Agent skill

Gpt Image Slide Prompt

by humantonylee in humantonylee/future-slide

Page-level GPT image slide prompting skill. An agent skill from humantonylee/future-slide.

Apache-2.0Auto-check passedDocuments & Office

Install Gpt Image Slide Prompt

skills CLI
$ npx skills add humantonylee/future-slide --skill gpt-image-slide-prompt -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install humantonylee/future-slide gpt-image-slide-prompt --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/humantonylee/future-slide.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/gpt-image-slide-prompt .claude/skills/gpt-image-slide-prompt && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gpt-image-slide-prompt
GitHub stars
150
Token cost
~2k tokens
SKILL.md length
888 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Page-level GPT image slide prompting skill. An agent skill from humantonylee/future-slide.

  • Works in 4 steps: preserve factual correctness → preserve the approved narrative flow → preserve the extracted design system → …
  • Tasks that involve Slides and decks
  • SKILL.md covers Primary objective, Most important rule, Inputs and their roles and Prompt-writing method, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gpt Image Slide Prompt is an agent skill from humantonylee/future-slide. Page-level GPT image slide prompting skill. Converts DESIGN.md and slideplan.json into detailed slide-generation prompts in JSON while preserving theme, body-slide consistency, and layout discipline.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Documents & Office, covering Slides and decks, Image generation and Design tokens. The repository describes itself as: The workflow for disciplined slide generation. Extract design, plan the deck, render with consistency. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Slides and decks
  • Tasks that involve Image generation
  • Tasks that involve Design tokens

Example prompts

  • “/gpt-image-slide-prompt”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. preserve factual correctness
  2. preserve the approved narrative flow
  3. preserve the extracted design system
  4. only then optimize phrasing

What it can do on your machine

Read from SKILL.md and the folder at commit 26914e8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gpt Image Slide Prompt loads about 2k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 888 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from humantonylee/future-slide at commit 26914e8, republished under its Apache-2.0 licence (© humantonylee). 888 words, ~2,050 tokens.

Download SKILL.mdSave it as .claude/skills/gpt-image-slide-prompt/SKILL.md (or your agent's skills folder).
name
gpt-image-slide-prompt
description
Page-level GPT image slide prompting skill. Converts DESIGN.md and slide_plan.json into detailed slide-generation prompts in JSON while preserving theme, body-slide consistency, and layout discipline.

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 law
  • slide_plan.json = narrative law
  • user files = factual evidence and raw content
  • your inference = gap-filling only

If these conflict:

  1. preserve factual correctness
  2. preserve the approved narrative flow
  3. preserve the extracted design system
  4. only then optimize phrasing

Prompt-writing method

For each slide:

  1. read the planned role and core message
  2. select the correct layout family from DESIGN.md
  3. map the content into a clear slide hierarchy
  4. specify what belongs in the header, body, and footer zones
  5. specify what belongs in the title, body, chart, callout, caption, icon group, card system, diagram flow, or footer
  6. enforce the recurring body-slide rules
  7. include explicit exclusions so the generator avoids clutter

Tightening rules

You must write prompts that are difficult to misread as generic slide-template instructions.

  • Do not write vague instructions like “make it modern” or “use a clean layout” without specifying the actual structure.
  • Do not let generators improvise the core composition. Name the dominant content system explicitly.
  • Do not allow title blocks to become narrow 5-6 line walls unless that is specifically required by the reference.
  • Do not permit random badges, floating icons, or empty decorative shapes.
  • Do not let every slide become a four-card template unless the plan explicitly calls for it.
  • If a slide is table-led, say so directly and specify where the table sits and how dense it can be.
  • If a slide is chart-led, state the chart family, what is primary, what is secondary, and what annotations are allowed.
  • If a slide is icon-led or diagram-led, specify the semantic role of the icons and connectors so they do not become decorative filler.
  • If a slide belongs to a report-like deck, preserve report discipline: restrained headers, analytical body, low-noise footers, and evidence-first visuals.

Required output format

Return valid JSON only, using this structure:

json
{
  "deck_prompt_meta": {
    "design_system_name": "",
    "global_theme_summary": "",
    "global_consistency_rules": [],
    "body_slide_system": "",
    "json_version": "1.0"
  },
  "slides": [
    {
      "slide_number": 1,
      "slide_role": "",
      "page_family": "title|body|end|appendix",
      "slide_title": "",
      "layout_family": "",
      "prompt": {
        "objective": "",
        "narrative_function": "",
        "visual_intent": "",
        "content_blocks": [
          {
            "block_type": "title|subtitle|summary|bullets|chart|table|callout|quote|timeline|comparison|image|footer_note|source_note|icon_group|metric_cards|infographic|diagram_flow",
            "purpose": "",
            "content_instruction": "",
            "placement_instruction": "",
            "style_instruction": ""
          }
        ],
        "layout_instructions": {
          "structure": "",
          "header_body_footer": {
            "header": "",
            "body": "",
            "footer": ""
          },
          "reading_order": [],
          "alignment": "",
          "spacing": "",
          "density": "",
          "body_slide_consistency": ""
        },
        "design_constraints": {
          "palette_rules": [],
          "typography_rules": [],
          "component_rules": [],
          "chart_rules": [],
          "table_rules": [],
          "icon_rules": [],
          "infographic_rules": [],
          "diagram_rules": [],
          "imagery_rules": [],
          "anti_patterns_to_avoid": []
        },
        "content_constraints": {
          "must_include": [],
          "must_not_include": [],
          "evidence_to_use": [],
          "evidence_to_avoid": []
        },
        "generator_notes": {
          "ppt_generation_note": "",
          "image_generation_note": "",
          "fallback_if_content_is_sparse": ""
        }
      }
    }
  ]
}
Show full SKILL.md (378 more words)Show less

Slide prompt quality bar

Each page prompt must answer these questions clearly:

  • what this slide is trying to achieve
  • what the audience should notice first
  • how the content should be arranged
  • what should be emphasized visually
  • what must remain consistent with the rest of the deck
  • what should be excluded to prevent generic slide clutter
  • how header, body, and footer are organized
  • whether icons, infographic cards, or diagram flows are used and why

Body-slide discipline

For slides 2 through N-1, default to a limited family of reusable body-slide layouts defined in DESIGN.md, such as:

  • insight + evidence
  • 2-column argument + proof
  • single hero chart + annotation rail
  • comparison matrix
  • process / timeline

Only deviate if the slide role strongly demands it.

For title pages and end pages:

  • explicitly preserve their own family logic rather than treating them like generic body slides
  • define what belongs in header, body, and footer zones even if one zone is sparse by design

Anti-generic slide rules

In every page prompt, explicitly suppress:

  • random icon spam
  • decorative shapes not present in DESIGN.md
  • overcrowded bullet dumps
  • inconsistent chart styling
  • inconsistent icon style or icon size hierarchy
  • infographic cards that look unrelated to the deck system
  • diagram arrows/connectors that feel like default template artifacts
  • title hierarchy drift
  • template-like “one title + four equal boxes” unless planned
  • visual novelty that breaks body-slide consistency
  • fake analyst charts with made-up legends or decorative numbers
  • table dumps with no hierarchy or unusably tiny text

When source material is dense

Do not paste raw text into prompts. Instead:

  • compress content into claims
  • map evidence to the right visual block
  • choose one visual center of gravity per slide
  • decide whether the visual center should be chart-led, card-led, icon-led, or diagram-led
  • push overflow material into appendix candidates if needed

Final validation

Before returning JSON, verify:

  1. every slide prompt matches a slide in the plan
  2. numbering is sequential and complete
  3. body-slide consistency rules are repeated where needed
  4. the deck still reflects the extracted DESIGN.md
  5. page prompts are detailed enough to generate slides without guessing the whole layout
  6. title page, body pages, and end page each preserve their intended flow
  7. header / body / footer placement is explicit
  8. icon / infographic / diagram usage is explicit where relevant
  9. table / chart usage is explicit where relevant

© humantonylee, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/gpt-image-slide-prompt of humantonylee/future-slide.

Open the folder on GitHubat commit 26914e8

Compare with similar skills

Gpt Image Slide Prompt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gpt Image Slide Prompt compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gpt Image Slide Prompt this skillhumantonylee/future-slide150—~2kAutomated safety check: PassApache-2.0
Nano BananaEvoScientist/EvoSkills4782 repos~3.5kAutomated safety check: PassApache-2.0
Q-Presentations Slide Deck GeneratorTyrealQ/q-skills108—~1.1kAutomated safety check: PassMIT
Gpt Image 2 Paper Ppt Imagesdracohu2025-cloud/draco-skills-collection227—~3.9kAutomated safety check: PassMIT
SenseNova PPT Creative RendererOpenSenseNova/SenseNova-Skills5.7k—~1.2kAutomated safety check: PassMIT
Slide Deck Image GeneratorSpaceZephyr/design-buddy176—~6.5kAutomated safety check: PassNone

Similar skills

  • Nano Banana

    EvoScientist/EvoSkills

    Generate professional presentation slides and high-quality illustrations using Gemini image generation API (Nano Banana 2), with interactive browser-based review and iterative editing.

    478 GitHub starsUsed in 2 repos~3.5k tokens
    Documents & OfficeAuto-check passed
  • Generates branded slide deck images from written content, with a content analysis step, a layout catalog and scripts that merge the slides into PowerPoint or PDF.

    108 GitHub stars~1.1k tokensUpdated 17 days ago
    Documents & OfficeAuto-check passed
  • Gpt Image 2 Paper Ppt Images

    dracohu2025-cloud/draco-skills-collection

    A skill your agent uses when generating PPT-style image slides, poetic presentation covers, quiet paper-texture visual pages, report pages, invitations, social cards, or slide-image sets with…

    227 GitHub stars~3.9k tokensUpdated 24 days ago
    Documents & OfficeAuto-check passed
  • SenseNova PPT Creative Renderer

    OpenSenseNova/SenseNova-Skills

    Turns an approved slide outline into a full-page image for every slide, one 16:9 PNG per page, and optionally packages the set into a PPTX.

    5.7k GitHub stars~1.2k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed
  • Slide Deck Image Generator

    SpaceZephyr/design-buddy

    Turns written content into designed slide images from an outline, merges them into PPTX or PDF, and can borrow styles from a registry of brand design systems.

    176 GitHub stars~6.5k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check passed
  • Carousel Writer

    social-media-skills/skills

    A skill your agent uses to write a carousel — a swipeable multi-slide post (Instagram carousel, LinkedIn document/PDF carousel, or TikTok photo carousel) — one of the highest-save, highest-dwell…

    134 GitHub stars~1.6k tokensUpdated 9 days ago
    Documents & OfficeAuto-check passed

More from humantonylee/future-slide

All 10 skills in this repo
  • Tightened Slide

    humantonylee/future-slide

    Build single-file HTML horizontal-swipe presentation decks using the Tightened Slide process with locked layouts, strict grid rules, theme presets, image slot discipline, and validation.

    150 GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check passed
  • HTML Slide Render

    humantonylee/future-slide

    Final HTML slide stage. An agent skill from humantonylee/future-slide.

    150 GitHub stars~377 tokensUpdated 4 mo ago
    Auto-check passed
  • Gpt Image Slide Plan

    humantonylee/future-slide

    Persuasive GPT image deck-planning skill. An agent skill from humantonylee/future-slide.

    150 GitHub stars~2.6k tokensUpdated 4 mo ago
    Auto-check passed
  • Gpt Image Slide Render

    humantonylee/future-slide

    Render slide images sequentially from DESIGN.md and slide prompt JSON using Codex native image generation, saving each output into the workspace with page-number filenames.

    150 GitHub stars~966 tokensUpdated 4 mo ago
    Auto-check passed
  • Slide Design

    humantonylee/future-slide

    Shared slide-style extraction skill for GPT-image and HTML slide workflows.

    150 GitHub stars~2.6k tokensUpdated 4 mo ago
    Auto-check passed
  • Gpt Image Slide

    humantonylee/future-slide

    End-to-end GPT image slide workflow. An agent skill from humantonylee/future-slide.

    150 GitHub stars~397 tokensUpdated 4 mo ago
    Auto-check passed

Questions about Gpt Image Slide Prompt

What does Gpt Image Slide Prompt do?

Page-level GPT image slide prompting skill. An agent skill from humantonylee/future-slide. Gpt Image Slide Prompt is an agent skill from humantonylee/future-slide. Page-level GPT image slide prompting skill.

When should I use Gpt Image Slide Prompt?

Gpt Image Slide Prompt fits situations like: tasks that involve Slides and decks; tasks that involve Image generation; tasks that involve Design tokens.

How do I install Gpt Image Slide Prompt in Claude Code?

Run `npx skills add humantonylee/future-slide --skill gpt-image-slide-prompt -a claude-code`. Or copy the skill folder (skills/gpt-image-slide-prompt in humantonylee/future-slide) into .claude/skills/gpt-image-slide-prompt in your project. Claude Code loads it when a task matches its description.

How do I install Gpt Image Slide Prompt in Codex?

Run `npx skills add humantonylee/future-slide --skill gpt-image-slide-prompt -a codex`. Or copy the skill folder (skills/gpt-image-slide-prompt in humantonylee/future-slide) into .agents/skills/gpt-image-slide-prompt in your project. Codex loads it when a task matches its description.

Can I use Gpt Image Slide Prompt in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add humantonylee/future-slide --skill gpt-image-slide-prompt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gpt-image-slide-prompt, .gemini/skills/gpt-image-slide-prompt, .github/skills/gpt-image-slide-prompt and .opencode/skills/gpt-image-slide-prompt in your project.

What does Gpt Image Slide Prompt need to run?

SKILL.md names no scripts, command-line tools or credentials: Gpt Image Slide Prompt is instructions for the agent only.

Does Gpt Image Slide Prompt access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Gpt Image Slide Prompt safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gpt Image Slide Prompt use?

Gpt Image Slide Prompt is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gpt Image Slide Prompt use?

About 2k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gpt Image Slide Prompt?

Skills that share tags, products or a category with Gpt Image Slide Prompt: Nano Banana (EvoScientist/EvoSkills, 478 stars), Q-Presentations Slide Deck Generator (TyrealQ/q-skills, 108 stars), Gpt Image 2 Paper Ppt Images (dracohu2025-cloud/draco-skills-collection, 227 stars) and SenseNova PPT Creative Renderer (OpenSenseNova/SenseNova-Skills, 5.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gpt Image Slide Prompt?

humantonylee (a GitHub user) maintains it in humantonylee/future-slide, which has 150 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on June 2, 2026.

Source: humantonylee/future-slide on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.