The 22 skills · Platform skill · Everything only

AGENT SKILL

deck-export: what it makes your agent do, and what it refuses.

deck-export makes the slide deck a fourth sibling of the build rather than a copy of the screen. Charts render from the page itself and headline figures go in as text from the same processed data, so the deck cannot drift from the report it came from, and the as of date is burned into every slide.

The job deck-export does

Analysts lose hours a week moving dashboards into slides, and an entire tool category exists to automate that copy loop for the big platforms. In this architecture the deck is another renderer of one build: page, CSV, workbook, PDF and now slides, all siblings of the same processed data. Chart images are captured from the page headlessly at presentation resolution, so the deck's chart is the page's chart. Headline figures arrive as editable, searchable text rather than pixels inside an image. Assembly runs against a branded template with real slide masters, so the build fills placeholders and never draws slides freehand, and the recurring Monday deck becomes a scheduled output.

What deck-export refuses

A skill is worth what it stops as much as what it produces. These are the refusals written into deck-export, taken from the rules and limits in its own file.

• ✓Re-plotting charts in slide land. A second charting path is a second place to lie.
• ✓A figure that exists only inside an image. Numbers go in as text, so they stay searchable and get recomputed every build.
• ✓A deck with no as of date. A forwarded deck outlives its data, so every slide carries the date it describes.
• ✓Drawing slides freehand. The build fills a branded template rather than inventing layout per run.

9 lines from the deck-export skill file, verbatim

From skills/deck-export/SKILL.md, unedited. Kymira skills are plain text you can read in full before you install them, which is the point of shipping a method rather than a binary.

- **Chart images render from the page itself** — the build screenshots
  each card headlessly at deck resolution (2× for projection). One
  renderer; the deck's chart is pixel-identical to the page's, because it
  *is* the page's. Never re-plot charts in slide-land: a second charting
  path is a second place to lie.
- **Headline figures go in as TEXT, derived from the same processed JSON**
  that built the page — editable, searchable, and recomputed every build.
  A figure that exists only inside a PNG is invisible to search and frozen
  in time.

The failure modes deck-export addresses

No entry in the catalogue of 51 observed failure modes names deck-export as the thing that addresses it. The catalogue records failures we have watched happen, so a skill appears there once a failure it covers has actually been observed and written up. Read the catalogue.

The tier deck-export ships in

Both paid tiers are a one-time purchase with lifetime updates, and all sales are final: the files are plain text you keep the moment they arrive, so judge the quality on the free skill and the published doctrine first. The pricing section states exactly what each tier contains.

Installing deck-export

A skill is a folder with a SKILL.md file in it. Installing one is copying that folder where your agent looks for skills, with no build step and no dependencies.

mkdir -p ~/.claude/skills
cp -R Kymira/skills/deck-export ~/.claude/skills/

Or open the unzipped pack in Claude Code and say install Kymira, which installs every skill in your tier, or double-click the installer for your system. Cursor reads the same skill as a rule file: copy deck-export.mdc into .cursor/rules/. Skills are read at startup, so start a new session and ask your agent which skills it has available.

Not for

Last updated 2026-08-14 · Dylan, founder · one of 22 packaged skills, each one a method written down, not a product tour.