agentleFS
jhonatan-oliveiradevjhonatan-oliveiradev/agent-skills/skills/building-project-showcases/SKILL.md

building-project-showcases

Skill1 starsChanged 3 months agoMITView on GitHub

Use when a finished app, open source project, or shipped feature needs a compelling public case study, portfolio presentation, repository showcase, or product demo that shows real work and proof.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a durable presentation that helps a stranger understand the project and inspect the work.

    line 8
  2. Distinctive:

    Ask a fresh reader to describe what the product does and the action they would take.

    line 17

≈ “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

Building Project Showcases

Create a durable presentation that helps a stranger understand the project and inspect the work. Use the audience, verified claims, and links from preparing-project-launch when available; otherwise inspect them before publishing.

Workflow

  1. Choose one primary reader and decision: try the product, install it, evaluate the engineering, or contribute. Confirm what exists now, its release state, and which visuals may be shared.
  2. Extract the problem, who experiences it, the actual product path, the most distinctive interaction, meaningful implementation decisions, and the result that can be demonstrated. Separate observed outcomes from goals and future plans.
  3. Build a narrative around real evidence: concise opening, a clear demo (entry → action → result), two or three specific decisions and trade-offs, proof close to each claim, and one clear next action. Show usable interface captures or product footage rather than abstract feature cards.
  4. Adapt that story to its surface: a portfolio case study can explain process and decisions; a README should get contributors to the install or demo quickly; a product page should answer audience needs and objections. Reuse building-conversion-product-pages for full page architecture and writing-conversion-copy for persuasive offer copy when those are the actual deliverables.
  5. Prepare an asset and link checklist: accessible image descriptions, caption or transcript for video when needed, mobile-safe crops, working install/demo/repository URLs, credit for borrowed assets, and a valid social preview. Review in the rendered surface at small and large widths.
  6. Ask a fresh reader to describe what the product does and the action they would take. Revise any point where the visual story suggests a capability the released project does not have.

Output

Return the chosen format, page or README outline or implemented artifact, visual shot list, validated claims with sources, CTA and links, and any evidence still missing. Avoid presenting a concept mockup as a working product or fabricated testimonials as proof. Video production belongs to brag-slim; campaign timing belongs to planning-launch-distribution.

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.