Skip to content

AgentiaPT/vela-slides / skills/vela-slides

vela-slides

Unverified

Create presentation decks using the Vela engine. Compact DSL format — never verbose JSON. Also loads, extracts, and edits existing decks.

FileKindSize
SKILL.mdskill md6.5 KB
app/vela.jsxother2.3 MB
examples/vela-demo.jsonconfig87.0 KB
references/block-schema.mdmarkdown25.6 KB
references/design-patterns.mdmarkdown20.5 KB
references/formats.mdmarkdown4.6 KB
references/themes.mdmarkdown4.5 KB
scripts/_safe_term.pyscript10.2 KB
scripts/assemble.pyscript9.3 KB
scripts/validate.pyscript16.7 KB
scripts/vela.pyscript115.0 KB

references/formats.md

View on GitHub
# Vela JSON Formats — Detailed Reference

## Format Detection

| Format | Detection | Token savings | Use case |
|---|---|---|---|
| **Full** | has `"lanes"` key | baseline | editing, shipping, human-readable |
| **Compact** | has `"S"` key | ~32% fewer | LLM generation (named keys = reliable) |
| **Turbo** | top-level is array | ~47% fewer | storage, cache, inter-LLM context |

Pipeline: any format → `_load_full()` auto-expands → validate → assemble → ship.

**Deck-level optional fields (Full format only).** Besides `deckTitle` and
`lanes`, a Full deck can carry `branding`, `guidelines` and `session`.
`session` is `{ "start": <epoch ms>, "end": <epoch ms> }`: whole numbers,
years 2000–2100, length 1 min to 24 h. The app drops an invalid value;
`validate.py` warns about it. The app sets this field (session end time);
compact and turbo do not carry `branding`, `guidelines` or `session`.

## Compact Format — Full Key Reference

### Key Differences from Full Format

| Full JSON | Compact JSON | Savings |
|---|---|---|
| `"type": "heading"` | `"_": "heading"` | shorter keys |
| `"text": "..."` | `"x": "..."` | shorter keys |
| `{"type":"spacer","h":8}` | `8` | spacer → int |
| `"bg":"#0A0F1C","color":"#E6F1FF",...` per slide | `"t":"d"` (theme ref) | theme presets |
| `"lanes":[{"items":[{"slides":[...]}]}]` | `"S":[...]` | flat structure |
| `"#3B82F6"` repeated 28× | `"$A"` + `"C":{"$A":"#3B82F6"}` | color palette |

### Compact Key Mapping

**Top-level**: `n`=deckTitle, `T`=themes, `C`=color palette, `S`=slides array

**Slide level**: `t`=theme ref, `n`=title, `d`=duration, `B`=blocks, `p`=padding (only if overriding theme)

**Block level**: `_`=type, `x`=text, `s`=size, `c`=color, `i`=icon, `b`=bg, `w`=weight, `ic`=iconColor, `ib`=iconBg, `I`=items, `B`=blocks (nested), `g`=gap, `lb`=label, `v`=variant, `H`=headers, `R`=rows, `sl`=sublabel, `slc`=sublabelColor, `ac`=arrowColor, `lc`=labelColor, `ts`=titleSize, `xs`=textSize, `hb`=headerBg, `hc`=headerColor, `cc`=cellColor, `bc`=borderColor, `str`=striped, `lo`=loop, `lnc`=lineColor, `nc`=numberColor, `tc`=titleColor, `xc`=textColor, `dc`=dotColor, `cir`=circle, `dir`=direction

**Color palette (`C`)**: define every color used ≥2× as `"$A":"#hex"`. Use `$A` everywhere instead of raw hex. Assign in frequency order ($A = most common).

**Theme palette (`T`)**: `"d"`:dark, `"l"`:light, `"a"`:alt. Keys: `b`=bg, `c`=color, `a`=accent, `p`=padding. Theme values can use `$` aliases too.

**Spacers**: bare int `8` instead of `{"_":"spacer","h":8}`

### Compact Conversion Commands

```bash
# Convert full → compact (for analysis/storage)
vela deck compact full.vela compact.vela

# Convert compact → full
vela deck expand compact.vela full.vela

# Ship auto-expands compact format transparently
vela deck ship compact.vela    # expand → validate → assemble → copy

# All read commands auto-expand compact format
vela deck list compact.vela    # works
vela slide view compact.vela 3 # works
```

## Turbo Format (~47% fewer tokens)

Positional arrays + color palette. NOT for LLM generation — for storage, cache, and passing deck context between LLM calls. The format eliminates all JSON key names by using positional arrays with implicit schemas.

Structure: `[deckTitle, [lanes], colorPalette]`
Blocks: `[type_id, ...positional values]` where type IDs: 0=badge, 1=spacer, 2=heading, 3=text, 4=grid, 5=icon, 6=callout, 7=icon-row, 8=code, 9=table, 10=flow, 11=steps, 12=tag-group, 13=divider, 99=passthrough

```bash
# Convert to turbo
vela deck turbo full.vela turbo.vela
vela deck turbo compact.vela turbo.vela  # compact→full→turbo automatically

# Read/ship turbo (auto-expands)
vela deck list turbo.vela
vela slide view turbo.vela 3
vela deck ship turbo.vela

# Expand turbo back to full
vela deck expand turbo.vela full.vela
```

## Workflow with Formats

```bash
# 1. LLM generates compact JSON (minified, named keys = reliable)
create_file /home/claude/deck.vela   # compact format

# 2. Ship (auto-expands + validates + assembles)
vela deck ship /home/claude/deck.vela

# 3. Edits work on any format (auto-expand on load)
vela slide edit /home/claude/deck.vela 3 block.2.text "New heading"
vela deck ship /home/claude/deck.vela

# 4. For passing deck context to another LLM call (minimal tokens)
vela deck turbo deck.vela context.vela   # 47% fewer tokens
```

## Benchmark (6-slide deck, 16 operations)

```
Baseline (full+minified):  4,955 bytes
Compact (short keys+palette): 3,363 bytes (32.1% smaller)
Turbo (positional arrays):    2,600 bytes (47.5% smaller)

All CLI operations work on any format: list, view, edit, replace-text,
insert, move, duplicate, remove, remove-block, validate, ship.
```
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall