officecli-pptx
Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions 'deck', 'slides', 'presentation', 'pitch', or references a .pptx filename.
What this skill does
# OfficeCLI PPTX Skill
## Setup
If `officecli` is missing:
- **macOS / Linux**: `curl -fsSL https://d.officecli.ai/install.sh | bash`
- **Windows (PowerShell)**: `irm https://d.officecli.ai/install.ps1 | iex`
Verify with `officecli --version` (open a new terminal if PATH hasn't picked up). If install fails, download a binary from https://github.com/iOfficeAI/OfficeCLI/releases.
## ⚠️ Help-First Rule
**This skill teaches what good slides look like, not every command flag. When a property name, enum value, or alias is uncertain, consult help BEFORE guessing.**
```bash
officecli help pptx # List all pptx elements
officecli help pptx <element> # Full element schema (e.g. shape, chart, animation, connector, zoom, group, background)
officecli help pptx <verb> <element> # Verb-scoped (e.g. add shape, set slide)
officecli help pptx <element> --json # Machine-readable schema
```
Help reflects the installed CLI version. When skill and help disagree, **help is authoritative**. Triggers to run help immediately: `UNSUPPORTED props:` warning, unknown animation preset, `connector.shape=` enum drifts, prop-vs-alias (`lineWidth` vs `line.width`, `color` vs `font.color`).
## Shell & Execution Discipline
**Shell quoting (zsh / bash).** ALWAYS quote element paths (`"/slide[1]/..."`) — zsh globs unquoted `[1]` to `no matches found`. Escapes happen at two layers; the CLI handles one for you:
1. **Shell.** `$` in a value still belongs to the shell — single-quote the whole value: `--prop text='$15M'`. Double-quoted `"$15M"` gets expanded to `M`. The CLI does NOT unescape `\$` for you.
2. **CLI (`text=`).** The two-char escapes `\n` and `\t` ARE interpreted, consistently across pptx / docx / xlsx — `\n` is a line / paragraph break, `\t` is a tab. To produce a literal backslash-n in text, double it (`\\n`); this is rarely what you want.
3. **JSON (batch).** Real newlines / tabs can also be passed as `"\n"` / `"\t"` inside a `<<'EOF'` heredoc; both forms produce the same result.
If in doubt, `view text` after writing and compare character-for-character.
**Incremental execution.** One command → check exit code → continue. A 50-command script that fails at command 3 cascades silently. After any structural op (new slide, chart, animation, connector) run `get` before stacking more.
## Requirements for Outputs
These are the deliverable standards every deck MUST meet. Violating any one = not done, regardless of content quality.
### All decks
**One idea per slide.** If a slide needs a second title to explain what it covers, split it. Dense "everything about X" slides lose the audience inside 3 seconds. Use a section divider to group related one-idea slides, not a mega-slide.
**Explicit type hierarchy — do NOT rely on theme defaults.** Theme defaults drift between masters. Set sizes explicitly on every text shape.
| Element | Minimum | Typical | Min shape height |
|---|---|---|---|
| Slide title | **≥ 36pt** bold | 36–44pt | ≥ 2cm |
| Section / subtitle | ≥ 20pt | 20–24pt | ≥ 1.2cm |
| Body text | **≥ 18pt** | 18–22pt | ≥ 1cm |
| Caption / axis label | ≥ 10pt muted | 10–12pt | ≥ 0.6cm |
Rule of thumb: **min shape height ≈ font_pt × 0.05cm**. An 18pt sublabel in a 0.8cm-tall box will overflow — `view annotated` catches this.
Title must be **≥ 2× body size** (36pt over 20pt works; 28pt over 20pt looks timid). Four legit exceptions to body ≥ 18pt: chart axis labels, legends, footer / page number, and ≤ 5-word KPI sublabels (e.g. "Active users"). Descriptive sentences must be ≥ 18pt. Left-align body; center only titles and hero numbers. If "the cards won't fit", drop cards instead of shrinking font.
**Two fonts max, one palette.** One heading font + one body font (e.g. Georgia + Calibri). One dominant brand color (60–70% weight) + one supporting + one accent. Never mix 4+ colors in body content.
**Every slide carries a non-text visual.** Shape, chart, icon, gradient band. A bullet-only deck is interchangeable with a Word doc. Exceptions: literal quote slides, code blocks, a single summary-table slide.
**Speaker notes on every content slide.** `--type notes --prop text="..."`. The speaker needs a script; the audience shouldn't read the slide verbatim.
**Preserve existing templates.** When a file already has a theme and masters, match them. Existing conventions override these guidelines.
### Visual delivery floor (applies to EVERY deck)
Before declaring done, the per-slide render (see QA) MUST satisfy:
- **No placeholder tokens rendered as content.** `{{name}}`, `$fy$24`, `<TODO>`, `lorem`, `xxxx`, empty `()`/`[]` in chart titles never appear.
- **No overflow past slide edges.** For 16:9 (33.87 × 19.05cm), every shape satisfies `x + width ≤ 33.87cm` AND `y + height ≤ 19.05cm`. `get` and check — don't eyeball.
- **No text overflow inside shapes.** A 72pt KPI in a 4cm-tall box clips. Shrink the number, enlarge the box, or shorten the text — never trim content to fit.
- **Cover slide is content-rich.** Title + subtitle + presenter/client block + date + a brand band or key-takeaway strap. A cover with 80% whitespace reads as a stub.
- **Contrast.** On fills with brightness < 30% (`1E2761`, `36454F`, `000000`, deep forest / berry / cherry), every run of body text, card body, chart series fill, and icon color must be `FFFFFF` or brightness > 80%. Mid-gray (`6B7B8D` ≈ 44%) reads fine on a laptop and vanishes on projection. Verify via `view html` after the dark-fill pass.
- **No `\$` literals in slide text.** If `view text` shows a literal `\$`, the shell didn't unescape it (the CLI does NOT interpret `\$`). Single-quote the value: `--prop text='$15M'`. Note: `\n` and `\t` ARE interpreted as a real paragraph break / tab; seeing those as literals means the value was double-escaped (`\\n`).
If any fails, STOP and fix before declaring done.
### KPI fit math
**KPI text must fit the card — pre-compute, don't eyeball.** In a 7cm-wide card at 60pt Georgia bold, values with `$` and `.` (wide glyphs) wrap at 4 characters. `$9.4M` breaks the card; use `$9M` + "USD millions" sublabel, or move to the 3-card 9.78cm layout. Upper bound: `max_size_pt ≈ card_width_cm × denom`, where denom = 10 for 1–2 chars, 7 for 3–4 chars, 5 for 5+ chars.
### `layout=blank` and alt text
- **`layout=blank` is the default for custom designs.** Titles become plain `shape` elements, not placeholders. `view outline` / `view issues` reporting `(untitled)` / `Slide has no title` is **expected**, not a defect. Use `layout=title` + `placeholder[title]` only when screen-reader outline compatibility matters.
- **Alt text verification.** `view stats "Pictures without alt text: 0"` is a false-positive zero (alt auto-fills to filename) — verify via `view annotated`.
## Design Principles
A deck is not a document. The audience has 3 seconds to get each slide. Before adding anything, ask: "If the audience reads only the biggest element and glances once, do they get the point?" If they have to read the bullets, the biggest element is wrong.
### Grid, margins, negative space
Standard widescreen is **33.87 × 19.05cm**. Treat it as a 12-column grid internally:
- **Edge margin ≥ 1.27cm** (0.5") on all sides.
- **Inter-block gap ≥ 0.76cm** (0.3") between cards / columns / rows.
- **≥ 20% negative space per slide.** Filling every pixel reads as amateur.
- For card grids: `usable = 33.87 − 2·margin − (N−1)·gap`, then `col_width = usable / N`. Don't hand-pick x coordinates.
### Font pairings
Two fonts max — one for headings, one for body. Pair by document register, not by novelty. "Best For" is a prompt, not a decree; if the topic matches a row, use it as the default and move on.
| Header | Body | Best For |
|---|---|---|
| Georgia | Calibri | Formal business, finance, executive reports |
| Arial Black | Arial | Bold marketing, product launches |
| Calibri | Calibri Light | Clean corporate, minimal design |
| Cambria | Calibri | Traditional professional, legalRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.