Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

codex-ppt — Claude Code skill: generate PPT decks from text

Builds PowerPoint decks from articles, reports, and notes. Each slide is a full 16:9 generated image.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add ningzimu/codex-ppt-skill --skill codex-ppt -a claude-code
Open on GitHub

What codex-ppt does

The skill turns source text into a visually unified .pptx file: reads the material, drafts a slide outline, picks a style, generates one sample slide for approval, then produces the rest. Each slide is created as a complete image via the built-in image generation tool or through an API with the gpt-image-2.5-flare model (if the built-in path is unavailable). Final assembly runs through assemble_ppt.py.

Inside is a step-by-step workflow with approval gates: outline, style, backend selection, sample slide, full-deck generation via subagents (one per slide), quality check, and speaker notes. Requires python3; the OPENAI_API_KEY is needed only for CLI fallback mode. This works well for quick visualization, but not when every text box or chart needs to stay editable: here a slide is a PNG image, not a set of objects.

What it helps with

  • build a presentation from a research paper or report
  • create a visually unified slide deck in one pass
  • generate all slides in parallel using subagents
  • check quality and write speaker notes

Example prompts for the agent

  • Make a 10-slide presentation from this article in a minimalist style
  • Build a PPT deck from `notes.md` using a dark corporate design

How to install codex-ppt

1Skills CLI (Vercel)

npx skills add ningzimu/codex-ppt-skill --skill codex-ppt -a claude-code

2Manually: put the files in place

~/.claude/skills/codex-ppt/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/codex-ppt/

Similar

audit-xls official anthropics Audits Excel sheets for formula errors, hardcoded values, and logic breaks. It checks financial model integrity before sharing work with clients or review committees. Claude Code CX Codex Cursor +1 2,200installs clean-data-xls official anthropics Automates cleanup of messy Excel and Google Sheets data: trims whitespace, unifies case, converts numbers stored as text, standardizes dates, removes duplicates, and flags mixed-type columns. Claude Code CX Codex Cursor +1 2,100installs 3-statement-model official anthropics Fills and links three-statement financial model templates in Excel using formulas across IS, BS, and Cash Flow. Claude Code CX Codex Cursor +1 2,100installs performance-review official anthropics Generates structured templates for self-assessments, manager reviews, and team calibration sessions. Claude Code CX Codex Cursor +1 3,300installs daily-briefing official anthropics Builds a morning rundown with today’s meetings, account context, closing-soon opportunities, stale flags, waiting customer emails, and top actions. Claude Code CX Codex Cursor +1 3,200installs deck-refresh official anthropics Swaps figures across an existing presentation without rebuilding slides. For quarterly refreshes, earnings updates, comp rolls and rebased market data. Claude Code CX Codex Cursor +1 1,700installs pptx official anthropics This skill helps create, read, and edit .pptx files and .potx templates. Use it when building a deck or extracting slide text. Claude Code Claude.ai 241,433installs pdf official anthropics This skill lets an agent read, create, and edit PDF files, including forms and scanned documents. Use it when PDF work is part of the task. Claude Code Claude.ai 216,041installs

Questions about codex-ppt

How to install codex-ppt in Claude Code?

Run npx skills add ningzimu/codex-ppt-skill --skill codex-ppt -a claude-code. The skill will deploy to ~/.claude/skills/codex-ppt/.

What does codex-ppt do?

It generates PowerPoint presentations from text: each slide is a full 16:9 image generated by a neural network. Useful for quick visualization, but not for editing individual blocks.

Can I edit the text on a slide later?

No, each slide is a PNG image, not a set of editable objects. If you need to edit text boxes and charts separately, this skill is not suitable.

Source text

SKILL.md · MIT
---
name: codex-ppt
description: Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or outlines.
metadata:
  openclaw:
    requires:
      bins:
        - python3
    primaryEnv: OPENAI_API_KEY
    envVars:
      - name: OPENAI_API_KEY
        required: false
        description: API key for CLI fallback.
      - name: OPENAI_BASE_URL
        required: false
        description: API base URL.
      - name: CODEX_PPT_IMAGE_MODEL
        required: false
        description: Image model, defaults to gpt-image-2.5-flare.
      - name: CODEX_PPT_HOME
        required: false
        description: Runtime home override.
    homepage: https://github.com/ningzimu/codex-ppt-skill
---

# Codex PPT

## Overview

This skill creates image-based PowerPoint decks from source material. Each slide is a complete 16:9 generated image. Final images are assembled into `.pptx` with `scripts/assemble_ppt.py`.

Use this when the user wants a visually unified presentation and accepts full-slide image pages. Do not use it when every textbox, chart, or shape must remain separately editable.

Prefer the built-in image generation/editing tool. Use `scripts/image_gen.py` only when the built-in backend is unavailable, lacks a required capability, or the user explicitly asks for API/CLI mode.

## Hard Constraints

- Read the relevant `Reference Map` files before each phase. This file is the orchestration contract; detailed rules live in `docs/` and worker prompts in `prompts/`.
- Respect approval gates. Do not create final `deck_spec.json`, `speech.md`, prompt jobs, slide images, or `.pptx` before the approvals in `docs/workflow-gates-and-progress.md`.
- After the user approves the sample slide and authorizes full-deck generation, every remaining slide image job must be dispatched to a slide subagent whenever subagents are available.
- The main agent owns orchestration, prompt jobs, state recording, QA, speaker notes, and assembly. Do not silently replace available slide subagents with sequential production.
- Every final `origin_image/slide_XX.png` must be generated by the selected image backend: built-in image generation/editing tool or `scripts/image_gen.py`.
- Local drawing, Pillow, SVG, HTML/CSS/canvas screenshots, python-pptx/PptxGenJS layouts, and manual overlays are failure modes, not fallbacks.
- The selected image backend must stay fixed after backend confirmation. Do not let subagents switch backend for convenience.
- After sample approval, record how the approved sample was generated and pass that exact method to every slide subagent.
- Slide dispatch and result state must be recorded with the bundled scripts. Chat messages alone do not make a slide dispatched or complete.
- If a required subagent, image backend, or required-image path is unavailable, stop and report a blocker with the slide id and evidence. Do not create a lower-quality replacement.

## Visible Progress

For non-trivial decks, keep a user-visible checklist with one active step. Canonical completion evidence is in `docs/workflow-gates-and-progress.md`.

Default visible steps:

1. Prepare source, outline, style, and backend decisions.
2. Generate and approve one sample slide.
3. Prepare slide jobs and slide state.
4. Dispatch slide subagents.
5. Record generated slide results.
6. QA, repair, notes, and PPT assembly.

Do not mark a step complete from chat alone; use real files or script-recorded state.

## Default Workflow

1. Understand the source content.
   - Identify topic, audience, goal, page count, style/brand constraints, and sections to include or exclude.
   - If no page count is specified, choose a practical count. Typical decks are 8-12 slides.

2. Plan the deck outline.
   - Before writing or updating `outline.md`, read `docs/workflow-gates-and-progress.md` and `docs/outline-style-and-sample.md`.
   - Draft slide roles and required source images. Ask for confirmation, then stop before style, backend, sample, or downstream artifacts until approved.

3. Confirm a unified visual style.
   - Before offering style options or using files from `references/`, read `docs/outline-style-and-sample.md`.
   - Offer 2-3 concrete style directions, recommend one, wait for confirmation, then keep one visual identity while varying layouts by page role.

4. Confirm the image backend.
   - Before generating any slide image, read `docs/backend-selection.md`.
   - Check whether a built-in image tool is callable, state what you checked, name the backend, explain fallback status, and wait for confirmation.
   - If CLI/API fallback is selected, read `docs/cli-api-fallback.md`. Read `docs/image-model-configuration.md` only after config errors or explicit API-setting requests.

5. Generate one sample slide for approval.
   - Before generating or approving the sample slide, read `docs/outline-style-and-sample.md`.
   - Generate exactly one representative sample after outline, style, and backend are confirmed. Do not generate the full deck until approved.
   - After approval, record `sample_generation_method` in `deck_spec.json` so jobs and subagents inherit the same path.

6. Create the project directory.
   - Before initializing folders or assembling files, read `docs/project-assembly-and-reporting.md`.
   - If no destination is specified, use the current working directory or the source file directory.

7. Prepare user-supplied assets.
   - Before using paper figures, charts, screenshots, logos, or other required assets, read `docs/user-supplied-assets.md`.
   - Treat required assets as strict inputs and confirm slide-to-asset mapping before generation.

8. Generate all slide images.
   - Before full-deck image generation, read `docs/slide-generation-and-subagents.md`.
   - Create per-slide jobs with `scripts/prepare_slide_prompts.py` or saved `prompts/slide_XX.json` files.
   - Every final image must come from the selected backend and be recorded with bundled state scripts.

9. Dispatch slide subagents.
   - Before dispatching or replacing slide workers, read `docs/slide-generation-and-subagents.md` and `prompts/slide-worker.md`.
   - Use one subagent per remaining slide job whenever possible. If required subagents cannot be spawned, stop and report a blocker unless the user changes the workflow.

10. Quality check and repair.
    - Before QA or assembly, read `docs/project-assembly-and-reporting.md`.
    - Inspect every slide before assembly: text, outline match, truncation, style, unwanted page numbers, overlaps, and required assets.
    - Regenerate severe failures with a tighter prompt. Use backend editing for localized issues when available.
    - For CLI/API fallback edit commands, read `docs/cli-api-fallback.md`. Replace the final slide only after validating the edited output.

11. Write speaker notes and assemble the PPT.
    - Before writing `speech.md` or running assembly, read `docs/project-assembly-and-reporting.md`.
    - Make sure `outline.md` reflects the final confirmed deck outline. Use `speech.md` headings that map to `Slide N`.
    - Before assembly, ensure `slide_jobs.json` shows generated slides as `recorded` and approved samples as `accepted`. If any slide is `pending`, `dispatched`, or `blocked`, stop.

12. Report the result.
    - Use the final report checklist in `docs/project-assembly-and-reporting.md`.
    - Include paths, slide count, backend used, recorded-result status, and any limitations or blockers.

13. Save reusable styles.
    - If asked to save the current deck style or a supplied image/PDF/PPT/PPTX style, read `docs/style-library.md`.
    - If the final deck used a custom or adapted style, proactively offer to save it in the final report, per `docs/project-assembly-and-reporting.md`. User custom styles are stored in `${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/`, outside the skill install.

## Subagent Dispatch

Slide subagents are mandatory after sample approval whenever the runtime can spawn them. The main agent prepares jobs and records state; each worker handles exactly one `prompts/slide_XX.json` job and returns only selected image path, backend, and QA note.

Use `docs/slide-generation-and-subagents.md` for dispatch, commands, result recording, blockers, and backend provenance. Use `prompts/slide-worker.md` as the handoff template.

Subagents must not edit `outline.md`, `deck_spec.json`, other slide jobs, `origin_image/`, `speech.md`, or the final `.pptx`. The parent records outputs and assembles.

## Acceptance Criteria

- Output is a valid `.pptx`.
- Each expected final slide image exists under `origin_image/slide_XX.png`.
- Every final slide image was generated by the confirmed backend and recorded through `record_slide_result.py`, except an approved sample marked accepted by run state.
- `outline.md` reflects the approved deck outline.
- `speech.md` exists when speaker notes are expected, and assembly writes those notes into the PPT.
- `slide_jobs.json` and `slide_run_state.json` reflect the final state.
- Required source images are visibly represented, or a blocker is reported.
- If blocked, the final response identifies phase, slide id, evidence path, and unfinished reason; do not call the deck complete.

## Reference Map

- `docs/workflow-gates-and-progress.md`: approval gates, progress, completion evidence.
- `docs/backend-selection.md`: backend decision rules and confirmation text.
- `docs/outline-style-and-sample.md`: outline, style, sample rules, prompt examples.
- `docs/user-supplied-assets.md`: strict handling for required source assets.
- `docs/slide-generation-and-subagents.md`: jobs, dispatch, result recording, blockers, provenance.
- `docs/cli-api-fallback.md`: fallback runtime, generation/edit commands, image limits, troubleshooting.
- `docs/image-model-configuration.md`: API key, base URL, model, `.env`; read only when config is needed.
- `docs/project-assembly-and-reporting.md`: project directory, notes, assembly, final report, prompting principles.
- `prompts/slide-worker.md`: slide subagent handoff template.
- `references/*.md`: built-in visual style references. User custom styles live in `${CODEX_PPT_HOME:-~/.codex-ppt-skill}/references/` and take priority over built-in styles with the same name.

## Documentation and Updates

For source, docs, install, config, and examples, see [ningzimu/codex-ppt-skill](https://github.com/ningzimu/codex-ppt-skill).

© ningzimu · MIT · ningzimu/codex-ppt-skill

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor