ワンクリックで
pptx
Use for creating, editing, reviewing, and validating presentation decks in PPTX format.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Use for creating, editing, reviewing, and validating presentation decks in PPTX format.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
How to send a notetaker bot into a video meeting (Google Meet / Zoom / Teams) and work with what it captures — join a call, confirm it got admitted, monitor its lifecycle, pull the speaker-attributed transcript, and produce a recap with decisions + action items, then remove it. Drives the `meet` CLI, which runs through the Kortix Executor (the meeting-bot provider key is resolved server-side; nothing in the sandbox). Load this WHENEVER the user asks to join / attend / record / transcribe / take notes on a meeting, "send a notetaker", "summarize that call", drops a Meet/Zoom/Teams link, or asks how to do anything with a meeting bot.
Kortix brand + design system: the rules, tokens, and component library for building any Kortix frontend UI (apps/web). Load this WHENEVER you create or edit a page, screen, component, list, card, badge, avatar, modal, form, empty state, toast, tooltip, or any visual surface in apps/web. Always load the companion skill make-interfaces-feel-better (apps/web/.agents/skills/make-interfaces-feel-better/SKILL.md) in the same session — brand/tokens here, polish/motion/haptics there. Source of truth: globals.css + the live /design-system page + src/components/ui + the reference implementations listed below.
How to roll Kortix PRODUCTION back to an older already-released version — the inverse of a release. Covers the one-dispatch rollback-prod.yml engine, the per-surface mechanics (API + gateway = Argo image-tag swap; frontend = Vercel promote), the all-important Vercel frontend behavior (why a backend-only push can 'clobber' a FE rollback, and the 'don't rebuild the FE for backend-only pushes' skip that fixes it), the DB/migration-drift safety check that is the real blocker, and how a later promote returns prod to latest. Load WHENEVER the user wants to roll back / revert / downgrade / 'go back a version' on prod, asks how the rollback or the frontend clobber/skip behavior works, or needs to run rollback-prod.yml. Pairs with kortix-release (the forward direction).
Create, manage, validate, preview, and export HTML presentation slides (1920x1080). Load this skill when you need to build a slide deck, export to PDF/PPTX, or preview slides in a browser.
Create, manage, validate, preview, and export HTML presentation slides (1920x1080). Load this skill when you need to build a slide deck, export to PDF/PPTX, or preview slides in a browser.
Canonical reference for a Kortix project: the platform model (repo-native projects, sessions on ephemeral branches, the strict boundary between `kortix.toml` and OpenCode config under `.kortix/opencode/`); the full `kortix.toml` manifest (keys, trigger fields, secrets contract, `[[apps]]` deploy surface); the complete `kortix` CLI (commands, flags, the project-scoped token model, the in-sandbox `KORTIX_TOKEN`); the change-request (CR) system for landing session work on `main` (an agent MUST open a CR to merge); the session sandbox runtime (which supports Docker and Docker-in-Docker); and the OpenCode runtime (agents, skills, commands, tools, plugins, MCP servers, permissions, AGENTS.md rules, models). Load whenever the user asks how Kortix works, about `kortix.toml`, the `kortix` CLI, anything under `.kortix/opencode/`, how to merge/ship/land work on `main`, change requests/CRs/PRs, or to author/edit any OpenCode primitive.
| name | pptx |
| description | Use for creating, editing, reviewing, and validating presentation decks in PPTX format. |
| Objective | Technique | Reference |
|---|---|---|
| Extract text or data | python -m markitdown presentation.pptx | Also: slides.py thumbnail for visual grid |
| Modify an existing file or template | Unpack to XML, edit, repack | See EDITING.md |
| Generate a deck from scratch | JavaScript with pptxgenjs | See CREATING.md |
Pre-installed sandbox packages: markitdown[pptx], Pillow, pptxgenjs (Node), react-icons + react + react-dom + sharp (icon rendering), LibreOffice (soffice), Poppler (pdftoppm).
Render equations with Unicode math symbols only. Do not use OMML or generate equation images — LibreOffice cannot display either during visual QA.
Design defaults: See skills/design-foundations/SKILL.md for palette, fonts + pairings, chart colors, and core principles (1 accent + neutrals, no decorative imagery, accessibility). Below is slides-specific guidance only.
Derive color from the content itself. Don't pick from a preset list — let the subject matter guide the accent:
Build every palette as 1 accent + neutral surface + neutral text. The accent is for emphasis only (headings, key data, section markers) — everything else stays neutral. See skills/design-foundations/SKILL.md for the full "Earn Every Color" philosophy, contrast rules, and the custom-palette workflow (user hue → derive surfaces by desaturating → test contrast).
When no topic-specific color is obvious, fall back to the Kortix neutral system: black/white or soft off-white neutrals with a single accent such as teal #22808D only where emphasis is needed (see skills/design-foundations/SKILL.md).
Use layout variety for visual interest — columns, grids, and whitespace keep slides engaging without decoration.
Layout options:
Data display:
See skills/design-foundations/SKILL.md for font pairings (Slides Pairings table) and size hierarchy. Default to professional sans-serif. Use serif for headings only when formal tone is needed.
margin: 0 on the text box or offset the shape to account for paddingborder-left: 3px solid <accent> is another AI-generated hallmark. Use background color, subtle neutral borders, or whitespace to separate content blocksbullet: true on large stat text — bullets at 60-72pt render as giant dots. Only use bullets on body-sized text (14-16pt)bullet: true on all text in a slide — bullet points should only be used for actual lists of 3+ items. Don't bullet a title, subtitle, description, or stat. Bullets on every text element makes slides look like a Word documentEvery slide that uses information gathered from web sources MUST have a source attribution line at the bottom of the slide using hyperlinked source names — each source name is displayed as clickable text linking to the full URL. Always use "Source:" (singular). Use an array of text objects with hyperlink options.
slide.addText([
{ text: "Source: " },
{ text: "Reuters", options: { hyperlink: { url: "https://reuters.com/article/123" } } },
{ text: ", " },
{ text: "WHO", options: { hyperlink: { url: "https://who.int/publications/m/item/update-42" } } },
{ text: ", " },
{ text: "World Bank", options: { hyperlink: { url: "https://worldbank.org/en/topic/water" } } }
], { x: 0.5, y: 5.2, w: 9, h: 0.3 });
hyperlink.url with the full https:// URL — never omit hyperlinks"Sources: WHO, Reuters, UNICEF" (plain text, no hyperlinks)"Source: WHO, https://who.int/report/123" (raw URL in text instead of hyperlink)[{ text: "WHO", options: { hyperlink: { url: "https://who.int/report/123" } } }] (clickable name)Every pptx task MUST complete ALL three QA steps below before delivering the file. Skipping any step is a failure.
Run markitdown on the output file and review the extracted text:
python -m markitdown output.pptx
Check for missing content, typos, wrong order.
When using templates, check for leftover placeholder text:
python -m markitdown output.pptx | grep -iE "xxxx|lorem|ipsum|this.*(page|slide).*layout"
If grep returns results, fix them before proceeding.
Use a fresh background session for visual inspection so the reviewer starts with fresh eyes.
soffice --headless --convert-to pdf output.pptx
pdftoppm -jpeg -r 150 output.pdf slide
ls slide-*.jpg # always ls — zero-padding varies by page count
session_start_background, or session_spawn if the alias is what the runtime exposes). Give it the slide image paths plus a prompt like this:Visually inspect these slides. Assume there are issues — find them.
Check for: stray dots/circles (orphan shapes, bullets at display size), overlapping elements, text overflow/cutoff, decorative lines mispositioned after title wrap, source footers colliding with content, elements too close (< 0.3" gaps), uneven spacing, insufficient slide-edge margins (< 0.5"), misaligned columns, low-contrast text or icons, narrow text boxes causing excessive wrapping, and leftover placeholder content.
For each slide, list every issue found, even minor ones.
session_read and treat the returned review as the visual QA checklist.Fix every issue the background review session found, then re-verify:
soffice + pdftoppm)At least one fix-and-verify cycle before delivering the file. Fixes create new problems — always re-check.
To re-render specific slides after fixes:
pdftoppm -jpeg -r 150 -f N -l N output.pdf slide-fixed
ls slide-fixed-*.jpg