agentleFS
SaikaAcoSaikaAco/saika-hermes-skills/skills/prototype/SKILL.md

prototype

Skill2 starsChanged 4 months agoMITView on GitHub

Use when the user explicitly asks for a prototype or when a named Wayfinder PROTOTYPE ticket needs runnable logic/UI decision evidence. Builds one throwaway artifact, obtains human reaction, and never promotes it to production automatically.

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

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

  • 0

    Common

    Most of the 179 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:

    Use ticket_handle: standalone in the handoff when no authoritative ticket exists.

    line 50
  2. Distinctive:

    Stop. Production specification, implementation, commit, publication, deployment, and cleanup require their own authority.

    line 67
  3. Distinctive:

    Do not drive a user-mediated IDE.

    line 75
  4. Distinctive:

    Do not install dependencies, mutate production data, merge prototype code, or delete evidence without separate approval.

    line 77

“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

Lineage and canonical protocol

This is an MIT-licensed Hermes entry point adapted from Matt Pocock's public prototype.

The complete upstream MIT notice is preserved in references/third-party-notices.md.

The canonical shared procedure and handoff schema live in Wayfinder's references/prototype-handler.md. Load that reference with skill_view and follow it exactly. Keeping the protocol there gives standalone prototypes and Wayfinder PROTOTYPE tickets one source of truth.

Invocation and input

Run only when:

  • the user explicitly asks to prototype one decision; or
  • one existing named Wayfinder PROTOTYPE / HITL ticket invokes it.

For a Wayfinder invocation, require its map and ticket handles and return the canonical wayfinder-prototype-v1 handoff.

For a standalone invocation, establish the equivalent bounded input before building:

  • destination;
  • exactly one decision question;
  • LOGIC or UI branch;
  • constraints and direct dependencies;
  • artifact authority and allowed location;
  • human decision owner.

Use ticket_handle: standalone in the handoff when no authoritative ticket exists. Do not create a Wayfinder package or tracker item merely to supply an ID.

Procedure

  1. Load wayfinder, then load references/prototype-handler.md through skill_view.
  2. Apply its authority, placement, branch, smoke-verification, human-reaction, evidence-lifecycle, persistence, and no-promotion gates.
  3. Build only the smallest runnable artifact needed to answer the named question.
  4. Execute the documented command or URL path and verify the decision-bearing interaction or variants.
  5. Deliver the artifact to the human and collect actual reaction. A runnable artifact without reaction remains unresolved.
  6. Return the complete wayfinder-prototype-v1 handoff.
  7. Stop. Production specification, implementation, commit, publication, deployment, and cleanup require their own authority.

Boundaries

  • A prototype is decision evidence, not production implementation.
  • A burnable visual brief may explain alternatives but cannot replace an interactive prototype when behavior or interaction is the question.
  • Do not drive a user-mediated IDE; provide a scoped prompt and independently inspect/verify the resulting artifact when that policy applies.
  • Do not install dependencies, mutate production data, merge prototype code, or delete evidence without separate approval.

Verification

  • Invocation was explicit or attached to one named prototype ticket.
  • The canonical Wayfinder prototype handler was loaded.
  • One LOGIC or UI question, owner, authority, and location were explicit.
  • The artifact passed a real smoke check.
  • Human reaction and accepted/rejected alternatives were preserved.
  • Durable context and prototype evidence have resolvable handles.
  • The handoff conforms to wayfinder-prototype-v1.
  • No production promotion or unauthorized side effect occurred.

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.