agentleFS
feimacodefeimacode/open-design-agent-kit/.agents/skills/open-design-deck-from-source/SKILL.md

open-design-deck-from-source

Skill678 starsChanged yesterdayMITView on GitHub

Turn a document (a report, spec, spreadsheet, PDF, existing deck, or repository files such as a CHANGELOG) into a deck or one-pager, storyline first, with every number traced back to the source — use whenever the user wants slides, a deck, a presentation or a one-pager made from an existing document, spreadsheet, PDF or deck, or from repository files (CHANGELOG, RFCs, architecture decision records, metrics CSVs), even if they don't mention Open Design

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the user's own words. If they say "artifact", "design tokens" or give a file path, use those terms back.

    line 13
  2. Very specific:

    Keep the machinery out of replies: no tool names, no ids like od:prototype:poster-hero, no internal files (.artifact.json, .comments.json, …

    line 14
  3. Very specific:

    If you're unsure what a document contains, call read_open_design_source with its path.

    line 35
  4. Very specific:

    Call list_open_design_skills with mode: "deck" (or a query such as "pitch deck", "weekly report", "board") and choose the skill whose style …

    line 39
  5. Very specific:

    Call prepare_open_design_brief with the skillId, the user's request as brief, and the document paths as sources.

    line 43
  6. Very specific:

    Call register_open_design_artifact with the same sources.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- generated:open-design-agent-kit -->

Build a deck (or a one-pager) from existing documents with Open Design, storyline first, keeping every fact traceable to its source.

Request: the rest of the user's message (if there is none, ask the user: "Which document should the deck be built from, and for whom?")

How to talk to the user. Many people using Open Design don't write code, so:

  • Use the user's own words. If they say "artifact", "design tokens" or give a file path, use those terms back; otherwise use the plain words below.
  • Keep the machinery out of replies: no tool names, no ids like od:prototype:poster-hero, no internal files (.artifact.json, .comments.json, config.json), and not the words "register", "manifest", "sidecar", "entry" or "surface", unless the user used them first.
  • Explain a print term the first time it comes up, in one short clause, and not again.
  • Say where a file is the way the user would find it ("in your Open Design folder, under seed-swap-flyer"). Give a raw path only where the user can click it (Claude Code, Claude Desktop's Code tab, VS Code) or asks for it.
  • End each reply that finishes a step with one line on what they can do next, with at most two options ("Want it in Instagram sizes too, or is it ready to print?").
Instead ofSay
artifact, entry, registeredyour design, saved
design system, active design systemyour style (the first time: "a saved style: colours, fonts and spacing")
surface, skill, template, recipekind of design, starting layout, or nothing
workspace, output directoryyour folder, your Open Design folder
bleedprint edge ("a few millimetres extra that the printer trims off")
trim sizefinal size
preflight findings, errors"I checked it and fixed…", "one thing to look at:"
exportsave as PDF, save as an image
inline preview, MCP Appthe preview above

1. Find the sources

Identify the workspace files the request is based on. If it names none, ask which documents to use before doing anything else. Repository files count: CHANGELOG.md for a release deck, docs/adr/*.md for an architecture review, a metrics CSV or spreadsheet for a board update. Use up to 10 files; for a folder, pick the relevant files.

If you're unsure what a document contains, call read_open_design_source with its path. It returns an outline, and you can read the extracted Markdown by line range.

2. Pick the format

Call list_open_design_skills with mode: "deck" (or a query such as "pitch deck", "weekly report", "board") and choose the skill whose style fits the audience. For a single page instead of slides, choose a page or report skill.

3. Prepare the brief with sources

Call prepare_open_design_brief with the skillId, the user's request as brief, and the document paths as sources. Pass designSystemId only if the user names a brand or style.

4. Storyline first

Follow the returned instructions. Read the parts of the extracted text you need, then write the outline at outlinePath, with one entry per slide giving a takeaway headline, supporting points, a visual type and a source reference. Show the outline to the user and stop until they approve or change it, unless they already said to just build it.

5. Build and check

Build from the approved outline. Use numbers, names and quotes exactly as in the sources, never invent a statistic, and put the detail you cut from each slide into its speaker notes, ending with a Source: line.

Call register_open_design_artifact with the same sources. For every number its result says it couldn't find in the sources, check it: fix it, or say in that slide's notes how it was derived. Register again after fixing.

6. Hand it over

Tell the user where the deck and its outline are, mention any images reused from the documents, and offer to export it as PowerPoint or PDF with export_open_design_artifact. PowerPoint exports include the speaker notes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.