prototype

Build a throwaway prototype to answer a focused logic, state-model, or UI question before committing to production design. Use when the user asks to prototype, sanity-check a model, mock up UI, explore design options, or try a few designs.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, directive skill body with concrete rules and a clear two-branch workflow, but it relies on LOGIC.md and UI.md for the executable branch detail and neither file exists in the bundle, which undercuts both actionability and the progressive-disclosure navigation.

Suggestions

Add the missing LOGIC.md and UI.md to ./references/ (or inline their essential executable content) so the body's branch links resolve and Claude gets the concrete build steps.

Add an explicit validation checkpoint such as "run the one command and confirm the prototype starts before iterating" to turn the implicit runnable rule into a real feedback loop.

Trim the justificatory tail clauses on the shared rules (e.g. "so context is obvious", "getting this wrong wastes the whole prototype") to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with no concept-padding, but several rules carry justification clauses ("so context is obvious", "getting this wrong wastes the whole prototype") that are slightly more than strictly needed to act, fitting the efficient-with-minor-trim anchor.	4 / 5
Actionability	Concrete guidance is present — "Use the repo's Bun script or a direct `bun <path>` command" and "a local file with a clear 'PROTOTYPE: wipe me' name" — but the executable branch detail is delegated to LOGIC.md/UI.md, which are missing from the bundle, leaving minor gaps.	4 / 5
Workflow Clarity	A clear sequence (Pick a branch -> apply shared rules -> When done capture/delete) with implicit checkpoints like "One command to run" and "Surface the state", but no explicit validation gate or feedback loop, capping it just below 5.	4 / 5
Progressive Disclosure	The body uses well-signaled one-level-deep references ("-> [LOGIC.md](LOGIC.md)" and "-> [UI.md](UI.md)"), but those files are absent from the bundle, so the actual referenced paths do not resolve and navigation is broken rather than merely a minor gap.	3 / 5
	Total	15 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that crisply states a single concrete purpose and backs it with a rich, natural set of trigger phrases covering both logic and UI prototyping. Minor specificity gap only in that the action set is one core behavior rather than several discrete operations.

Dimension	Reasoning	Score
Specificity	"Build a throwaway prototype to answer a focused logic, state-model, or UI question" names a concrete action and a clearly bounded domain, but it is essentially one action across question types rather than multiple distinct concrete operations, so it sits just below the comprehensive 5 anchor.	4 / 5
Completeness	It explicitly answers both what ("Build a throwaway prototype to answer a focused... question") and when ("Use when the user asks to prototype, sanity-check a model, mock up UI...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	The "Use when..." clause lists natural phrases users say — "asks to prototype, sanity-check a model, mock up UI, explore design options, or try a few designs" — giving comprehensive synonym coverage of how the request is phrased.	5 / 5
Distinctiveness Conflict Risk	The throwaway-prototyping niche with triggers like "sanity-check a model" and "mock up UI" is clearly distinct from production coding skills and carries minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/prototype/SKILL.md
Commit: 9e1f9d2

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.