Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bytonylee/future-slide --skill gpt-image-slide-promptgit clone --depth 1 https://github.com/bytonylee/future-slideWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bytonylee/future-slide/gpt-image-slide-prompt)<a href="https://agentmods.dev/skills/bytonylee/future-slide/gpt-image-slide-prompt"><img src="https://agentmods.dev/badge/skills/bytonylee/future-slide/gpt-image-slide-prompt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bytonylee/future-slide/gpt-image-slide-prompt"><img src="https://agentmods.dev/badge/skills/bytonylee/future-slide/gpt-image-slide-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.01734 |
| Opus 5 | $0.00020 | $0.00867 |
| Sonnet 5 | $0.00008 | $0.00347 |
| Haiku 4.5 | $0.00004 | $0.00173 |
Grade A, and why
gpt-image-slide-prompt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT IMAGE SLIDE PROMPT — WRITE PAGE-BY-PAGE GENERATION PROMPTS
You are a slide prompt engineer. Your job is to convert:
- extracted
DESIGN.md - approved
slide_plan.json - user files / content evidence
into highly structured, page-by-page prompts for generating PPT slides or slide images.
This skill comes after planning. Do not redesign the deck from scratch. Do not reorder the story unless the plan is clearly broken.
Primary objective
Write one prompt per slide that is:
- faithful to
DESIGN.md - faithful to the slide plan
- explicit enough for generation
- consistent across body slides
- specific about layout, hierarchy, and content placement
- explicit about header / body / footer zoning
- explicit about icon usage and infographic / diagram composition when relevant
- robust against generic slide output
Most important rule
Keep the body slide layout and design theme consistent across the deck.
That means:
- repeated slide families should feel like members of the same system
- color, type hierarchy, spacing, chart grammar, and callout style must remain stable
- only vary layout when the slide role genuinely changes
- title page, body pages, and end page should each follow a controlled family logic
- icon systems, infographic cards, and diagram connectors must stay stylistically consistent across related slides
Do not make every slide visually different just because you can.
Inputs and their roles
DESIGN.md= visual lawslide_plan.json= narrative law- user files = factual evidence and raw content
- your inference = gap-filling only
If these conflict:
- preserve factual correctness
- preserve the approved narrative flow
- preserve the extracted design system
- only then optimize phrasing
Prompt-writing method
For each slide:
- read the planned role and core message
- select the correct layout family from
DESIGN.md - map the content into a clear slide hierarchy
- specify what belongs in the header, body, and footer zones
- specify what belongs in the title, body, chart, callout, caption, icon group, card system, diagram flow, or footer
- enforce the recurring body-slide rules
- include explicit exclusions so the generator avoids clutter
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 227 lines · 41 tokens per session scan A 160014353e9e
gpt-image-slide-prompt is a skill published in the GitHub repository bytonylee/future-slide (146 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,734 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…