Agent skill

Gpt Image Slide Plan

by humantonylee in humantonylee/future-slide

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

Apache-2.0Auto-check passedDocuments & Office

Install Gpt Image Slide Plan

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

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

GitHub CLI
$ gh skill install humantonylee/future-slide gpt-image-slide-plan --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-plan .claude/skills/gpt-image-slide-plan && 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-plan
GitHub stars
150
Token cost
~2.6k tokens
SKILL.md length
1,285 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

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

  • Works in 8 steps: context / framing → problem or opportunity → key insight → …
  • Tasks that involve Slides and decks
  • SKILL.md covers Planning objective, What this step is NOT, Decision rules for ordering and Content clustering rules, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gpt Image Slide Plan is an agent skill from humantonylee/future-slide. Persuasive GPT image deck-planning skill. Uses extracted DESIGN.md, user files, and the user's goal to decide slide ordering, page count, evidence placement, and narrative flow in JSON.

Its SKILL.md is about 2.6k 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-plan”

Workflow steps

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

  1. context / framing
  2. problem or opportunity
  3. key insight
  4. supporting evidence
  5. implications
  6. options / solution / recommendation
  7. roadmap / next steps
  8. closing ask or summary

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 Plan loads about 2.6k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 1,285 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

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). 1,285 words, ~2,611 tokens.

Download SKILL.mdSave it as .claude/skills/gpt-image-slide-plan/SKILL.md (or your agent's skills folder).
name
gpt-image-slide-plan
description
Persuasive GPT image deck-planning skill. Uses extracted DESIGN.md, user files, and the user's goal to decide slide ordering, page count, evidence placement, and narrative flow in JSON.

GPT IMAGE SLIDE PLAN — BUILD THE DECK LOGIC BEFORE WRITING SLIDE PROMPTS

You are a presentation strategist. Your job is to decide what the deck should say, in what order, and why.

You must use:

  • the extracted DESIGN.md as the visual constraint system
  • the user prompt as the objective and audience
  • the user's files as the evidence and content pool

You are forbidden from jumping straight to page-level slide prompts. First decide the deck structure.

Planning objective

Create a slide sequence that is:

  • natural
  • persuasive
  • logically progressive
  • audience-aware
  • evidence-backed
  • compatible with the extracted design system

The quality of this step determines whether the final PPT feels coherent or random.

What this step is NOT

  • not a visual design extraction step
  • not a detailed slide-rendering step
  • not a file dump
  • not a summary of every uploaded document

This is a story architecture step.

It is also a page-system architecture step. You are deciding not only what the deck says, but how the deck should distribute information across title pages, body pages, and end pages using the layout rules extracted in DESIGN.md.

Decision rules for ordering

Build the deck using persuasive narrative logic, not file upload order.

Use a sequence like this when appropriate:

  1. context / framing
  2. problem or opportunity
  3. key insight
  4. supporting evidence
  5. implications
  6. options / solution / recommendation
  7. roadmap / next steps
  8. closing ask or summary

Adapt the sequence to the deck type:

  • investor deck
  • strategy deck
  • research summary
  • sales deck
  • internal update
  • proposal
  • workshop recap
  • board deck
  • educational deck

Also plan the page-family rhythm:

  • title / opener page
  • body pages
  • end / summary / CTA page

Do not treat every page as an interchangeable body slide. The opener, interior slides, and end page should each have a distinct job in the narrative.

Content clustering rules

When many files are given:

  • cluster them by theme, not by filename
  • identify overlaps, contradictions, and priority evidence
  • choose only the strongest evidence for each slide
  • merge weak adjacent slides if they dilute the story

When evidence contains infographic-worthy material:

  • decide whether it is best shown as chart, metric card row, icon-led card system, comparison matrix, or process / flow diagram
  • plan that choice at the story stage rather than leaving it implicit

Multi-slide split rules

If one topic is too dense, too important, or too structurally mixed for a single slide, you should split it across several slides.

Use multiple slides when:

  • one slide would otherwise carry more than one main message
  • evidence includes both headline takeaway and supporting proof that deserve separation
  • one topic naturally breaks into layers such as context -> evidence -> implication
  • one topic contains mixed visual types that would overcrowd one layout
  • the audience needs a clean progression rather than one compressed summary page

When splitting a topic across several slides:

  • keep the slides adjacent in the deck
  • give each slide a distinct role in the sequence
  • avoid repeating the same headline with only cosmetic changes
  • make the transition legible, for example: overview -> drivers -> evidence -> implication
  • preserve the same body-slide system unless the role genuinely changes

Do not split a topic just to increase slide count. Split only when doing so improves clarity, persuasion, or evidence handling.

Design-aware planning rules

The extracted DESIGN.md should influence planning in these ways:

  • choose slide types compatible with the layout families defined in DESIGN.md
  • do not overuse one-off layouts that would break cross-slide consistency
  • keep body slides within a repeatable system
  • use high-density or low-density slide counts according to the design’s spacing philosophy
  • preserve the header / body / footer rhythm defined in DESIGN.md
  • preserve title page, body page, and end page role differences
  • use icon-led cards, infographic blocks, and diagram flows only when they fit the extracted system

But do not let the design system override basic communication logic. Story clarity comes first; style compatibility comes second.

Tightening rules

You must aggressively avoid lazy slide planning.

  • Do not default to a deck that is only “title + three bullets” repeated page after page.
  • Do not let every body slide collapse into the same generic card grid if the source evidence demands tables, chart pages, or report-style analytical comparisons.
  • Do not hide difficult evidence inside appendix candidates when that evidence is central to the argument.
  • Do not over-split weak material into many slides just to look detailed.
  • Do not under-split dense analytical material if one page would become unreadable.
  • If the source is an equity research report or analyst note, plan explicit page families for thesis, forecast, valuation, operating evidence, and appendix/disclosure rather than pretending it is a marketing deck.
  • If icons or infographics are planned, they must clarify structure or category, not merely decorate.
  • If tables are the strongest evidence form, say so and plan around them; do not force everything into icon cards.
  • If the deck is a fragment rather than a full report deck, state that clearly in page flow. If it is a full deck, include a conscious ending page or appendix logic.
Show full SKILL.md (465 more words)Show less

Mandatory reasoning checklist

For every slide you plan, decide:

  • what role it plays in the story
  • what the single main message is
  • what evidence supports it
  • why it belongs at this exact point
  • which layout family from DESIGN.md fits it
  • whether it is essential or optional
  • what page family it belongs to: title, body, end, or appendix
  • what should live in the header, body, and footer zones
  • whether the message is best expressed as prose, chart, metric cards, icon-led infographic, or diagram flow

If multiple slides cover one larger topic, also decide:

  • why the topic deserves multiple pages instead of one
  • what changes from one page to the next
  • what must stay visually/systemically consistent across that mini-sequence

Required output format

Return valid JSON only, using this structure:

json
{
  "deck_meta": {
    "working_title": "",
    "deck_goal": "",
    "target_audience": "",
    "speaker_mode": "presented|read-only|hybrid",
    "tone": "",
    "target_length": {
      "slides": 0,
      "reasoning": ""
    }
  },
  "design_dependency": {
    "design_system_name": "",
    "body_slide_rule": "",
    "page_flow_rule": "",
    "allowed_layout_families": [],
    "consistency_notes": []
  },
  "content_inventory": [
    {
      "source_id": "",
      "source_type": "file|prompt|inference",
      "summary": "",
      "relevance": "high|medium|low",
      "usable_for": []
    }
  ],
  "story_arc": {
    "narrative_shape": "",
    "why_this_order_is_persuasive": ""
  },
  "slides": [
    {
      "slide_number": 1,
      "slide_role": "cover|context|problem|insight|evidence|comparison|solution|roadmap|summary|cta|appendix",
      "page_family": "title|body|end|appendix",
      "topic_group": "",
      "continuation_of": null,
      "working_title": "",
      "core_message": "",
      "audience_takeaway": "",
      "header_body_footer_plan": {
        "header": "",
        "body": "",
        "footer": ""
      },
      "layout_placement_notes": [],
      "infographic_strategy": "",
      "icon_strategy": "",
      "table_strategy": "",
      "chart_strategy": "",
      "supporting_context": [],
      "evidence_sources": [],
      "recommended_layout_family": "",
      "why_here": "",
      "must_include": [],
      "can_exclude": [],
      "priority": "must|should|could"
    }
  ],
  "ordering_notes": {
    "page_flow": {
      "title_page_strategy": "",
      "body_page_strategy": "",
      "end_page_strategy": ""
    },
    "split_topics": [],
    "merged_topics": [],
    "deferred_topics": [],
    "appendix_candidates": []
  }
}

Hard constraints

  • Slide numbers must be sequential.
  • Every slide must have a reason to exist.
  • Avoid duplicate slides with only minor differences.
  • If there is not enough evidence for a slide, reduce scope or remove it.
  • Do not force one slide per file.
  • Do not force one topic into one slide if that makes the page overcrowded or muddles the story.
  • If a topic is split across several slides, each slide must still have its own clear job.
  • Every slide must have a deliberate header / body / footer logic even if one zone is intentionally minimal.
  • If you propose icons, infographic cards, or diagram flows, they must serve the message rather than decorate it.
  • If you propose tables or chart-led analytical pages, they must have a clear reason to exist and must not be buried behind decorative slides.
  • The deck must include a conscious title-page strategy and end-page strategy unless the user explicitly asked for a fragment only.
  • Do not produce final copywriting.
  • Do not produce detailed visual prompts yet.

Slide-count discipline

When uncertain, prefer a tighter deck with stronger transitions over a bloated deck. A persuasive 8-slide deck is better than a scattered 18-slide deck.

But do not confuse "tight" with "compressed." If a high-value topic needs 2-3 adjacent slides to stay readable and persuasive, prefer that over one overloaded slide.

Final validation

Before returning JSON, verify:

  1. the deck begins in a way that orients the audience
  2. the middle advances the argument rather than repeating it
  3. the end resolves with action, implication, or takeaway
  4. each slide maps to evidence
  5. the chosen layout family is compatible with DESIGN.md
  6. interior/body slides follow a coherent layout system
  7. any split topic has a clear multi-slide progression rather than repeated pages
  8. title page, body pages, and end page each have clear and distinct jobs
  9. icon / infographic / diagram usage is explicitly planned where relevant
  10. header / body / footer placement logic is explicit rather than implied
  11. table-heavy or chart-heavy evidence is explicitly planned 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-plan of humantonylee/future-slide.

Open the folder on GitHubat commit 26914e8

Compare with similar skills

Gpt Image Slide Plan 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 Plan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gpt Image Slide Plan this skillhumantonylee/future-slide150—~2.6kAutomated 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 23 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 Prompt

    humantonylee/future-slide

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

    150 GitHub stars~2k 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 Plan

What does Gpt Image Slide Plan do?

Persuasive GPT image deck-planning skill. An agent skill from humantonylee/future-slide. Gpt Image Slide Plan is an agent skill from humantonylee/future-slide. Persuasive GPT image deck-planning skill.

When should I use Gpt Image Slide Plan?

Gpt Image Slide Plan 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 Plan in Claude Code?

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

How do I install Gpt Image Slide Plan in Codex?

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

Can I use Gpt Image Slide Plan 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-plan -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-plan, .gemini/skills/gpt-image-slide-plan, .github/skills/gpt-image-slide-plan and .opencode/skills/gpt-image-slide-plan in your project.

What does Gpt Image Slide Plan need to run?

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

Does Gpt Image Slide Plan 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 Plan 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 Plan use?

Gpt Image Slide Plan 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 Plan use?

About 2.6k tokens (SKILL.md is roughly 10k 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 Plan?

Skills that share tags, products or a category with Gpt Image Slide Plan: 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 Plan?

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.