agentleFS
sassarini-marcosassarini-marco/track-to-demo/skills/present/SKILL.md

present

Skill0 starsChanged 24 days agoMITView on GitHub

Prepare the demo presentation: agree the deck content with the team, build it as a Claude Slides deck on the team's design system, and after validation export the .pptx on the team's template. Use it for the pitch, slides, demo rehearsal or judges' questions.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use tdd.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never invent results, metrics or integrations.

    line 9
  2. Distinctive:

    Write the link in the brief's "Deck" line and commit.

    line 17
  3. Distinctive:

    Do not export before the team validates.

    line 19
  4. Distinctive:

    Update your rows in WORK.md, then commit.

    line 25
  5. Distinctive:

    Use real screenshots and recordings as support and backup.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “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

Present

Arguments: $ARGUMENTS Reply in the user's language. Read BRIEF.md and WORK.md. Respect the demo and Q&A lengths in the schedule. Never invent results, metrics or integrations. Keep mock, implemented and verified apart, and say which data is synthetic.

  1. Content before form. Propose the deck outline from WORK.md: problem and promise, live demo with the wow moment, why trust it, results and limits; one line of content per slide, timings and speakers. Ask the team what to change. Nobody answers: go on and mark it "to confirm".
  2. The deck. Create a Claude "Slides" Artifact titled "Deck · <project>" with the design system the brief names for the deck, which overrides any default. Use real screenshots of the running app; a screenshot you need and do not have, capture it from the real demo with the planned demo login, never a placeholder. Speaker notes go in each slide's notes. Write the link in the brief's "Deck" line and commit.
  3. Validation. The team comments on the deck; read the comments, apply the requested changes, ask for confirmation. Do not export before the team validates.
  4. The .pptx. If the brief names a slide template, work on a copy of it with the pptx skill, keeping its masters and layouts: same content and order as the validated deck, real screenshots, speaker notes. Save it next to the template in templates/, out of git unless the team allows it. Without a template, tell the team to download the validated deck as .pptx from the deck's download menu. A template but no pptx skill: say so, give the install command from kickoff and the deck link.
  5. PRESENTATION.md: script, speaker notes, rehearsals to do before the freeze, likely questions and answers, links. Update your rows in WORK.md, then commit. Use real screenshots and recordings as support and backup. No alternative theme, no automatic video.

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.