agentleFS
lynchypinlynchypin/project-onboard/skills/prototype/SKILL.md

prototype

Skill0 starsChanged 3 months agoMITView on GitHub

Build a throwaway artifact to answer "how should it look/behave?" Use when a wayfinder ticket needs a concrete artifact to react to before a decision can be made. Two modes — logic (terminal) or UI (browser).

194 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

  • +5 more from lilangMax
  • +3 more from CoralGame

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 7

    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:

    When "how should it look?" or "how should it behave?" is the key question and plain-English options aren't resolving the decision

    line 15
  2. Distinctive:

    Keep it under 100 lines — it's a conversation piece, not a draft

    line 29
  3. Distinctive:

    Use real (or realistic) data, not lorem ipsum — decisions change when content is real-shaped

    line 37
  4. Very specific:

    No framework, no build step — raw HTML/CSS/JS only

    line 40
  5. Distinctive:

    Delete the prototype code

    line 48
  6. Distinctive:

    Never let a prototype survive past the decision it was built to inform

    line 52
  7. Distinctive:

    Never build a prototype as a "head start" on implementation

    line 53
  8. Distinctive:

    Never spend more than 15 minutes on a prototype — if it's taking longer, the question needs more grilling first

    line 54

“Common” is measured: kept by at least 6 in 10 of the 179 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

Prototype

Raise the fidelity of a discussion by making a cheap, rough, concrete artifact to react to. Prototypes are throwaway — once the decision is captured on the wayfinder map, the prototype code is deleted.

When to use

  • A wayfinder ticket typed as prototype
  • When "how should it look?" or "how should it behave?" is the key question and plain-English options aren't resolving the decision
  • Especially valuable for anything touching UI or complex state machines

Two modes

Logic prototype

For state machines, algorithms, edge-case behavior.

  • Terminal app (Node/Python script, whatever's fastest)
  • Exercise the specific state transitions or edge cases under discussion
  • Output should make the behavior visible: print state transitions, show before/after, highlight the edge case
  • Keep it under 100 lines — it's a conversation piece, not a draft

UI prototype

For visual design, layout, interaction patterns.

  • Self-contained HTML file with inline styles
  • Multiple variants switchable via URL params (?variant=a, ?variant=b)
  • Use real (or realistic) data, not lorem ipsum — decisions change when content is real-shaped
  • Open in browser for the user to react to
  • No framework, no build step — raw HTML/CSS/JS only

Process

  1. Confirm which mode fits (ask if unclear)
  2. Build the minimal artifact
  3. Present it to the user
  4. Capture the decision on the wayfinder map
  5. Delete the prototype code

What this skill must never do

  • Never let a prototype survive past the decision it was built to inform
  • Never build a prototype as a "head start" on implementation
  • Never spend more than 15 minutes on a prototype — if it's taking longer, the question needs more grilling 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.