prototype

构建一次性原型来回答一个设计问题。适用于用户想验证某个 state model 或 logic 是否感觉对，或探索 UI 应该长什么样时。

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

78%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 concise, well-structured, and actionable, with a clear branching workflow and explicit capture guidance. The main defect is that the two referenced bundle files (LOGIC.md, UI.md) do not exist, breaking progressive disclosure and navigation.

Suggestions

Provide the missing LOGIC.md and UI.md bundle files referenced in the 'Pick a branch' section, or remove/replace the references with inline guidance.

Add an explicit validation/verification checkpoint to rule 6 (e.g., confirm the prototype answered the design question before capturing the decision into real code).

Include at least one small copy-paste-ready code or command snippet per branch (e.g., a minimal HTML scaffold for the logic branch) to lift actionability to fully executable.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding about what a prototype is or basic concepts Claude already knows; every line earns its place. Matches the 'lean and efficient, assumes Claude's competence' anchor.	5 / 5
Actionability	Provides concrete, specific guidance (e.g. 'pnpm <name>', 'python <path>', single shareable HTML file, URL search param + floating bottom bar) but no copy-paste-ready code, leaving minor executable gaps. Not a 5 because there are no complete runnable examples.	4 / 5
Workflow Clarity	Clear sequence (identify branch → build → capture decision) with most checkpoints present and explicit decision-capture steps. Not a 5 because rule 6's branch-commit/capture step lacks an explicit validation/verify checkpoint.	4 / 5
Progressive Disclosure	Structure is clean and references ([LOGIC.md](LOGIC.md), [UI.md](UI.md)) are clearly signaled one level deep, but both referenced bundle files are absent from the skill directory, so navigation is broken. Not a 4 because the missing files mean the references do not resolve.	3 / 5
	Total	16 / 20 Passed

Description

87%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 well-constructed description that clearly states what the skill does and when to use it, with concrete trigger scenarios and low conflict risk. The only minor weakness is slightly limited synonym/term coverage in the trigger phrases.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('构建一次性原型', two branch use-cases: validating a state model/logic and exploring UI) with only minor coverage gaps typical of a meta-skill. It is not a 5 because the actions are described at a moderately abstract level without enumerating multiple distinct concrete operations.	4 / 5
Completeness	Explicitly answers both 'what' (build throwaway prototypes to answer a design question) and 'when' ('适用于...时' with two concrete triggering scenarios), matching the anchor that requires explicit trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would actually say ('验证某个 state model 或 logic 是否感觉对', '探索 UI 应该长什么样'). Good coverage but lacks synonyms/file-extension variants, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (throwaway prototypes for design questions) with distinct triggers and minimal overlap risk with production-coding or other skills.	5 / 5
	Total	18 / 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: vinvcn/mattpocock-skills-zh-CN
Path: skills/engineering/prototype/SKILL.md
Commit: 9fe7e7a

Reviewed: 11 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.