/acid-labels

name: acid-labels-pptx
description: "Reusable fixed-style PPTX generation skill for the Acid Labels visual brand — bold acid-green (#A9FF7A) operating-guide aesthetic on hard-edged modular panels, deep forest (#3F5E31) plates, black pill labels, white tag chips, oversized italic serif curly-brace title moments, condensed sans labels, data-native charts and dashboards, widescreen 16:9 editable .pptx output. Use this skill whenever the user mentions Acid Labels, asks for a presentation or deck in the Acid Labels style, wants a bold acid-green operating guide / playbook deck, a modular label-driven data deck, or mentions the acid-green + forest-green + black pill-label look for slides. Also trigger when the user says 'acid labels', 'acid green deck', 'operating guide deck', 'playbook slides', or 'label system presentation' in any context. Display name: Acid Labels PPTX."

Acid Labels PPTX Skill

A reusable fixed-style PowerPoint generation skill. It builds on the `pptx` skill's technical capabilities while locking in the **Acid Labels** visual identity: a bold, acid-green professional *operating guide* — modular, label-driven, data-native, and confident.

**Core principle — style wins over content volume.** When the user's topic contains more information than the format can hold, compress and reinterpret into charts, chips, tiles, and extra slides. The deck must feel like a bold acid-green operating guide for the user's topic — **not** a generic report, **not** a copied brand-guidelines deck, and **not** a text-heavy memo. Every slide is a modular panel in a confident operating system.

**This skill is topic-agnostic.** It generates Acid Labels decks for *any* user-provided topic. Never hardcode a sample topic (finance, equities, chips, AI infrastructure, or any other) into a deck. Any topic-specific wording in this file is an *example only* — replace it at runtime with the user's topic variables.

---

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

Do **not** start generating immediately. Use the `AskUserQuestion` tool to present the missing questions in a **single** call (up to 3 at once). Only ask what the user hasn't already provided in their prompt — if they already gave the topic, slide count, or image choice, skip that question. Do not ask any extra questions unless the deck literally cannot be built without them.

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

• header: "Topic"
• question: "What is the topic or title of the deck?"
• options: 2–3 relevant example topics plus allow Other

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

• header: "Slides"
• question: "How many slides should the deck include?"
• options: `8 slides`, `10 slides (Recommended)`, `12 slides`, `15 slides`

**Question 3 — Images**:

• header: "Images"
• question: "How should visuals be handled?"
• options:
• `No generated images` — Editable native panels and charts only (Recommended)
• `Generate with gpt-image-2` — Abstract acid-green textures + topic-supporting theme images
• `Use my uploaded / reference images` — Insert images I provide

If the user hasn't provided data, audience, dates, or other details, **infer neutral content or use clearly labeled placeholder figures** (see Content Rules). Do not keep asking. Once you have the three core answers, proceed directly to generation.

---

Step 2: Topic Translation — Everything Becomes an Operating Guide

Before writing any slide copy, translate the user's topic into an Acid Labels frame. No topic is too technical, soft, or unusual. Every subject becomes a confident operating guide, playbook, or decision system — while preserving the user's actual subject.

| User provides | Acid Labels treatment | |---|---| | Product / launch | Operating guide: how it works, the numbers, the decision | | Strategy / plan | Playbook: sections, scenarios, checklist | | Research / concept | Field system: taxonomy labels, data blocks, sources | | Team / process | Operating manual: roles, workflow, KPIs, risk grid | | Event / program | Program system: schedule grid, tracks, KPI tiles | | Any other subject | Reframe as a labeled, data-native operating guide |

Decide these **before** writing slides, and use them as the cover's curly-brace title moment `{TOPIC}` and the deck's spine:

• The **guide title** (the `{TOPIC}` moment).
• The **one-line operating thesis** (what this guide is for).
• The **taxonomy label stack** (2–4 stacked short labels, e.g. category / subject / edition).

---

Step 3: Generate Images (only if the user chose gpt-image-2)

If the user chose **No generated images** or **uploaded images**, skip this step. For uploads, place their images into forest-green image plates and leave editable placeholder rects where images are missing.

If the user chose **gpt-image-2**, 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"` and `aspectRatio` matching the plate (`"16:9"` for cover/dividers). Save each image to `/tmp/acid-img-N.png`.

Generate **two clearly separated asset types**. Both types must contain **no readable text, no logos, no numbers, no real company/brand marks, and no recognizable real people.**

**Decorative image set** — abstract acid-green guideline textures, used *only* as cover backplates, section-divider image plates, and non-informational background texture:

Abstract acid-green guideline texture, shadowy green gradients, diagonal glass-like shadows,
close-cropped abstract panels, acid-green (#A9FF7A) overlays over deep forest green, subtle grain,
high-contrast black and green geometric shapes. No text, no logos, no numbers, no company marks,
no people. 16:9 composition, flat design-system texture, non-illustrative.

**Theme image set** — topic-specific *supporting* images that visually back the user's subject without embedding any slide content:

Abstract supporting imag