Skip to content

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

docs(prompts): calibrate rates are sample averages, use the CAPS rate for acronyms and keep a 5% margin

hugohe3ff4a87668dba
diff --git a/skills/ppt-master/references/executor-base.md b/skills/ppt-master/references/executor-base.md
index f529a01a..7379d451 100644
--- a/skills/ppt-master/references/executor-base.md
+++ b/skills/ppt-master/references/executor-base.md
@@ -271,7 +271,7 @@ Mechanical repetition comes from reusing one carrier and topology without a page
- **Element grouping (Mandatory)**: wrap each logical Slide-local body unit in a descriptive, page-unique top-level `<g id>` with root-coordinate `data-pptx-bounds="x y width height"`. A helper-authored preset atom stays top-level with `data-pptx-frame` and no bounds; nested groups need none. Give a root background image or full-canvas scrim/decoration rectangle a stable `id` plus `data-pptx-role="background"` / `"decoration"` instead of a wrapper. Thresholds, exemptions, and the Morph staging marker: [`shared-standards-core.md`](./shared-standards-core.md) §4.3.
- **Reference — nested edit groups**: a top-level group may contain descriptive nested `<g>` groups for meaningful subunits; they need no bounds and create no animation step, with no default depth or quota.
- **Default — bounds are the module zone, not a glyph box (may skip when no text is estimable)**: make each zone as generous as the canvas and siblings allow without overlap. A group's bounds are the union of every child's geometry — text lines, preset frames, image frames, line stroke half-width — plus margin, never the title text alone. An untransformed line spans `y − 0.85 × font_size` to `y + 0.35 × font_size`. Write the sentence first, then fit the zone to it; recompute the bounds after any font-size, line-count, or child-geometry change.
-- **Width estimation**: width is estimated, never measured per page. The route calibrates every role once before P01 (Default Step 6, Quick §3) and keeps a per-role chars-per-100-px table in context; size each zone as characters ÷ that rate × 100; a line mixing CJK with Latin words or digits adds the two parts, CJK chars ÷ CJK rate + other chars ÷ Latin rate (the estimator already carries the wrapping headroom). Never trim wording to satisfy an estimate. When text does not fit, expand a zone with unused space first, then reflow or switch texture (prose → points) before dropping a qualifier; larger bounds never repair off-canvas text.
+- **Width estimation**: width is estimated, never measured per page. The route calibrates every role once before P01 (Default Step 6, Quick §3) and keeps a per-role chars-per-100-px table in context; size each zone as characters ÷ that rate × 100; a line mixing CJK with Latin words or digits adds the two parts, CJK chars ÷ CJK rate + other chars ÷ Latin rate (acronyms and uppercase words use the CAPS rate; the rates are sample averages while the checker measures real glyphs, so keep about 5% below the bounds width). Never trim wording to satisfy an estimate. When text does not fit, expand a zone with unused space first, then reflow or switch texture (prose → points) before dropping a qualifier; larger bounds never repair off-canvas text.
- **Spec adherence**: binding color, canvas, typography, identity, resource, and template anchors hold; layout and other References apply under §2.1 without becoming locks.
- **Template structure**: inherit the native framework only for `template_reuse_scope: mirror|layout`; `style` uses the flat route.
- **Main-agent ownership**: the current main agent hand-writes every page SVG — never a sub-agent, and never a generator that writes slide files — because pages share upstream context for cross-page continuity. `preset_shape_svg.py` and `shape_boolean_svg.py` print fragments only after the agent has chosen role, operands, paint, and z-order. Resource, inspection, checker, verification, and export tools are unrestricted.
diff --git a/skills/ppt-master/scripts/docs/svg-pipeline.md b/skills/ppt-master/scripts/docs/svg-pipeline.md
index 93ea0833..4370067d 100644
--- a/skills/ppt-master/scripts/docs/svg-pipeline.md
+++ b/skills/ppt-master/scripts/docs/svg-pipeline.md
@@ -1025,8 +1025,12 @@ the SVG quality checker.
`validation/text_calibration.json`, and prints a compact table or JSON. The
estimator is additive across scripts, so a line mixing CJK with Latin words
or digits is estimated as (CJK chars ÷ CJK rate + other chars ÷ Latin rate)
- × 100; spaces, digits, and punctuation count as Latin. Rates are rounded, so
- the estimate carries a few percent of slack; leave that margin in the zone. The checker's overflow
+ × 100; spaces, digits, and punctuation count as Latin. The rates are sample
+ averages taken with the checker's own estimator (headroom included), while
+ the checker measures each real line glyph by glyph: capital-heavy words and
+ wide letters run wider than the Latin rate, so the table also prints a CAPS
+ rate for acronyms and uppercase, and a zone should stay about 5% below its
+ bounds width. The checker's overflow
diagnostic prints that line's average px per character, which is not a
reusable rate. A lock role without its own
`<role>_family` resolves to `title_family` when the role name contains