New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Image to Editable PPTX

by Yuan1z0825 in Yuan1z0825/nature-skills

Rebuilds slide images, screenshots, scanned PDFs or image-only PPTX files as PowerPoint with editable objects, using a local CLI with per-page manifests and QA.

MITAuto-check passedDocuments & Office

Install Image to Editable PPTX

skills CLI
$ npx skills add Yuan1z0825/nature-skills --skill nature-image2ppt -a claude-code

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

GitHub CLI
$ gh skill install Yuan1z0825/nature-skills nature-image2ppt --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/Yuan1z0825/nature-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nature-image2ppt .claude/skills/nature-image2ppt && 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
nature-image2ppt
GitHub stars
47k
Token cost
~2.5k tokens
SKILL.md length
1,033 words
Files
95 (incl. scripts, references)
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Rebuilds slide images, screenshots, scanned PDFs or image-only PPTX files as PowerPoint with editable objects, using a local CLI with per-page manifests and QA.

  • Works in 5 steps: Preflight and OCR choice → Prepare one run → Advance and claim pages → …
  • Converting a screenshot of a slide into an editable PowerPoint slide
  • SKILL.md covers Read the local contracts…, Preserve the single source of…, Keep every write inside its… and Preserve pre-migration behavior, plus 2 more sections
  • Runs Python scripts from its folder; calls python; needs PADDLE_OCR_TOKEN

What it does

The skill treats its own directory as the whole runtime and runs deterministic steps only through `cli/image2ppt/cli.py`, with Python 3.10 or later and the requirements installed. A `doctor` command checks dependencies, and work stops if it fails until the one reported missing piece is installed. The agent is told not to discover or call any other skill, CLI, prompt, schema or state machine.

State has a single source of truth: `page_jobs.json` for page state, a `manifest.json` in each page folder for page content and `deck_manifest.json` for the final assembly. Lifecycle commands (`prepare` and the `run` subcommands next, dispatch, record, reset, hints and finalize) move pages through the job, and QA may report failures but never changes state. Each page's work stays inside that page's folder. References are read progressively: a workflow guide always, a decision tree and manifest schema before writing a manifest, others when a page needs them, and a QA contract before delivery. It is not for writing a new deck from research notes.

When your agent uses it

  • Converting a screenshot of a slide into an editable PowerPoint slide
  • Rebuilding a scanned PDF deck as editable slides
  • Reconstructing a diagram image as native shapes and arrows

Example prompts

  • “Turn the screenshots in ./slides/ into an editable PPTX with text, shapes and arrows.”
  • “Rebuild this scanned PDF as an editable deck and run the QA checks before you hand it over.”
  • “Reconstruct the architecture diagram in diagram.png as editable PowerPoint objects.”

Requirements

  • Python 3.10 or later with the skill's `requirements.txt` installed
  • Any dependency that the `doctor` command reports as missing

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Preflight and OCR choice
  2. Prepare one run
  3. Advance and claim pages
  4. Reconstruct and gate each page
  5. Finalize and revalidate the rebuilt deck

What it can do on your machine

Read from SKILL.md and the folder at commit e605b35. 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

    Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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 these keys or tokens, usually read from environment variables:

    • PADDLE_OCR_TOKEN

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

Context cost

Image to Editable PPTX loads about 2.5k tokens when it runs, and up to ~26k if it reads all its reference files. Until then it costs about 58 tokens; SKILL.md has 1,033 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~26k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from Yuan1z0825/nature-skills at commit e605b35, republished under its MIT licence (© Yuan1z0825). 1,033 words, ~2,509 tokens.

Download SKILL.mdSave it as .claude/skills/nature-image2ppt/SKILL.md (or your agent's skills folder). This skill also uses 94 other files; get the full folder from GitHub.
name
nature-image2ppt
description
Reconstruct slide images, screenshots, scanned PDFs, or image-only PPTX files as object-level editable PowerPoint. Use for 图片转可编辑PPT、截图还原PPT and diagram reconstruction; not authoring a new deck from research notes.

Nature Image2PPT

Use this directory as the complete runtime. Run deterministic actions only through:

bash
python <image2ppt-root>/cli/image2ppt/cli.py <command> ...

Use Python 3.10 or later with requirements.txt installed. When a dedicated environment exists, substitute <image2ppt-root>/.venv/bin/python on macOS/Linux or <image2ppt-root>/.venv/Scripts/python.exe on Windows for every python command below. Do not continue after a failed doctor; install only the reported missing dependency, then rerun it.

Do not discover or invoke another Skill, CLI, Prompt, Schema, module, or state machine.

Read the local contracts progressively

Always read references/workflow.md. Read references/runtime-dependencies.md only for setup or doctor failures, and read references/ocr-text-hints-contract.md only when choosing or troubleshooting OCR.

Before writing a page manifest, read references/page-decision-tree.md and references/manifest-schema.md. Add only the references needed by that page:

  • structured or compound page: references/region-decomposition.md and references/object-routing.md;
  • arrows: references/manifest-arrow-extension.md;
  • raster assets or image-backend work: references/assets-provenance-contract.md.

Before accepting or delivering output, read references/qa-contract.md.

Preserve the single source of truth

  • Treat page_jobs.json as the only page-state source.
  • Treat each pages/page_NNN/manifest.json as the only page-content source.
  • Treat deck_manifest.json as the final-assembly source.
  • Use only prepare, run next/dispatch/record/reset/hints/finalize, and the page commands in the local CLI for stateful lifecycle operations.
  • Keep semantic-region evidence in manifest.json.image2ppt_region_decomposition.
  • Never create a second job file, reconstruction plan, OCR normalizer, page controller, packager, or finalize path.
  • Let supplemental QA report failures; never let it mutate lifecycle state.

Keep every write inside its owner directory

  • Page build, validation, hints, and QA may read and write only inside that page directory. Manifest paths, recorded assets, formulas, reports, previews, and --out overrides must not use .., symlinks, or absolute paths to escape it. The sole external-input exception is an explicit image-tool result supplied to image import or as process-sheet --asset-sheet-source; it is copied into the page before becoming a build dependency.
  • Run-level manifests and final outputs must remain inside the prepared run directory. Finalization rebuilds into a same-directory temporary file and publishes it atomically only after a successful build.
  • Treat any boundary rejection as a hard failure; do not copy the rejected file back into scope and present it as runtime output.

Preserve pre-migration behavior

  • Treat self-containment as a path/import/entrypoint migration, not a redesign of reconstruction behavior.
  • Generate each worker Prompt from the complete local base layer plus the preserved Image2PPT profile layer. Do not condense, reinterpret, or replace either layer.
  • Prefer the previously validated visual strategy when several routes satisfy the contracts. Keep simple measured objects native and retain bounded complex assets wherever a native redraw would reduce fidelity.
  • Never re-author an accepted baseline page merely to prove runtime independence.

Run the workflow

Image backend selection

Use builtin-imagegen when the agent runtime exposes image_gen.imagegen; it is the preferred backend because the worker can inspect edit inputs and import the explicit local result. Use the CLI image contract only when the built-in tool is unavailable, errors, cannot read an input, or returns no valid local output. A missing optional argument such as model, mask, size, quality, or output path never authorizes fallback. Record the actual producer and permitted fallback reason in imagegen-jobs.json.

The CLI image contract is provider-neutral at the transport boundary. Select codex-oauth only for GPT Image model ids. Select openai-compatible-api for any provider-specific model whose endpoint implements the OpenAI Images-compatible /images/generations and/or /images/edits schema. Do not infer the image backend from the task's language model. Use an explicit backend when provenance matters; auto uses Codex OAuth only for compatible GPT Image ids and otherwise selects the configured API without sending Codex OAuth credentials to third parties.

1. Preflight and OCR choice
bash
python <image2ppt-root>/cli/image2ppt/cli.py doctor --json

Use Baidu AI Studio PADDLE_OCR_TOKEN when configured. If it is absent, tell the user once that the local builtin-ink fallback measures text geometry but does not recognize characters; offer the configuration path in references/ocr-text-hints-contract.md. Respect an offline-only choice.

Show full SKILL.md (423 more words)Show less
2. Prepare one run
bash
python <image2ppt-root>/cli/image2ppt/cli.py prepare <input...> \
  --out-root output/image2ppt --image-backend builtin-imagegen

To pin a configured third-party provider/model for auditable provenance, prepare with --image-backend openai-compatible-api. The run contract records the exact IMAGE2PPT_IMAGE_MODEL from the active project config or environment; it does not substitute a GPT Image default merely because no --model flag was passed.

Use --no-text-hints only when OCR processing is intentionally disabled. Regenerate hints without creating a new run when needed:

bash
python <image2ppt-root>/cli/image2ppt/cli.py run hints <run-dir>
3. Advance and claim pages
bash
python <image2ppt-root>/cli/image2ppt/cli.py run next <run-dir> --json
python <image2ppt-root>/scripts/build_page_worker_prompt.py \
  <run-dir> --page <page-id> --out <absolute-page-dir>/worker-prompt.md
python <image2ppt-root>/cli/image2ppt/cli.py run dispatch \
  <run-dir> --page <page-id> --agent-id <id> --prompt-file <absolute-prompt>

For exactly one page, claim it with --local and reconstruct it in the current agent. For multiple pages, dispatch independent page workers up to the capacity in page_jobs.json. Do not reset a live worker merely because it is slow.

4. Reconstruct and gate each page

Plan a structured page as 3–5 semantic regions and route each region independently. Use measured compound diagrams: measure every node, relation, and protected anchor. Keep measurable circles, cards, straight/dashed relations, and simple connectors native. Use bounded transparent assets only for complex local subparts.

Represent a thin arrow as one connector with its arrowhead on the same object. Represent a filled arrow as one Arrow AutoShape, with centered label text inside the same object. Never construct an ordinary arrow from a line plus triangle and never flatten a whole knowledge graph into one image.

Write new page manifests with schema_version: 2. Use structured visual_inventory items with explicit kind and representation values, and write a concrete quality_evidence observation for every required quality check. Formula rendering is a hard gate: a missing engine, converter, or failed compile must keep the page failed unless the user explicitly approves that exact formula exception and the manifest records both user_approved_exception: true and a concrete approval_note.

The worker Prompt performs the deterministic sequence. Its final gates are:

bash
python <image2ppt-root>/cli/image2ppt/cli.py page build <page-dir>
python <image2ppt-root>/scripts/run_image2ppt_qa.py <page-dir>
# The first run writes visual-review-evidence.template.json and remains pending.
# Inspect source.png against render/rendered.png, copy and complete the template
# as visual-review-evidence.json, repair if needed, then:
python <image2ppt-root>/scripts/run_image2ppt_qa.py <page-dir> \
  --visual-review-status reviewed \
  --visual-review-evidence <page-dir>/visual-review-evidence.json
python <image2ppt-root>/cli/image2ppt/cli.py page contact-sheet <page-dir>

The evidence file must cover the current source/render hashes and every required check with a specific observation. --visual-review-notes is optional context and cannot substitute for the evidence file.

Record only after standard validation and the Image2PPT region, arrow, and rendered gates pass:

bash
python <image2ppt-root>/cli/image2ppt/cli.py run record \
  <run-dir> --page <page-id> --agent-id <id>

Use the same run reset → dispatch → record lifecycle to repair rejected pages.

5. Finalize and revalidate the rebuilt deck

When run next reports finalize, run:

bash
python <image2ppt-root>/cli/image2ppt/cli.py run finalize <run-dir>
python <image2ppt-root>/scripts/run_final_image2ppt_qa.py <run-dir>
# The first run writes final/visual-review-evidence.template.json and remains pending.
# Inspect every rendered slide, complete final/visual-review-evidence.json, then:
python <image2ppt-root>/scripts/run_final_image2ppt_qa.py <run-dir> \
  --visual-review-status reviewed \
  --visual-review-evidence <run-dir>/final/visual-review-evidence.json

Finalize rebuilds from page manifests, preserves source speaker notes, validates the package, and writes the output recorded by deck_manifest.json. Final QA reapplies manifest arrows, verifies arrow atomicity and compound structure, renders every slide, checks speaker-note integrity, and writes final/image2ppt_qa.json.

Deliver

Return the final PPTX path, standard final validation, and final/image2ppt_qa.json. Report which complex visuals remain replaceable bitmap assets. Do not call the deck complete while any page/final gate is pending or failed.

© Yuan1z0825, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 94 other files (scripts, references) in skills/nature-image2ppt of Yuan1z0825/nature-skills.

  • SKILL.md
  • .gitignore
  • LICENSE
  • README.md
  • README_EN.md
  • agents/openai.yaml
  • cli/image2ppt/__init__.py
  • cli/image2ppt/cli.py
  • cli/image2ppt/runtime/__init__.py
  • cli/image2ppt/runtime/_input_normalization.py
  • cli/image2ppt/runtime/_page_artifacts.py
  • cli/image2ppt/runtime/build_pptx_from_manifest.py
  • cli/image2ppt/runtime/configure_image_backend.py
  • cli/image2ppt/runtime/deck_run_state.py
  • cli/image2ppt/runtime/deck_text_hints.py
  • cli/image2ppt/runtime/finalize_deck_run.py
  • cli/image2ppt/runtime/formula_renderer.py
  • … and 78 more

Open the folder on GitHubat commit e605b35

Compare with similar skills

Image to Editable PPTX 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.

Image to Editable PPTX compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Image to Editable PPTX this skillYuan1z0825/nature-skills47k—~2.5kAutomated safety check: PassMIT
PowerPoint PPTX ToolkitXiaomiMiMo/MiMo-Code14k—~6.8kAutomated safety check: NotesApache-2.0
PPT Masterhugohe3/ppt-master59k1 repos~2.5kAutomated safety check: PassMIT
Open Kimi Pptjinwyp/open-ppt-skill1612 repos~5.1kAutomated safety check: PassMIT
McKinsey-Style PPT Designlikaku/Mck-ppt-design-skill297—~2.1kAutomated safety check: PassApache-2.0
AI Image PowerPoint Generatorbytedance/deer-flow84k4 repos~7.1kAutomated safety check: PassMIT

Similar skills

  • PowerPoint PPTX Toolkit

    XiaomiMiMo/MiMo-Code

    Creates, edits and reads PowerPoint .pptx files with python-pptx or PptxGenJS, with scripts for XML edits, text dumps, PDF and image rendering, and thumbnails.

    14k GitHub stars~6.8k tokensUpdated 2 days ago
    Documents & OfficeAuto-check: notes

  • PPT Master

    hugohe3/ppt-master

    Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.

    59k GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed

  • Open Kimi Ppt

    jinwyp/open-ppt-skill

    Create, edit, replicate, read, and export presentations. An agent skill from jinwyp/open-ppt-skill.

    161 GitHub starsUsed in 2 repos~5.1k tokens
    Documents & OfficeAuto-check passed

  • McKinsey-Style PPT Design

    likaku/Mck-ppt-design-skill

    Builds consultant-style PowerPoint decks from scratch with the MckEngine python-pptx wrapper, through a five-stage flow with scripted quality gates.

    297 GitHub stars~2.1k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed

  • AI Image PowerPoint Generator

    bytedance/deer-flow

    Creates a PowerPoint deck by planning the slide structure, generating one AI image per slide in a chosen visual style, and assembling the images into a PPTX file.

    84k GitHub starsUsed in 4 repos~7.1k tokens
    Documents & OfficeAuto-check passed

  • PPTX Deck Editor

    EveryInc/hands-on-deck

    Reads, edits, creates, merges and visually verifies .pptx decks through one script, deck.py, which applies atomic JSON patches.

    219 GitHub stars~2.9k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed

More from Yuan1z0825/nature-skills

All 23 skills in this repo

  • Nature Paper Card

    Yuan1z0825/nature-skills

    Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.

    47k GitHub starsUsed in 2 repos~2.1k tokens
    Auto-check passed

  • Nature-Style Scientific Figures

    Yuan1z0825/nature-skills

    Creates, revises, audits and exports manuscript-ready scientific figures in Python or R, and routes AI-generated graphical abstracts to a separate workflow.

    47k GitHub stars~3.1k tokensUpdated today
    Auto-check passed

  • Paper to Chinese Patent Drafter

    Yuan1z0825/nature-skills

    Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.

    47k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed

  • Researchwrite Proposal Pipeline

    Yuan1z0825/nature-skills

    Composes, revises or audits research proposals and opening reports through an evidence-first state machine with argument maps, section contracts and dynamic expert reviewers.

    47k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed

  • Nature Literature Downloader

    Yuan1z0825/nature-skills

    Routes literature requests to lawful full-text sources: open access, publisher APIs, CNKI and institutional browser access, with a supporting-information gate.

    47k GitHub starsUsed in 2 repos~6k tokens
    Auto-check passed

  • Manuscript Statistics Audit

    Yuan1z0825/nature-skills

    Audits or rewrites the statistical reporting in a manuscript: experimental units, replication, tests, uncertainty and figure legends, without inventing missing details.

    47k GitHub starsUsed in 2 repos~2.1k tokens
    Auto-check passed

Works with

Categories

Questions about Image to Editable PPTX

What does Image to Editable PPTX do?

Rebuilds slide images, screenshots, scanned PDFs or image-only PPTX files as PowerPoint with editable objects, using a local CLI with per-page manifests and QA. 10 or later and the requirements installed. A `doctor` command checks dependencies, and work stops if it fails until the one reported missing piece is installed.

When should I use Image to Editable PPTX?

Image to Editable PPTX fits situations like: converting a screenshot of a slide into an editable PowerPoint slide; rebuilding a scanned PDF deck as editable slides; reconstructing a diagram image as native shapes and arrows.

How do I install Image to Editable PPTX in Claude Code?

Run `npx skills add Yuan1z0825/nature-skills --skill nature-image2ppt -a claude-code`. Or copy the skill folder (skills/nature-image2ppt in Yuan1z0825/nature-skills) into .claude/skills/nature-image2ppt in your project. Claude Code loads it when a task matches its description.

How do I install Image to Editable PPTX in Codex?

Run `npx skills add Yuan1z0825/nature-skills --skill nature-image2ppt -a codex`. Or copy the skill folder (skills/nature-image2ppt in Yuan1z0825/nature-skills) into .agents/skills/nature-image2ppt in your project. Codex loads it when a task matches its description.

Can I use Image to Editable PPTX 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 Yuan1z0825/nature-skills --skill nature-image2ppt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nature-image2ppt, .gemini/skills/nature-image2ppt, .github/skills/nature-image2ppt and .opencode/skills/nature-image2ppt in your project.

What does Image to Editable PPTX need to run?

Going by SKILL.md and its folder, Image to Editable PPTX needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named PADDLE_OCR_TOKEN. Our summary lists: Python 3.10 or later with the skill's `requirements.txt` installed; Any dependency that the `doctor` command reports as missing.

Does Image to Editable PPTX 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 Image to Editable PPTX 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Image to Editable PPTX use?

Image to Editable PPTX is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Image to Editable PPTX use?

About 2.5k 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. Its references folder adds about 24k tokens, read only when the agent opens those files.

What are the alternatives to Image to Editable PPTX?

Skills that share tags, products or a category with Image to Editable PPTX: PowerPoint PPTX Toolkit (XiaomiMiMo/MiMo-Code, 14k stars), PPT Master (hugohe3/ppt-master, 59k stars), Open Kimi Ppt (jinwyp/open-ppt-skill, 161 stars) and McKinsey-Style PPT Design (likaku/Mck-ppt-design-skill, 297 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Image to Editable PPTX?

Yuan1z0825 (a GitHub user) maintains it in Yuan1z0825/nature-skills, which has 47,222 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 11, 2026.

Source: Yuan1z0825/nature-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.