate

Before SVG generation, run the Academic QA Gate on the finalized deck_plan.json:

python scripts/academic_qa_gate.py <project_path>/deck_plan.json --json

The gate checks the deck-plan contract plus academic expression rules: action_title must be a conclusion sentence rather than a topic label, result pages need figure/table/data/chart evidence, source-linked decks should include a References/source-provenance slide, and scenarios that recommend conclusion_last should end on Conclusions rather than a generic thank-you page. Errors block execution; warnings should be resolved or consciously accepted before writing final SVGs.

For academic content, run the general clarification gate first. Then present the Five Confirmations (blocking) only for academic values that are still unresolved; do not repeat a value the user already selected:

After user confirms, output deck_plan.json, deck_execution_lock.json, design_spec.md, and spec_lock.md.

Step 2: Template and Design Foundation

Choose the design foundation from the confirmed scenario and template route:

• If the user provides an explicit template path, inspect that template and bind the story roles to its available shells or reusable modules.
• If the user asks to use an available EasySlides template, select the best matching active academic pack from templates/layouts/.
• If no matching template exists, create a free academic design or use a general/domain academic pack; do not force a defense or literature-report template onto unrelated academic scenarios.
• academic_general is the neutral general academic fallback when no domain or scenario-specific pack fits.
• academic_scqa is the structured academic/technical report variant when the material benefits from visible Audience-State-Transfer and SCQA progression.

The design spec must record the chosen scenario_profile, any scenario_variant, the template route, and which template constraints may override visual preferences. Use templates/reference/design_spec_reference.md for the required 11-section structure, then pull the selected template's design_spec.md only if that template is actually selected.

Step 3: SVG Generation

Generate SVG pages sequentially (one at a time). In Path A, each page is hand-written SVG. In Path C, generated SVG must be normalized to the same contract before validation and export.

Critical rules:

• viewBox must match canvas (e.g., 0 0 1280 720)
• Use <rect> for backgrounds, <tspan> for text wrapping
• Never use rgba(), foreignObject, <mask>, or <script>
• Reference icons via <use data-icon="library/icon-name"/> (see templates/icons/README.md); for new generic icons and emoji replacement, prefer lucide/* and color it with the deck theme color
• Use scripts/icon_library.py for icon-family validation, semantic lookup, payload checks, and project-local synchronization. Select one stylistic family per batch; simple-icons is reserved for real brand marks.
• Reference charts from templates/charts/ as SVG templates
• Re-read deck_execution_lock.json and spec_lock.md before every page to prevent layout, body-variant, palette, and gate drift

SVG quality check:

python scripts/svg_quality_checker.py <project_dir>

Step 4: Post-processing & Export

# 1. Split speaker notes
python scripts/validate_svg_text_slots.py <project_dir>/svg_output --strict-unboxed --require-valign --check-canvas --report <project_dir>/reports/svg_text_slot_report.json

# 2. Split speaker notes
python scripts/total_md_split.py <project_dir>

# 3. Finalize SVGs (embed icons, base64 images, flatten text)
python scripts/finalize_svg.py <project_dir>

# 4. Export to PPTX
python scripts/svg_to_pptx.py <project_dir>

Output: exports/<project_name>.pptx with native DrawingML shapes.

Step 5: PPTX Package & Render QA

After every export, run package validation and rendered preview checks before delivery:

python scripts/office/unpack.py <output.pptx> <tmp_unpacked>
python scripts/office/pack.py <tmp_unpacked> <tmp_roundtrip.pptx> --original <output.pptx> --validate true
python scripts/source_to_md/ppt_to_md.py <output.pptx> -o <project_dir>/reports/pptx_text_check.md
python scripts/render_pptx_png.py <output.pptx> --out <project_dir>/reports/rendered_png --report <project_dir>/reports/rendered_png_report.json
python scripts/visual_measure_gate.py --pptx <output.pptx> --report <project_dir>/reports/visual_measure_report.json

If speaker notes are enabled, package validation must prove that ppt/notesMasters/notesMaster1.xml exists, the presentation has a notes master relationship, and the deck has the expected notesSlide*.xml files. Missing notes master relationships are blocking even if slide previews look fine.

visual_measure_gate.py is the blocking exit gate. It aggregates template slot contracts, template geometry, PPTX text layout, and optional rendered-PNG diff reports into visual_measure_report.json; it invokes scripts/validate_pptx_text_layout.py and writes text_layout_report.json as the PPTX text subreport. Repair any SLOT-CONTRACT-*, TEXT-OVERFLOW, TEXT-OVERLAP, TEXT-OFF-SLIDE, TEXT-FONT-TOO-SMALL, protected-region overlap, or visual diff threshold issue before delivery. Fix by shortening copy, splitting slides, choosing a lower-density layout, preserving locked template geometry, or rasterizing complex styling before shrinking body text.

For production templates, template_visual_invariants.py is also mandatory: every data-center-lock="true" text box must be a native middle-aligned text frame, and any declared container relation must share the same vertical centre. Mirrored decoration pairs must be literal 180-degree copies without SVG filters that could introduce directional rendering differences. Never mark an unboxed, source-faithful label as centre-locked merely to satisfy this gate.

Render the final PPTX itself, not just the source SVGs. On Windows the wrapper scripts/render_pptx_png.py automatically prefers the installed Microsoft PowerPoint COM renderer, which exports PNGs using the same Office layout engine that users will see. On other systems, or when PowerPoint is unavailable, it falls back to LibreOffice/soffice -> PDF -> Poppler or PyMuPDF. Use --renderer powerpoint or --renderer soffice to force a backend. If no renderer is available, install one or pass an explicit executable path; do not skip visual QA. Inspect full-size previews for dense cards, process pages, tables, references, and any text that was ported from a larger template. Contact sheets are useful for rhythm only and can hide one-line overflow.

Academic Page Layouts

When academic_general is selected as the neutral fallback, use these base layout patterns:

Content page variants:

• Figure evidence: one primary figure and three observations
• Comparison synthesis: two alternatives plus one decision
• Process outcome: three ordered steps plus one outcome
• Metrics evidence: three metrics plus two evidence rows
• Evidence argument: a text-rich claim plus three auditable arguments
• Table decision: compact three-by-three decision matrix
• Open local composition: explicitly requested placement of registered academic_general components, bounded by the invisible body canvas

Academic Built-in Layout Library

Use templates/layouts/ when the user explicitly asks to use a template path or asks what formal templates are available. The mandatory project policy is templates/template_policy.json; the official set is exactly academic_general, academic_scqa, defense_leftnav, defense_topnav, literature_minimal, nsfc_defense, and thu_speech. Package QA status such as review does not make nsfc_defense non-official. All other templates are development assets and require an explicit user request.

Each classic pack contains design_spec.md and page shell SVGs such as 01_cover.svg, 02_toc.svg, 02_chapter.svg, 03_content.svg, and 04_ending.svg. If a future active pack uses a slot-guided mode, it should also carry layouts.json, page_catalog.json, rules.md, story_structure.json, and generated contract sidecars.

Discovery:

• Human overview: templates/layouts/README.md
• Slim index: templates/layouts/layouts_index.json
• Root template references: templates/reference/design_spec_reference.md and templates/reference/spec_lock_reference.md

Do not fuzzy-match a bare template name when following PPT Master's stricter template flow. Prefer an explicit directory path such as templates/layouts/academic_general/.

Archived Style Packs

The L001 notebook-defense and Guizang style packs are not part of the current project template route. Their assets are managed in the external archive; do not select templates/style_packs/... paths because those paths are intentionally absent from this checkout.

Chart Integration

Reference chart SVGs from templates/charts/. The catalog contains 71 templates. Common academic charts:

To use a chart: read the SVG template, replace placeholder data with actual data, and embed in the slide SVG. For productized selection, use the normalized chart/<chart_id> asset instead of referring to a raw filename. The adapter preserves the PPT Master pick/skip rule while adding family, data model, slots, renderer, editability, provenance, and required QA gates. An explicit chart_id in deck_plan.json is a direct asset match; otherwise the component selector can search the chart catalog by content shape and page role.

python scripts/chart_library.py validate
python scripts/chart_library.py search "trend" --limit 10
python scripts/component_selector.py query --content-shape chart --limit 10

Card Component Library

PPT Master Page Recipe Library

Use templates/page_layouts/ppt_master_page_recipes.json before selecting cards whenever the deck follows the PPT Master-compatible route. Page recipes are the main source of visual diversity: they define the whole-page archetype, regions, slot capacity, and required text measurement contract.

Useful commands:

python scripts/page_recipe.py count
python scripts/page_recipe.py query --content-shape causal_chain --item-count 4
python scripts/page_recipe.py validate --recipe-id pm_causal_map --payload-file payload.json
python scripts/page_recipe.py prompt --recipe-id pm_causal_map

After SVG authoring, run scripts/validate_svg_text_slots.py before export. Every meaningful text item longer than a tiny label should use data-pptx-textbox="true" and data-pptx-box-x/y/w/h with explicit <tspan> lines. If text does not fit, shorten, split, or choose a larger page recipe.

Card Component Library

Use templates/cards/card_library.json when content should be assembled from fixed-size cards instead of freeform text boxes. Read templates/cards/assembly-manual.md before selecting cards. The library currently contains 13 card styles covering metrics, parallel points, comparisons, processes, evidence, method modules, literature notes, and callouts.

For PPT Master-like cards, also read templates/cards/visual-recipes-manual.md and query templates/cards/visual_recipes.json through scripts/card_recipe.py. Visual recipes define fixed geometry, slot capacity, layered SVG skeletons, and a prompt contract the Executor can follow when hand-writing SVG pages.

Useful commands:

python scripts/card_library.py count
python scripts/card_library.py query --content-shape parallel_points --item-count 3
python scripts/card_library.py validate --card-id three_card_summary --payload-file payload.json
python scripts/card_library.py preview --output outputs/card_library_preview.pptx
python scripts/card_recipe.py count
python scripts/card_recipe.py query --content-shape sequence --item-count 3
python scripts/card_recipe.py validate --recipe-id pm_flow_strip --payload-file payload.json
python scripts/card_recipe.py prompt --recipe-id pm_flow_strip

Before rendering a card into PPTX, validate the payload. If a slot exceeds its declared capacity, shorten, split, or choose another card/body variant; do not expand the card or shrink text below the declared minimum.

Path B: Edit Existing PPTX

Step 1: Analyze Template

python scripts/thumbnail.py template.pptx
python -m markitdown template.pptx

Review thumbnails.jpg for layouts, markitdown output for placeholder text.

Step 2: Plan Slide Mapping

For each content section, choose a template slide.

Use varied layouts — monotonous presentations are a common failure mode. Don't default to title + bullet slides. Actively seek out:

• Multi-column layouts (2-column, 3-column)
• Image + text combinations
• Full-bleed images with text overlay
• Quote or callout slides
• Section dividers
• Stat/number callouts

Step 3: Unpack

python scripts/office/unpack.py template.pptx unpacked/

Extracts PPTX, pretty-prints XML, escapes smart quotes.

Step 4: Structural Changes (do sequentially, not with subagents)

• Delete unwanted slides: remove from <p:sldIdLst> in ppt/presentation.xml
• Duplicate slides: python scripts/add_slide.py unpacked/ slide2.xml
• Reorder: rearrange <p:sldId> elements
• Complete all structural changes before editing content

Step 5: Edit Content (parallelizable with subagents)

Each slide is a separate XML file (ppt/slides/slide{N}.xml). Use subagents for parallel editing.

Use the Edit tool, not sed or Python scripts.

Formatting rules:

• Bold headers: b="1" on <a:rPr>
• Never use unicode bullets — use <a:buChar> or <a:buAutoNum>
• Multi-item content: separate <a:p> elements, never concatenate

Step 6: Clean & Validate

python scripts/clean.py unpacked/
python scripts/office/pack.py unpacked/ output.pptx --original template.pptx

Design Quality Standards (from guizang-ppt-skill)

Layout Rhythm

• Alternate light/dark/hero pages — no 3+ consecutive same-theme pages
• Use varied layouts across the deck
• Maintain consistent spacing (card gap 20px, content block gap 24px)

Typography Hierarchy

Color Usage (60-30-10 Rule)

• 60%: Neutral backgrounds (#FFFFFF, #F5F7FA)
• 30%: Primary color (#003366)
• 10%: Accent color (#0066CC, #CC0000 for emphasis)

Icon Discipline

• Use one stylistic icon library per deck; prefer lucide for new generic icons and emoji replacement, with fill set to the deck theme color. simple-icons is only for brand marks.
• Reference via <use data-icon="library/icon-name"/>
• Icons are embedded during finalization — never use emoji

Common Pitfalls

SVG Generation

1. Wrong viewBox: Must match canvas dimensions exactly
2. Missing spec_lock re-read: Re-read before every page
3. Script-generated SVG: Forbidden — each page must be hand-written
4. Using rgba(): Use hex colors with opacity attributes instead
5. SVG <text> labels: Use HTML labels, not SVG text in diagrams
6. Template porting overflow: Compact templates such as defense_leftnav cannot safely reuse long card/process copy from larger templates. Shorten at the source content layer and use punctuation-aware Chinese wrapping before export.

PPTX Editing

1. Unicode bullets: Never use • — causes double bullets
2. Smart quotes: Use XML entities (“ etc.) in new text
3. Missing clean.py: Always run after structural changes
4. Manual slide copy: Use add_slide.py — manual copy misses bookkeeping
5. ElementTree: Use defusedxml.minidom — ElementTree corrupts namespaces
6. Unvalidated speaker notes: Notes slides require a notes master part, relationships, and content types. Always run the unpack/pack validation and a PPT-to-Markdown extraction check after exporting a deck with notes.

Design

1. Monotonous layouts: Vary layout types across the deck
2. Inconsistent spacing: Use the template's spacing system
3. Mixed icon styles: Stick to one library per deck
4. No visual rhythm: Alternate between light, dark, and hero pages

File Structure

<repo>/
├── SKILL.md                          # This file
├── references/
│   ├── workflow-create.md            # Path A detailed workflow
│   ├── workflow-edit.md             

…(truncated)