happycapy-ai/happycapy-skills/signal-green
Claude Code and agent skill by happycapy-ai/happycapy-skills
- community
Checking that the SKILL.md file is still in the repository.
Reusable fixed-style PPTX generation skill for the Signal Green Atlas visual brand — fluorescent green (#0CDA76) dominant background, black (#000000) typography and rules, black-and-white imagery only, bold avant-garde editorial atlas aesthetic, oversized uppercase grotesk headlines, strict two-column information grids, sharp rectangular photo windows, black circular bullets, deliberate asymmetry, widescreen 16:9 editable .pptx output. Use this skill whenever the user mentions Signal Green Atlas, asks for a fluorescent-green editorial presentation, wants an avant-garde atlas or guidebook-style deck, requests a bold black-and-green presentation, or needs a deck using strict information grids and monochrome imagery. Also trigger for 'signal green', 'signal green atlas', 'fluorescent green deck', 'atlas pptx', 'black and green presentation', 'avant-garde atlas deck', 'guidebook style slides', or 'editorial atlas presentation'.
Install
npx vskill@latest install happycapy-ai/happycapy-skills/signal-greenSKILL.md
Signal Green Atlas PPTX Skill
A reusable fixed-style PowerPoint generation skill. It builds on the pptx skill's technical capabilities while locking in the Signal Green Atlas visual identity: bold, avant-garde, editorial — a fluorescent-green guidebook system with strict typographic grids, sharp rectangular image windows, black-and-white photography, and deliberate asymmetric composition.
Core principle — style fidelity over content volume. The atlas visual language originates in European editorial guides and experimental cartography, but it is a design system, not a fixed travel subject. Translate any topic into this visual language without forcing it to become a travel itinerary. The deck must feel bold, sharp, fluorescent, and editorial — never a soft brochure, text-heavy report, or generic corporate presentation.
Step 1: Gather Inputs (Ask First — Max 3 Questions)
Do not start generating immediately. Use the AskUserQuestion tool to present all questions in a single call. Only ask about what the user hasn't already provided.
Question 1 — Topic (skip if already provided):
- header: "Topic"
- question: "What is the presentation topic or title?"
- options: 2–3 relevant examples plus allow Other
Question 2 — Slide count (skip if already specified):
- header: "Slides"
- question: "How many slides should the deck include? (9 recommended)"
- options:
6 slides,9 slides (Recommended),12 slides,15 slides
Question 3 — Visual assets:
- header: "Images"
- question: "How should visual assets be provided?"
- options:
Use uploaded images— Insert images I provideGenerate with gpt-image-2— AI creates black-and-white editorial imageryCombine both— Mix uploaded and AI-generated assets
Infer the audience, narrative structure, sections, labels, and supporting metadata from the user's topic. Do not ask additional questions unless essential information is missing and the presentation cannot be completed without it.
Once you have the three answers, proceed directly to generation.
Step 2: Translate the Topic into Signal Green Atlas Language
Before writing any slide copy, decide how to translate the user's topic into the atlas frame. The visual system originated in route guides and cartographic atlases, but any subject can be reframed as a structured atlas — sections become stops, stages, coordinates, chapters, signals, milestones, sequences, or reference points.
| User provides | Signal Green Atlas treatment | |
|---|---|---|
| Product or brand | Atlas of the product ecosystem — sections, versions, features as stops | |
| Strategy or business topic | Strategic atlas — milestones, phases, decision coordinates | |
| Research or educational topic | Reference atlas — chapters, findings as entries, index overview | |
| Process or workflow | Sequential route — numbered stages, process stops, comparison grid | |
| Event or conference | Event atlas — session index, schedule grid, speaker entries | |
| Any other subject | Reframe as a bold structured guide — sections, reference points, or field entries |
Preserve the user's topic, terminology, facts, and intended meaning. Do not invent locations, routes, dates, statistics, people, companies, products, claims, or research results.
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
- 9-slide deck → 4–5 images
- 12–15 slide deck → 5–6 images
- 6 slides → 3–4 images
Cover image rule
The cover must include one large topic-relevant black-and-white hero image. Generate or use an uploaded image for this first.
Signal Green Atlas image prompt formula
Generated images are black-and-white editorial assets — not slide screenshots and never images with embedded text.
For non-architectural topics, adapt the scene:
Save each image to /tmp/signal-green-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
If Arial Black is unavailable, substitute Impact or Franklin Gothic Heavy.
Layout — LAYOUT_16x9 always (10" × 5.625")
Background is GREEN on every slide by default. Black fields may appear as panel blocks or full-cover sections. Images are always black-and-white and placed in sharp rectangular windows — no rounded corners, no soft frames.
Typography sizing
| Role | Font | Size | Color | |
|---|---|---|---|---|
| Cover title | SANS uppercase | 72–110pt | BLACK | |
| Slide headline | SANS uppercase | 40–64pt | BLACK | |
| Section identifier / index label | SANS uppercase | 32–48pt | BLACK | |
| Body / supporting statement | META | 22–30pt | BLACK | |
| Grid entries / labels | META | 16–20pt | BLACK | |
| Metadata / captions | META | 12–16pt | BLACK |
On black background panels or dark image areas, use WHITE for text.
Signal Green Atlas Visual System Rules
Rule 1: Style over content volume
The atlas system takes priority over including every detail. Compress, summarise, and choose the one most important idea for each slide. Generous empty green space is a design choice — not wasted space. A mostly-green slide with one oversized headline is correct Signal Green Atlas style.
Rule 2: One idea per slide. Under 35 words.
Count visible words before finalizing each slide. Most slides must be under 35 words total. Grid content and tiny metadata may be excluded only when it remains compact and legible. No paragraphs, no dense bullets, no long itinerary-style copy.
Wrong: "This section provides a comprehensive overview of the four key stages of the product development lifecycle, including discovery, definition, delivery, and deployment phases as practiced by our team."
Right:
Rule 3: Varied layouts within the same system
The Signal Green Atlas uses multiple layout types. Plan the slide mix before writing code — do not default to a single repeating composition. The variety is what makes it feel like a real atlas system.
Layout vocabulary:
- Cover: Large black-and-white hero image (full right half or full bleed) + oversized SANS uppercase title left
- Atlas overview / index: Numbered list of sections, two-column grid, clean atlas-style index
- Two-column info grid: Left column label/index, right column content; thin black rules between rows
- Full-slide image plate: Black-and-white image near full bleed, minimal uppercase text overlay
- Section identifier: Large oversized section number or name, compact metadata block below
- Image + metadata: Left sharp rectangular image panel, right compact metadata cluster
- Comparison / sequence grid: Two-column structure comparing stages, options, or entries
- Closing poster: Green field, large centered uppercase statement, compact credit metadata
Rule 4: Sharp geometry only
The Signal Green Atlas style is defined by sharp rectangular image windows, precise grid lines, and exact alignment. No rounded corners on image panels, no decorative cards, no soft shadows, no pill-shaped labels, no ornamental illustration. Corners are sharp. Geometry is precise.
Rule 5: Safe layout zones — no collisions
Before placing elements, define these non-overlapping zones:
Conflict resolution order: reduce copy → remove secondary info → shorten grid entries → reduce rows → increase spacing → remove rule → simplify layout → move to another slide.
Rule 6: Two-column grid discipline
Use two-column grids for index, comparison, and sequence slides. Grid rules:
- Left column: labels, index numbers, section names (META bold, left-aligned)
- Right column: content entries (META, left-aligned)
- Column break at approx. x: 3.0"–3.5"
- Row height: ~0.4"–0.5"
- Thin BLACK rules (LINE, h:0, 0.75–1pt) between row groups — never crossing text
- Internal padding: 0.1"–0.15" above each text row
- Maximum 6–8 rows before splitting to another slide
Layout Patterns
Cover (hero image + oversized title)
Atlas overview / index slide
Two-column info grid
Full-slide monochrome image plate
Section identifier
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/signal-green/SKILL.md
Popularity
- Repository stars
- 137
- Repository forks
- 30
- 7-day trend score
- 25
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/happycapy-ai/happycapy-skills/signal-green)