CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/engineering/prototype/SKILL.md
SKILL.md
Quality
Evals
Security

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.

An efficient, opinionated, and highly actionable overview that assumes Claude's competence and encodes clear decision rules (branch selection, ambiguity defaults, capture-on-completion). Its one significant defect is progressive disclosure: the body's two branch links point to LOGIC.md and UI.md, which are missing from the bundle, leaving the core branch instructions inaccessible.

Suggestions

Ship LOGIC.md and UI.md in the skill bundle — the body's central branch decision routes to them, and their absence makes the primary guidance unreachable.

Add one minimal worked example per branch in the body or reference files (e.g. a sample `pnpm` script entry for a UI prototype route, or the skeleton of the tabbed guided-walkthrough HTML) to move guidance from placeholders to copy-paste ready.

Make the completion loop explicit: spell out the validate-with-user step before 'capture' (confirm the verdict, then fold the decision into real code and branch the prototype), so the workflow has a visible checkpoint rather than an implicit one.

DimensionReasoningScore

Conciseness

The body is lean and directive throughout — "Prototype 是用来回答一个问题的 throwaway code。问题决定形状" sets framing in one line, and each of the six rules (e.g. "不写 tests,不做超过“能跑起来”所需的 error handling") adds only project-specific policy. No concept Claude already knows is explained; every token earns its place.

5 / 5

Actionability

Concrete, instruction-level guidance dominates: launch via "`pnpm <name>`、`python <path>`、`bun <path>`", a double-clickable single HTML file, "通过 URL search param 和浮动底栏切换", scratch DBs named "PROTOTYPE — wipe me", and commit-to-throwaway-branch capture. As an instruction-only skill this is actionable without code, but it is not 5: the commands are placeholders rather than a worked example (e.g. a sample package.json script or a minimal variant-switching snippet), and branch details are delegated out.

4 / 5

Workflow Clarity

The sequence is clear: identify the question ("来自用户 prompt、周围代码,或在用户在线时直接询问") → pick a branch with an explicit tie-breaking default ("backend module → logic;page 或 component → UI") → build under the six rules → "完成后 capture". Checkpoints exist implicitly (rule 5's expose-state after every action, capturing only "验证过的 decision") but there is no explicit validate-with-user/fix loop, keeping it below 5.

4 / 5

Progressive Disclosure

The structure itself is good — a short overview that cleanly delegates the two branches to well-signaled, one-level-deep links ([LOGIC.md](LOGIC.md), [UI.md](UI.md)). However, neither LOGIC.md nor UI.md exists in the bundle (no references/, scripts/, or assets/ directories are present), so the branch-specific instructions the overview points to are unreachable; navigation is broken rather than easy, which drops it below 4.

3 / 5

Total

16

/

20

Passed

Description

62%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 solid description with an explicit 'use when' clause and two concrete trigger scenarios, written in appropriately impersonal voice. Its main weakness is thin specificity: it says 'build a throwaway prototype to answer a design question' without describing the actual artifacts (single-file HTML demos, switchable UI variants) or broader trigger synonyms.

Suggestions

Add 1-2 concrete artifact details to the what-clause, e.g. '构建一次性原型(单个可分享的 HTML 状态机 demo 或可切换的 UI 变体路由)来回答一个设计问题', to lift specificity from 'one action' toward comprehensive coverage.

Broaden trigger coverage with natural synonyms users actually say — mock, demo, spike, POC, wireframe, '快速试一下这个交互' — alongside the existing 验证/探索 phrasings.

State the disposal/capture behavior as a distinguishing capability (throwaway branch, verdict captured on the issue) to further separate it from generic UI or diagramming skills.

DimensionReasoningScore

Specificity

"构建一次性原型来回答一个设计问题" names the domain (throwaway prototyping) and one concrete action (build a prototype to answer a design question), but stops there — it never says what the artifacts are (single shareable HTML file, switchable UI variants), matching the '1-2 concrete actions, not comprehensive' anchor. It is not 4 because there are not several distinct specific actions listed.

3 / 5

Completeness

It has an explicit what ("构建一次性原型来回答一个设计问题") and an explicit use-when clause ("适用于用户想验证…或探索…时") with two concrete trigger scenarios, so it clears the level-3 cap for a missing use-when clause. It is not 5 because the 'what' remains high-level — it does not concretely state what gets built (an HTML state-machine demo, UI variation routes).

4 / 5

Trigger Term Quality

"验证某个 state model 或 logic 是否感觉对" and "探索 UI 应该长什么样" are natural phrases a user would say, so this is above level 2, but coverage is narrow — missing common synonyms users would reach for such as mock, demo, spike, POC, or wireframe. That fits 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The niche is distinctive — throwaway prototypes built to answer a single design question, split into logic/state-model validation vs UI exploration — with triggers unlikely to fire for unrelated skills. It is not 5 because it could still mildly overlap with generic frontend-design or diagramming/mockup skills given no artifact details distinguish it.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
vinvcn/mattpocock-skills-zh-CN
Reviewed

Table of Contents

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.