/olive-rose

name: olive-rose-pptx
description: "Reusable fixed-style PPTX generation skill for the Olive Rose Salon visual brand — dark olive-brown background (#372E19), pale pink typography (#FFE1FC), high-fashion art exhibition poster aesthetic, large serif title type, widescreen 16:9 editable .pptx output. Use this skill whenever the user mentions Olive Rose Salon, asks for a presentation or deck in the Olive Rose style, wants an exhibition poster deck, needs a high-fashion poster-led PowerPoint, or mentions the olive-brown/pale-pink color scheme for slides. Also trigger when the user says 'olive rose', 'salon deck', 'poster presentation', or 'fashion deck' in any context."

Olive Rose Salon PPTX Skill

A reusable fixed-style PowerPoint generation skill. It builds on the `pptx` skill's technical capabilities while locking in the Olive Rose Salon visual identity: high-fashion, poster-led, exhibition-grade.

**Core principle — style wins over content volume.** When the user's topic contains more information than the poster format can hold, compress and reinterpret. Do not expand the deck into dense explanations. The user's subject is preserved, but expressed through sparse, editorial, exhibition-like language. Every deck must feel like a sequence of art exhibition posters — not a report, not an explainer, not a generic slide deck. The topic is the subject of an exhibition. The slides are the posters.

---

Step 1: Gather Inputs (Ask First — Max 3 Questions)

Do **not** start generating immediately. Use the `AskUserQuestion` tool to present interactive questions. Ask all missing questions in a **single** `AskUserQuestion` call (up to 3 questions at once).

Only ask questions the user hasn't already answered in their prompt. If the topic is already clear from their message, skip question 1 and only ask what's still missing.

**Question 1 — Topic** (skip if already provided):

• header: "Topic"
• question: "What is the presentation topic, exhibition title, project title, or brand/product name?"
• options: provide 2–3 example options relevant to context, plus allow Other

**Question 2 — Slide count** (skip if already specified):

• header: "Slides"
• question: "How many slides should the deck include?"
• options: `6 slides`, `8 slides (Recommended)`, `10 slides`, `12 slides`

**Question 3 — Images**:

• header: "Images"
• question: "How should images be handled?"
• options:
• `Generate with AI` — I'll create botanical abstract illustrations using gpt-image-2
• `Use my uploaded images` — Insert images I provide
• `Combine both` — Mix uploaded and AI-generated images

If the user hasn't provided audience, date, venue, speakers, or other details, **infer or use neutral placeholder copy** — do not keep asking. Only follow up if the missing info makes it literally impossible to build the deck.

Once you have the three core answers, proceed directly to generation.

---

Step 2: Topic Translation — Everything Becomes an Exhibition

Before writing any slide copy, translate the user's topic into an Olive Rose Salon frame. No topic is too technical, strange, or non-botanical. Every subject can be reframed as an atmospheric poster sequence, cultural exhibition, brand mood story, or poetic concept deck — while preserving the user's actual subject.

| User provides | Olive Rose treatment | |---|---| | Fragrance brand | Exhibition of scent, memory, and form | | Tech product launch | A collection. An object. A ritual. | | The Backrooms | A mysterious cultural exhibition — liminal space as architecture | | Scientific concept | An atmospheric visual essay | | Corporate pitch | A manifesto sequence | | Historical topic | An archival mood installation | | Any other subject | Atmospheric poster sequence — reframe through the lens of feeling, not fact |

**Do not** create a generic educational report, business explainer, or text-heavy slide deck about the topic. Instead, decide: what is the *exhibition title*? What is the *one-line framing statement*? What is the *3–4 word subtitle*? Write these first. They become the cover slide's primary elements and anchor the visual language of the whole deck.

---

Step 3: Generate Images (if requested)

Read the `generate-image` skill at `/home/node/.claude/skills/generate-image/SKILL.md` for the exact API call pattern. Use `openai/gpt-image-2` with `response_format: "b64_json"`.

How many images to generate

• 8-slide deck → 3–4 images
• 10–12 slide deck → 4–5 images
• Fewer than 6 slides → 2–3 images

Image prompt formula — Olive Rose Salon

All generated images must read as atmospheric, non-literal, and Olive Rose in palette. Even for dark or strange topics, reinterpret through abstract blurred forms — never literal scenes, never people, never readable text.

Base formula:

Soft motion-blurred botanical forms, painterly abstract foliage, deep olive green, moss, muted amber, shadow green, very faint pale pink highlights. Long-exposure photography style, atmospheric blurred garden movement, painterly flowers dissolving into color. No text, no logos, no people. Dark olive-brown dominant tone, 16:9 landscape composition.

For darker topics (e.g., liminal space, industrial, dystopian), adapt the mood while keeping the Olive Rose palette:

Abstract blurred forms suggesting [mood word — shadows, corridors, silence, depth], deep olive and moss tones, motion blur, painterly dissolution. No readable text, no logos, no people. Dark olive-brown dominant. 16:9.

Save each image to `/tmp/olive-rose-img-N.png`.

---

Step 4: Build the PPTX

Read the `pptx` skill at `/home/node/.claude/skills/pptx/SKILL.md` and its `pptxgenjs.md` reference for the full API. Build using PptxGenJS.

Core style constants — do not deviate

const BG    = "372E19";        // all slide backgrounds
const PINK  = "FFE1FC";        // primary type — titles, headlines
const CREAM = "F5EFE0";        // secondary — body, taglines
const GOLD  = "C8A96A";        //