agentleFS
vipink1203vipink1203/vk-skills/skills/showcase/SKILL.md

showcase

Skill0 starsChanged 13 days agoMITView on GitHub

Make a project's public showcase - a demo video cut from recordings of the real running app, with AI narration and labelled AI b-roll, plus a professional README with real screenshots, a name check and a clean public repo. Use when preparing a hackathon or launch submission, making a demo video of an app, or making a repo or README look professional.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. pandazki/pneuma-skills★ 161same name
    2. BenjaminG/ai-skills★ 4same name
    3. mikec-git/showcase-skill★ 2same name
    4. Thimorrow/claude-showcase-skill★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every frame and every claim comes from the real app and the project's proven evidence.

    line 9
  2. Distinctive:

    Read the primary pages (with a research skill, if you have one).

    line 15
  3. Distinctive:

    Name: Ask whether the project's name is a product name or only a category ("Accessible PDF Forms" is a category).

    line 17
  4. Distinctive:

    If it is a category, search for clashes and offer two or three names with the owner.

    line 18
  5. Very specific:

    Script: Write docs/demo-video.md: scenes in order, each tagged with the criterion it serves, narration one sentence per line, and a "Lines …

    line 20
  6. Distinctive:

    Repo: Before anything goes public, run the hygiene checks in REPO.md.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 3 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

Showcase

A showcase is everything a stranger sees of a project: the demo video, the README, the repo page. Every frame and every claim comes from the real app and the project's proven evidence; nothing is mocked up. Say only what the project has shown: when it keeps a list of what is proven and what is not, every claim comes from the proven part; when it keeps none, write that list first, with the test or script behind each line.

Steps

  1. Rules. Find the event's or launch's own rules: what to submit (repo, video host, length, fields), judging criteria with weights, deadline with time zone, rules on AI-generated content. Read the primary pages (with a research skill, if you have one); when a page needs a login, say so and name what could not be checked. Done when every criterion is mapped to the scene or README section that serves it.
  2. Name. Ask whether the project's name is a product name or only a category ("Accessible PDF Forms" is a category). If it is a category, search for clashes and offer two or three names with the owner; the owner picks. Done when the name is settled, before any frame or screenshot shows it.
  3. Script. Write docs/demo-video.md: scenes in order, each tagged with the criterion it serves, narration one sentence per line, and a "Lines never to say" list copied from the project's can't-claim list. Done when every narrated number is under Proven in the README.
  4. Video. Record the real app and cut the video by following VIDEO.md. Done when the frame check and the sound check in VIDEO.md both pass on the final file.
  5. README. Rewrite the README by following REPO.md, with screenshots taken from the recordings. Done when every link and image resolves and the page has no em dash.
  6. Repo. Before anything goes public, run the hygiene checks in REPO.md. Making a repo public, renaming it, and pushing are the owner's calls: ask, then do exactly that. Done when the public page shows the new README and its images load for someone signed out.
  7. Hand-off. Give the owner the upload steps for the video host, including its AI-content question, and the one link still missing from the README.

Spend

Paid generation (narration voice, b-roll, model calls during recording) is spent once: preflight its cost, cache every output, and never pay again for a re-render. A re-cut of the video re-uses the takes and the narration; only a change to the app itself needs a new take.

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.