Skip to content
Pro is liveSee plans
Deepdoer skills

Violet Editorial Team Deck

Create a team introduction with monochrome portraits, bold editorial headings, and violet arrow blocks. Explain roles, responsibilities, and shared habits in a presentation you can edit in your browser and export to PowerPoint.

Works in
Claude CodeCodexCursorGemini CLIOpenCodeKimi Code CLIAntigravityGitHub CopilotHermes Agent
Languages
English

Similar Skills

View all skills

What you’ll get

  • A ten-page violet editorial team example with original case content and concise speaker notes.
  • A browser editor and PowerPoint export: text and notes remain editable; backgrounds, drawings, and charts become images.
  • Four coordinated accent presets and ten varied layouts for a coherent presentation.

Great for

  • Small-team introductions and onboarding.
  • Roles, responsibilities, and studio culture.
  • Editorial company or service-team profiles.

Skip it if

  • Copying another team's portraits or names.
  • Dense investor financial modeling.
  • Unverified client outcome claims.

About this Skill

  1. 1Confirm the user's topic, audience, source facts, communication language, content language and slide count. Write slide copy in English unless the user asks for another language. Keep this style's art direction, layout proportions and content limits below; do not substitute a generic template.
  2. 2Plan a clear narrative with one job per page, using the agreed number of fixed 16:9 pages and this style's word budgets and evidence rules.
  3. 3Read this package's style references (below). Named palettes are choices for slide content; the shared editor stays unchanged.
  4. 4Compose from the style kit so the deck matches the store example: write `plan.json` picking a recipe from `references/style-kit.json` for each page (recipes may repeat), set the new text, pictures, picture descriptions (`alt`), icons, chart labels and data values by node ID, remove nodes a page does not need, then run `python3 scripts/style-kit.py compose --style-kit references/style-kit.json --plan plan.json --output project.json`. Work through the report: fill every `unfilledImages` slot and replace each `leftoverExample` entry that belongs to the example's topic. The [compose guide](references/compose.md) documents every plan field. Refine `project.json` where needed (add, delete, move or restyle nodes, keeping IDs unique), keep the kit's `contentCSS`, and write `editor-config.json` with the bundled schema.
  5. 5Pictures:
  6. 6 - Before making any picture, ask the user once (with the step 1 questions when possible) and offer exactly three options. Pictures the user supplies come first in every option. If the user cannot be asked or does not answer, use option 1. Tell the user which option you used.
  7. 7 1. **Reuse this style's original pictures (recommended)**: use only pictures from this Skill's picture library, with no image credits. A slot with no fitting picture keeps its labeled image frame; list those slots for the user.
  8. 8 2. **Generate as needed**: reuse library pictures where they fit and generate only the remaining slots.
  9. 9 3. **Regenerate everything**: generate every picture new for this topic.
  10. 10 - Library: run `node scripts/embed-library-images.mjs --list`; use `any-topic` pictures freely and `topic-specific` ones only when their topic matches the deck, never show one picture on two pages, and set the plan's `images` value (or an image node `src`) to `library:<id>`. After composing, run `node scripts/embed-library-images.mjs project.json` to inline them; if a download fails, treat those slots as unfilled.
  11. 11 - Generate pictures following `references/image-prompts.md`, at the `aspect` that `style-kit.json` and the compose report list for each slot. Use FAL with the user's `FAL_KEY` through `node scripts/fal-image.mjs` (submit once, then status/fetch; each submission is a paid task that is never retried automatically). In ChatGPT or Codex, the built-in image generation (GPT Image) may be used instead and needs no key. Never use another image provider. Library pictures (`--download <id> --out <dir>`) or pictures already made for this deck can be passed as `--reference` to keep the series consistent.
  12. 12 - With neither FAL nor a built-in tool, options 2 and 3 fall back to option 1.
  13. 13Set `uiLocale` and `conversationLocale` to the user's communication language and `contentLocale`/`contentDirection` from the brief; compose detects Chinese, Japanese and Korean plans. Arabic and Hebrew right-to-left layout is handled by the framework; do not reverse logical arrays.
  14. 14Build and check: `python3 scripts/build-deck.py --project project.json --config editor-config.json --output presentation.html`, then `python3 scripts/check-deck.py presentation.html --expected-slides N --style-kit references/style-kit.json --report deck-check.json`. Resolve every example string the check still reports. If it warns about size, run `python3 scripts/optimize-images.py presentation.html` and check again.
  15. 15Open the file over local HTTP and inspect every page: typography, pictures, hierarchy, crops, bounds, contrast and spacing. Edit text, add/delete/move a block, change a color or Smart layout, edit notes, undo/redo, save and reopen. Presentation mode must disable editing and its glass navigation must hide after five idle seconds.
  16. 16Deliver the single HTML file. It opens in a page view with an Edit button and works offline. Tell the user that edits stay in the browser until they press Save (Cmd/Ctrl+S), which writes them into the file. On request, export PPTX from the built-in menu, run `python3 scripts/check-pptx.py presentation.pptx --project project.json --report pptx-check.json` and inspect it in PowerPoint, Keynote or WPS. Keynote uses the compatible `.pptx`. Print/PDF gives one page per slide.
bs-lavender-editorial-team-deck/SKILL.md
---
name: bs-lavender-editorial-team-deck
description: Create a team introduction with monochrome portraits, bold editorial headings, and violet arrow blocks. Explain roles, responsibilities, and shared habits in a presentation you can edit in your browser and export to PowerPoint.
---

# Violet Editorial Team Deck

Use this Skill for team introductions, studio or agency profiles, onboarding decks, and "meet the people" pages. The identity is fixed: grayscale editorial portraits, light paper pages with a few black pages, violet square arrow tiles, one white name card set inside a photo (on at most two pages), and large uppercase Schibsted Grotesk headings with Inter body text (both embedded, offline). Keep that identity across the whole deck.

## Shared editor contract

This style always uses the bundled framework in `references/framework/`; never build a separate editor or paging engine. The editor UI is identical across styles: black, white and gray, with localized icon tooltips and independently editable objects. Palettes, fonts, artwork and layouts stay specific to this Skill and come from its style kit. Read [runtime](references/runtime.md) for the editor, saving and export behaviour, and [compose guide](references/compose.md) for the plan format.

## Workflow

1. Confirm the user's topic, audience, source facts, communication language, content language and slide count. Write slide copy in English unless the user asks for another language. Keep this style's art direction, layout proportions and content limits below; do not substitute a generic template.
2. Plan a clear narrative with one job per page, using the agreed number of fixed 16:9 pages and this style's word budgets and evidence rules.
3. Read this package's style references (below). Named palettes are choices for slide content; the shared editor stays unchanged.
4. Compose from the style kit so the deck matches the store example: write `plan.json` picking a recipe from `references/style-kit.json` for each page (recipes may repeat), set the new text, pictures, picture descriptions (`alt`), icons, chart labels and data values by node ID, remove nodes a page does not need, then run `python3 scripts/style-kit.py compose --style-kit references/style-kit.json --plan plan.json --output project.json`. Work through the report: fill every `unfilledImages` slot and replace each `leftoverExample` entry that belongs to the example's topic. The [compose guide](references/compose.md) documents every plan field. Refine `project.json` where needed (add, delete, move or restyle nodes, keeping IDs unique), keep the kit's `contentCSS`, and write `editor-config.json` with the bundled schema.
5. Pictures:
   - Before making any picture, ask the user once (with the step 1 questions when possible) and offer exactly three options. Pictures the user supplies come first in every option. If the user cannot be asked or does not answer, use option 1. Tell the user which option you used.
     1. **Reuse this style's original pictures (recommended)**: use only pictures from this Skill's picture library, with no image credits. A slot with no fitting picture keeps its labeled image frame; list those slots for the user.
     2. **Generate as needed**: reuse library pictures where they fit and generate only the remaining slots.
     3. **Regenerate everything**: generate every picture new for this topic.
   - Library: run `node scripts/embed-library-images.mjs --list`; use `any-topic` pictures freely and `topic-specific` ones only when their topic matches the deck, never show one picture on two pages, and set the plan's `images` value (or an image node `src`) to `library:<id>`. After composing, run `node scripts/embed-library-images.mjs project.json` to inline them; if a download fails, treat those slots as unfilled.
   - Generate pictures following `references/image-prompts.md`, at the `aspect` that `style-kit.json` and the compose report list for each slot. Use FAL with the user's `FAL_KEY` through `node scripts/fal-image.mjs` (submit once, then status/fetch; each submission is a paid task that is never retried automatically). In ChatGPT or Codex, the built-in image generation (GPT Image) may be used instead and needs no key. Never use another image provider. Library pictures (`--download <id> --out <dir>`) or pictures already made for this deck can be passed as `--reference` to keep the series consistent.
   - With neither FAL nor a built-in tool, options 2 and 3 fall back to option 1.
6. Set `uiLocale` and `conversationLocale` to the user's communication language and `contentLocale`/`contentDirection` from the brief; compose detects Chinese, Japanese and Korean plans. Arabic and Hebrew right-to-left layout is handled by the framework; do not reverse logical arrays.
7. Build and check: `python3 scripts/build-deck.py --project project.json --config editor-config.json --output presentation.html`, then `python3 scripts/check-deck.py presentation.html --expected-slides N --style-kit references/style-kit.json --report deck-check.json`. Resolve every example string the check still reports. If it warns about size, run `python3 scripts/optimize-images.py presentation.html` and check again.
8. Open the file over local HTTP and inspect every page: typography, pictures, hierarchy, crops, bounds, contrast and spacing. Edit text, add/delete/move a block, change a color or Smart layout, edit notes, undo/redo, save and reopen. Presentation mode must disable editing and its glass navigation must hide after five idle seconds.
9. Deliver the single HTML file. It opens in a page view with an Edit button and works offline. Tell the user that edits stay in the browser until they press Save (Cmd/Ctrl+S), which writes them into the file. On request, export PPTX from the built-in menu, run `python3 scripts/check-pptx.py presentation.pptx --project project.json --report pptx-check.json` and inspect it in PowerPoint, Keynote or WPS. Keynote uses the compatible `.pptx`. Print/PDF gives one page per slide.

## Style references

Read the [style kit](references/style-kit.json), [compose guide](references/compose.md), [palettes](references/themes.md), [layout recipes](references/layouts.md), [image prompts](references/image-prompts.md), [icons](references/icon-library.md), [style reference](references/style-reference.md) and [runtime](references/runtime.md).

## Restraint rules

- Word budget: headline ≤ 7 words (cover ≤ 5), one supporting line ≤ 18 words, at most 3 items per page (label ≤ 3 words + one line ≤ 10 words), ≤ 45 words per page. Detail goes into speaker notes.
- No tag clutter: only the brand mark top-left. No section labels, date pills, eyebrows, footer captions or page numbers.
- Content runs from about 86px to 634px from the top of the 1280x720 page.
- At most 3 content blocks per page on the 12-column grid (77px margins, 26px gutters); never overlap two photos.
- One radius for every photo and card (square), sibling cards share one style, one accent element per page.

## Inputs and outputs

Inputs: topic, audience, the one action the deck should support, rough length, people and roles, facts, and any photos the user may use. Slide copy defaults to English. Never invent business evidence; mark illustrative numbers as illustrative.

Output: one self-contained presentation HTML (page view, editor, presentation mode, speaker notes, pictures inline), optionally an exported PPTX (editable text and notes) and a PDF via print.

## Constraints

- No real company logos, names, people, slogans, or screenshots; fictional examples only unless the user supplies their own material.
- Keep the deck offline: no network calls, analytics, cookies, or embeds. The finished deck makes no network requests; only the build step downloads library pictures. Keep it under 20 MB.
- Never repeat a photo on two different pages.
- Keep the common editable framework unchanged.
- Lucide icons are ISC licensed; see `references/third-party-notices.md`.

## Style-specific planning and composition

- Clarify audience and purpose. If details are missing, draft an outline and state the assumptions.

- Theme: apply a preset from `references/themes.md` (default Violet Editorial). Do not add new dark pages beyond contents, team, and data pages.

- Layouts: pick archetypes from `references/layouts.md` (cover, contents, overview, featured lead, team roster, partner split, process cards, chart, habits, closing). Each archetype is a recipe in `references/style-kit.json`; follow the hard rules, grid, and type scale in `layouts.md` and keep the embedded fonts.

- Icons: inline Lucide SVG from `references/icon-library.md`. Never emoji, dingbats, or icon fonts.

- Pictures: follow Workflow step 5 for sources, the library question and tools, and `references/image-prompts.md` for the look, framing and prompt pattern. Never show one picture on two pages.

## Package boundary

Keep SKILL.md, scripts and references together. Include the shared runtime and required style resources. Examples, manifests, provider records, migration reports, previews and credentials do not belong in the installation ZIP. Use only references inside this Skill.

User reviews

0.0

0 reviews

Rate this Skill

Pick a rating to write your review

No reviews yet.

Ratings show up here once real people have tried it. We don’t display scores without the reviews behind them.

FAQ

Can I edit the result?

Yes. Change text, pictures, page order, colors, and notes in the browser studio. PowerPoint keeps text and notes editable; complex art and charts are images.

Do I need an image-generation account?

Decks can reuse this Skill's own picture library at no image cost: you choose up front whether to reuse it or generate every picture new. New pictures use your agent's built-in image generation tool (GPT Image class) with no separate API key, and availability follows your agent account.

Are the example numbers and people real?

No. The example uses a fictional context and newly generated original case imagery. Illustrative figures are labeled and should be replaced with your own evidence.