agentleFS
brayandiazcbrayandiazc/project-starter-template-en-ai/.claude/skills/prototype/SKILL.md

prototype

Skill2 starsChanged 2 months agoMITView on GitHub

Generates the product's navigable static views (landing, auth, app, legal, errors and the ones in the screen map) using the design system in design/, with no backend logic. Use it when views need to be laid out (e.g. "build the prototype", "mock up the views", "create the static landing").

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use playtest-report, soak-test and 10 more.

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.
  • CoralGameSkill

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 12 projects that use this

  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

  • CoralGameSkill

    team-polish

    Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.

    Also in 14 projects that use this

  • boraoztuncSkill

    pick-ui-library

    Pick the library for a frontend task from a curated list — primitives, toasts, drawers, command menus, OTP, numbers, charts, virtualization, drag and drop, state, styling.

    Also in 45 projects that use this

  • +3 more from lilangMax
  • +4 more from CoralGame

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 3

    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. Very specific:

    Read design/README.md + design/tokens.css (system and tokens), the view map in docs/architecture/screens.md and the project's README.md.

    line 11
  2. Distinctive:

    If there is no screen map, build it with the person first.

    line 13
  3. Distinctive:

    Start from the standard catalog and check it against the map:

    line 18
  4. Distinctive:

    Do NOT add business logic, nor JS beyond navigation/trivial toggles, nor invent views outside the map without proposing them first.

    line 57

“Common” is measured: kept by at least 6 in 10 of the 178 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

Build clickable static views — they validate flow and design before any logic is written, and afterwards they get connected (not thrown away).

Step 1 — Context

Read design/README.md + design/tokens.css (system and tokens), the view map in docs/architecture/screens.md and the project's README.md. If there is no screen map, build it with the person first. When you finish, mark in that map the views that move to prototype state.

Step 2 — View inventory

Start from the standard catalog and check it against the map:

  • Public: landing/home, pricing (if there is payment), about, contact, 404 and 500.
  • Legal: terms, privacy, cookies. The template does not ship these texts — lay out the page structure and leave the content marked as pending.
  • Auth (if there are accounts): login, sign-up, password recovery.
  • App: the views of the critical journey (dashboard, the value action, settings/account).

Confirm with the person which ones go into the prototype (default: all of the critical journey + landing + legal).

Step 3 — Build

On the tokens, not on a library. There are no versioned example views on purpose: they age and end up contradicting the design system. You build with design/tokens.css and native HTML primitives (<dialog>, <details>, popover), which bring focus, keyboard and Escape already solved.

  • Format according to the stack: the templating or component system the project already uses. If it is not instantiated yet, plain HTML importing tokens.css.
  • If the target is mobile: the mockup serves as a content and hierarchy spec, but the layout, the navigation (tabs, not a sidebar) and the screen catalog are different — there are screens that only exist on mobile (onboarding, permissions, offline) and web views with no equivalent.
  • Semantic design-system tokens only; loading/empty/error states visible where they apply (with realistic sample data, not "lorem ipsum").
  • Images/illustrations from the approved sources in design/README.md — optimized and with alt.
  • Real navigation between views (working links) — the prototype is walked end to end.
  • Light and dark mode (prefers-color-scheme + data-theme="dark") and localized text (no hardcoded strings if the stack already has i18n).

Step 4 — Validate

Walk the prototype against the product's critical journey and list what grates (extra steps, missing information). Close with: views created, design decisions taken, and which view to connect first when implementation starts.

Do NOT add business logic, nor JS beyond navigation/trivial toggles, nor invent views outside the map without proposing them first.

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.