This release includes 1 breaking change for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Topics
+4 more
ReleasePort's take
Moderate signalThe release retires the old "three executor styles" model, making mode and visual style independent axes. It also introduces several new features such as a standalone template‑fill route for .pptx editing and direct on‑canvas editing.
Why it matters: Retiring the coupled executor model requires developers to adjust integration logic; no version bound is given. New features like template‑fill routing and canvas editing enhance workflow flexibility without measurable triggers.
Summary
AI summaryUpdates Highlights, Strategist & content quality, and Export & fidelity across a mixed release.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Breaking | High |
Retires old "three executor styles" model; mode and visual style now independent axes. Retires old "three executor styles" model; mode and visual style now independent axes. Source: llm_adapter@2026-06-14 Confidence: high |
— |
| Feature | Medium |
Adds standalone template-fill route to directly edit existing .pptx files without SVG generation. Adds standalone template-fill route to directly edit existing .pptx files without SVG generation. Source: llm_adapter@2026-06-14 Confidence: high |
— |
| Feature | Medium |
Converts DOCX equations (OMML) to inline LaTeX instead of dropping them. Converts DOCX equations (OMML) to inline LaTeX instead of dropping them. Source: llm_adapter@2026-06-14 Confidence: high |
— |
| Feature | Medium |
Merges paragraph blocks by default during export, reducing text frames. Merges paragraph blocks by default during export, reducing text frames. Source: llm_adapter@2026-06-14 Confidence: high |
— |
| Feature | Medium |
Introduces OpenAI‑compatible knobs to simplify image generation configuration. Introduces OpenAI‑compatible knobs to simplify image generation configuration. Source: llm_adapter@2026-06-14 Confidence: high |
— |
| Feature | Medium |
Adds direct on‑canvas editing (L1 text, L2 style, L3 geometry) with move coordinates in `svg_editor`. Adds direct on‑canvas editing (L1 text, L2 style, L3 geometry) with move coordinates in `svg_editor`. Source: llm_adapter@2026-06-14 Confidence: high |
— |
| Feature | Medium |
Preserves stroke colors of outline icons during rendering. Preserves stroke colors of outline icons during rendering. Source: llm_adapter@2026-06-14 Confidence: high |
— |
| Feature | Low |
Provides `ppt-master-skill-v2.10.0.zip` (~48 MB) containing only the skill for non‑Claude‑Code hosts. Provides `ppt-master-skill-v2.10.0.zip` (~48 MB) containing only the skill for non‑Claude‑Code hosts. Source: llm_adapter@2026-06-14 Confidence: high |
— |
| Bugfix | Medium |
Tolerates notes slides whose placeholders have no `notesMaster` in PPT source conversion. Tolerates notes slides whose placeholders have no `notesMaster` in PPT source conversion. Source: llm_adapter@2026-06-14 Confidence: high |
— |
| Bugfix | Medium |
Drops redundant post‑generation in‑image text verification step. Drops redundant post‑generation in‑image text verification step. Source: llm_adapter@2026-06-14 Confidence: high |
— |
Full changelog
Highlights
Mode + Visual-Style — two independent catalogs
The old "three executor styles" model is retired. Deck structure and deck look are now two orthogonal axes the Strategist locks separately, so any structure can pair with any style:
- Modes (how the argument is structured) —
pyramid/narrative/instructional/showcase/briefing, plus a user-authority escape hatch for custom structures. Keynote / 发布会 / TED-style requests route toshowcase. - Visual styles (how the deck looks) — the catalog grew to 16 named styles across regrouped families (Swiss-minimal, editorial, soft-rounded, dark-tech, brutalist, blueprint, memphis, zine, photo-editorial, data-journalism, ink-wash, glassmorphism, …), each zero-HEX and reference-strength so palette stays driven by the deck's real colors.
- The Strategist locks
modeandvisual_styleindependently intospec_lock.md; the executor and resume-execute paths read both.
Template-fill — direct PPTX route (issue #53)
A new standalone route reuses an existing .pptx design and fills new content back into it, editing PPTX directly (it never enters the SVG generation pipeline) so the output stays natively editable:
- check-plan guardrails flag non-text source pages and over-reuse of the same source slide before filling.
- Slide library now exposes chart data, and private parts are isolated on slide reuse with improved capacity checks.
- See
workflows/template-fill-pptx.md.
Strategist & content quality
- One core message per outline page — each page now carries a single primary point, pushing decks away from the even-weight "web look".
- Per-block expression register — each content block follows its natural expression mode instead of defaulting to bullets; prose rendering hardened against bullet gravity.
- Hero-page title layer choice at h.5 (default SVG title vs. embedded-in-image title).
- Opt-in refine-spec checkpoint — ask to review/revise the full spec before any image or SVG work; off by default. (
workflows/refine-spec.md)
Converter
- DOCX equations → LaTeX — Word-native and MathType "Office Math" (OMML) formulas are now rewritten to inline LaTeX instead of being silently dropped. Pure-Python, no new dependencies. (Classic MathType OLE objects carry no OMML and are kept as their preview image.)
- PPT source — tolerate notes slides whose placeholders have no
notesMaster.
Export & fidelity
- Paragraphs merge by default — mergeable
dy-stacked blocks collapse into one editable text frame; pass--no-mergefor strict per-line fidelity. - Accurate document properties stamped on export, with an optional
metadata.jsonoverride. - PPTX ⇄ SVG text fixes — font-size resolved from
pPr/defRPr, placeholder list text styles inherited, digits/%treated as tabular width, CJK soft-break join spaces dropped, flat inline tspan runs merged. - Wider font variety and recognition to reduce default-font sameness across decks.
Image generation
- OpenAI-compatible knobs replace per-provider backends, simplifying configuration.
- Dropped post-generation in-image text verification (redundant with live preview).
Live preview & editor
- Direct on-canvas editing (L1 text / L2 style / L3 geometry) documented across the guides;
svg_editornow accepts added move coordinates.
Icons
- Outline icons preserve their stroke colors.
Community
- New corporate sponsor: RunAPI.
- README reframed around "it's a tool, not a wishing well"; Gemini 3.5 Flash noted as a strong value pick.
Loading just the skill? The attached ppt-master-skill-v2.10.0.zip (~48 MB) contains only skills/ppt-master/ for Codex / Cursor / non-Claude-Code hosts. The full repository remains the primary working form.
Breaking Changes
- Retires the old "three executor styles" model; mode and visual style are now independent axes locked separately in spec_lock.md.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About ppt-master
AI generates natively editable PPTX from any document — real PowerPoint shapes, not images — no design skills needed
Related context
Related tools
Beta — feedback welcome: [email protected]