agentleFS
ryanbaumannryanbaumann/fieldwork/.agents/skills/portfolio-presenting/SKILL.md

portfolio-presenting

Skill2 starsChanged 28 days agoMITView on GitHub

How Ryan presents. Use when drafting talk abstracts, outlines, speaker notes, or deck content, and when adding presentations to the site.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    The problem, in one real developer moment: Not market sizing — an actual moment of friction a builder in the room recognizes.

    line 12
  2. Distinctive:

    No bullet walls. If a slide needs paragraphs, it's a doc, not a slide.

    line 21
  3. Very specific:

    Create content/talks/<slug>.md (copy content/talks/_TEMPLATE.md) with type: deck and a link like {"label": "Slides", "url": …

    line 31
  4. Distinctive:

    Write the abstract in the body so the owned page explains the developer problem, demo, architecture, business meaning, and invitation path.

    line 32
  5. Very specific:

    Add a distinct 1200×627 raster social card through scripts/social-cards.mjs, then set socialImage, shareTitle, shareSummary, and …

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

How Ryan presents

The format: demo-first

Working product beats slides, every time. The arc of every talk:

  1. The problem, in one real developer moment. Not market sizing — an actual moment of friction a builder in the room recognizes.
  2. The demo. Live, real product, real API keys, real failure modes. The demo IS the argument.
  3. How it's built. Enough architecture that engineers trust it and can reproduce it.
  4. What it means for the business. Close the loop to growth: adoption, funnel, revenue. A demo without a so-what is a toy.

Slide rules

  • Slides support the demo; they don't replace it. If the wifi dies, the talk should still mostly work — but build the recorded-demo fallback anyway.
  • One idea per slide. One metric per slide, big.
  • No bullet walls. If a slide needs paragraphs, it's a doc, not a slide.
  • Screenshots of real product > diagrams > stock art (never stock art).

Q&A posture

Answer as the practitioner, not the spokesperson: "here's what I saw in the traces last week" beats "our documentation covers that." It's fine to say "we haven't solved that yet" — and better to follow with how you'd measure whether a solution works.

Adding a presentation to this site

  1. Drop the deck (PDF) into static/decks/ — anything in static/ ships verbatim with the built site.
  2. Create content/talks/<slug>.md (copy content/talks/_TEMPLATE.md) with type: deck and a link like {"label": "Slides", "url": "/decks/<file>.pdf"}.
  3. Write the abstract in the body so the owned page explains the developer problem, demo, architecture, business meaning, and invitation path. Use the writing skill for the talk title, abstract, share title, and social summary.
  4. Add a distinct 1200×627 raster social card through scripts/social-cards.mjs, then set socialImage, shareTitle, shareSummary, and shareImageAlt in front matter.
  5. node build.mjs and verify the talk page, /talks/, and emitted social metadata.

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.