prototype

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/prototype/SKILL.md

The canonical home for this skill is prototype in mattpocock/skills

Quality

Content

75%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.

The body is a lean, well-structured overview that routes to one-level-deep branch references and gives concrete runnable guidance for both branches. Its only real weakness is that the referenced detail files (LOGIC.md, UI.md) are not present in the bundle, so progressive disclosure and inline actionability cannot be fully verified.

Suggestions

Include LOGIC.md and UI.md in the skill bundle so the referenced branch detail actually exists and progressive disclosure can be verified as one-level-deep and complete.

Add a brief inline HTML skeleton or minimal runnable example for the logic-demo branch to lift actionability from mostly-executable to copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is tight and assumes Claude's competence throughout, with no padding about what a prototype is or how libraries work; each rule earns its place, though a few explanatory asides (e.g. spelling out 'so context is obvious', 'no thinking required to start it') could be trimmed, keeping it just below fully lean.	4 / 5
Actionability	Gives concrete, runnable guidance such as specific task-runner commands (`pnpm <name>`, `python <path>`, `bun <path>`) and a concrete artifact recipe (single shareable HTML with free-play buttons and tabbed walkthroughs); it is mostly executable, with minor gaps because the actual HTML/JS skeleton is deferred to referenced files rather than shown inline.	4 / 5
Workflow Clarity	The branch-selection step plus the six numbered shared rules form a clear, ordered sequence with an explicit disambiguation fallback ('default to whichever branch better matches the surrounding code... state the assumption'); it lacks an explicit validate-then-fix feedback loop, but this skill is non-destructive throwaway scaffolding so the destructive/batch cap does not apply, leaving a strong-but-not-perfect sequence.	4 / 5
Progressive Disclosure	The SKILL.md is a concise overview that splits the two branches into one-level-deep references ([LOGIC.md](LOGIC.md), [UI.md](UI.md)) with clear signaling; it stops at 4 rather than 5 because those referenced files are not present in the bundle to verify, so the split cannot be confirmed as cleanly one-level and complete.	4 / 5
	Total	16 / 20 Passed

Description

78%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.

The description is concise, third-person, and clearly answers both what the skill does and when to use it with concrete trigger phrases. It is strong on completeness and trigger quality; its main limitation is that specificity understates the two distinct artifact types the skill actually produces.

Suggestions

Mention the two concrete deliverables in the description (e.g. '...a single-file HTML logic demo, or multiple UI variants on one route') to lift specificity toward comprehensive coverage.

Add a couple of common synonyms users might say ('prototype', 'mock', 'spike', 'proof of concept') to the trigger clause to push trigger-term quality to comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain (throwaway prototype) and the concrete action ('Build a throwaway prototype to answer a design question') but does not enumerate the distinct concrete artifacts the skill produces (HTML logic demo vs. multi-variant UI), so it stops at naming the domain plus one or two concrete actions rather than comprehensive coverage.	3 / 5
Completeness	Explicitly answers both 'what' ('Build a throwaway prototype to answer a design question') and 'when' with a concrete 'Use when...' trigger clause covering the state-model and UI cases, matching the anchor for clearly answering both with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('sanity-check whether a state model or logic feels right', 'explore what a UI should look like', 'design question') with good keyword coverage; a few common synonyms (e.g. 'prototype', 'mock', 'spike', 'POC') are missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The 'throwaway prototype' framing plus the sanity-check/feels-right and UI-look triggers carve a fairly distinct niche with minimal conflict risk, though the broad term 'design question' could marginally overlap with general coding or design skills, keeping it just below a 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: ArcReel/ArcReel
Path: .agents/skills/prototype/SKILL.md
Commit: 5350d64

Reviewed: 5 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.