Slides
Make, read or edit a PowerPoint deck (.pptx) - a review, a pitch, a status deck, slides with tables and charts - with a TypeScript script run by bise office run. Use when the user asks for slides, a deck or a pptx, sends one, or leaves notes on a pptx artifact.
Get the complete skill folder, including its scripts and reference files.
When to use this skill
Use Slides when an AI agent needs a reusable SKILL.md workflow for this job: Make, read or edit a PowerPoint deck (.pptx) - a review, a pitch, a status deck, slides with tables and charts - with a TypeScript script run by bise office run. Use when the user asks for slides, a deck or a pptx, sends one, or leaves notes on a pptx artifact.
When not to use it
Skip Slides when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.
How to install
Where will you use it?
mkdir -p ~/.claude/skills/slides # Save SKILL.md to ~/.claude/skills/slides/SKILL.md
- Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/slides/SKILL.md. For a shared project, commit the folder at .claude/skills/slides/ instead.
- Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
- For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.
Full install guide for Claude, Cursor, and Codex →
Try a starter prompt
After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.
Use the Slides skill for this task: Use Slides when this documented workflow matches the task. Confirm any required inputs or files before making changes.
What supports this recommendation?
69/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.
- Documentation
- 77/100
- Practical detail
- 68/100
- Source evidence
- 57/100
- Source signals
- 70/100
Model compatibility evidence
- claudeuntested
No model-specific signal or recorded compatibility test was found.
- chatgptuntested
No model-specific signal or recorded compatibility test was found.
- geminiuntested
No model-specific signal or recorded compatibility test was found.
- copilotuntested
No model-specific signal or recorded compatibility test was found.
- llamauntested
No model-specific signal or recorded compatibility test was found.
- perplexityuntested
No model-specific signal or recorded compatibility test was found.
- mistraluntested
No model-specific signal or recorded compatibility test was found.
- grokuntested
No model-specific signal or recorded compatibility test was found.
Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.
What this skill does
# Slides (pptx)
You write a short TypeScript script against `@bise/office` and run it with `bise office run`. The script reads and writes the deck; you never unzip or hand-edit XML. Each write of a file that is an artifact is its next version, and the user sees it in the side panel.
## Quick start
```sh bise office inspect q3.pptx # the outline as JSON: slides, shapes with ids, boxes, text bise office check q3.pptx # the problems as JSON ([] when none) bise office run "$TMPDIR/deck.ts" ```
```ts // $TMPDIR/deck.ts: an ES module, top-level await, no other import import { slides, run } from "@bise/office";
const deck = await slides.create(); // 16:9, 960 x 540 pt const s = deck.addSlide({ layout: "title-body" }); s.placeholder("title")!.setText("Q3: revenue up 4%"); s.placeholder("body")!.setText(["North carried the quarter", "South flat", "West back to growth"]); console.log(JSON.stringify(deck.check())); console.log(await run.write("q3.pptx", await deck.save(), { artifact: true })); ```
`{ artifact: true }` on the first write of a new file, so it shows in the panel; later writes to the same path are its next versions without it.
The script runs in a closed box: `run.read` and `run.write` reach your worktree and `$TMPDIR` only (a file elsewhere: `cp` it into `$TMPDIR` first), files up to 50 MB, 5 minutes, no network, no timers, no `fs`, no `process`. `console.log` prints a line. Keep scripts in `$TMPDIR`, not in the repo. An image goes in with `run.read("chart.png")`.
## The loop
1. **Inspect.** `bise office inspect <file>`, or `deck.inspect()`. A slide is `s<n>` with `props.index`, `layout`, `w`, `h`; a shape is `s<n>/<id>` with `props.box` `[x, y, w, h]` in points, its text, its placeholder type, font size, fill. Read the deck's layouts (`deck.layouts()`), sizes and fonts before you add to it. 2. **Edit by id.** `deck.slide(n)`, `slide.shape("3")` or by name, `slide.placeholder("title")`, or `deck.at(anchor)`. On a shape: `setText`, `replace`, `style`, `move`, `fill`, `line`, `setCell`, `replaceImage`, `remove`. On a slide: `addText`, `addShape`, `addImage`, `addTable`, `addChart`, `duplicate`, `moveTo`, `remove`. 3. **Save.** `await run.write(path, await deck.save())`, to the same path: that path is the artifact. Print what `run.write` returns. 4. **Check.** `deck.check()` before the write, `bise office check` after. 5. **Fix** each `error` and `warning`: text that overflows its box, a shape off the slide, an empty placeholder, text under 10 pt, shapes whose text overlaps. Or say in your reply why one stays.
Done means: saved, checked, the problems fixed or named, and the deck reads well (`style.md`).
## Notes and selections from the user
He can point at a slide, a shape, or a box he drew on a slide. Two shapes reach you:
- a message `you sent N notes on "q3.pptx" (artifact <id> vN, ...)` with an `<artifact-notes artifact="<id>" version="N">[...]</artifact-notes>` block: a JSON list of `{id, anchor, text}`; - an `<artifact-selection artifact="<id>" version="N">` block inside his own message: the first line is an anchor's JSON, the lines after are what he saw selected.
Anchors here: `{"kind": "shape", "slide": 2, "shape": "12", "quote": "up 4%"}` (a shape, `quote` the words he selected in it) or `{"kind": "slide", "slide": 5, "rect": {"x": 10, "y": 40, "w": 30, "h": 20}}` (a slide, `rect` in % of it when he drew a box). Pass it as it is: `deck.at(anchor)` gives the shape or the slide; on a slide with a rect, `.under()` lists the shapes in that box. Do each note, save once to the artifact's path (`sb artifact list` shows it), then reply one or two lines per note: what you changed, or why not. The new version marks the notes done. `at()` throws `not_found` when the shape is gone: inspect, find it by its text (the quote), and say so.
## Errors
The SDK throws `OfficeError` with a `code` and words that say what to do: `not_found` (it lists what is there), `bad_arg` (it shows the shape it takes), `anchor_kind_mismatch`. A refused path names the folders you may use.
## Read next
- `api.md`: every call, its arguments, the outline's fields. - `recipes.md`: a deck from a brief, a chart slide, a table slide, edit his deck, answer notes, split a dense slide. - `style.md`: how a deck should look and read. - `check.md`: each problem code, what it means, how to fix it.
Intended uses
- Use Slides when this documented workflow matches the task.
Implementation notes
- Review the source instructions and adapt inputs before running the workflow.
Try it, then tell us how it went
A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.