YouMind
Sign in
Skill Evaluator

Skill Evaluator

A reference for evaluating AI Skills

Installed by
11
CategoryResearch
FromYouMind

Showcase

评测 · 技能图标生成器 · 2026-08-27

评级:★★★★☆(4.1 / 5)|综合分 82 / 100 → 达到「留存/上架」判定线

结论:值得留存/继续上架——核心能力(锚点图锁定一致性的三件套流水线)经实测成立,且来源完全可信(作者即本人);但「单张长图交付」依赖环境拼图工具、描述缺负面边界两处短板,建议打磨后长期保留。

五维评分表

维度得分关键证据(事实)归因(推断)
触发可靠性26/303/3 正面触发成功(2 条 showcase+1 条现场实测);实测用自然口语「给我做一套视觉物料:技能名……」即触发描述含明确的输入格式与用途(inputHint),触发面清晰
执行有效性20/25实测完整跑通锚点→封面→信息区三步,封面以锚点图为参考、风格一致;showcase 两套成品均三件套齐全一致性机制(锚点图+头图原图复用)设计成立;但本环境无拼图工具时只能降级交付两张图
成本效率11/15实测 3 次生图+2 次确认门控即完成一套;无无用重试摇骰子随机基调有「用户不满意→重生成」的潜在重复成本;确认门控增加交互次数
稳健与边界11/15实测中确认门控严格执行:未经锚点确认不生成封面、未经文案确认不生成长图防漂移设计是本技能最大优点;但描述无「何时不该用」负面边界,负面/边缘用例未实测
安全可信14/15作者=用户本人(own_skill);reviewStatus=approved;全文可查;仅调用 Create image 技能,无异常外发来源完全可信,无数据风险

综合分 = 26+20+11+11+14 = 82 ≥ 80 → 达到留存/上架判定线。

短板归因

  • 描述(触发边界不全):描述只讲「该用时怎么用」,没写「何时不该用」(如:只想做单张图、已有固定视觉品牌时不该用),会诱使 AI 在用户只想要一张图时也跑整套流程。

  • 步骤(阶段三交付形态依赖环境):最后一步「合成单张 9:16 长图」要求执行环境支持图片拼接;本环境不支持时只能交付「头图原图+信息区」两张图,「开箱即用单张长图」的承诺打折扣。

  • 步骤(showcase 与铁律轻微偏离):水果动画 showcase 实际用「单次生图+头图参照重绘」方式出整张长图,与「头图绝不重绘、必须原图复用」的铁律不完全一致——成功率依赖模型听话,存在潜在漂移。

改进建议(按优先级)

  1. 描述补一句负面边界(最易改):加「当只需单个图标、或已有既定视觉规范时,不要启动三件套流程」。

  2. 阶段三写明降级交付:在步骤里预置「环境无拼图工具时,明确告知用户需自行拼接头图与信息区,并给出拼接尺寸建议」,避免交付时突然降级。

  3. 收敛 showcase 执行路径:统一走「先拼图后交付」或「单图生图」其中一条,避免同一步骤两种做法并存导致行为不稳定。

迭代落地记录(2026-08-27)

评测 · 技能图标生成器 · 2026-08-27

Description

Enter the name, link, or instructions for the AI Skill to evaluate, then conduct an evidence-based initial quality review in real-world usage scenarios. Keep the six-question quick test (4 positive, 1 negative, and 1 ambiguous), and separately verify automatic selection and execution after explicit invocation; successful manual invocation does not count as successful automatic triggering. Use direct scoring across five dimensions: triggering 30%, execution 25%, cost 15%, robustness and boundaries 15%, and safety 15%. Distinguish between evidence from this test, historical run evidence, static checks, and unverified items. Do not provide an overall score or star rating when key evidence is incomplete. Assess safety based on data access, external transmission, and operational authorization—not on the author's identity or endorsement. Block recommendations in cases of serious unauthorized access. Produce a one-page, conclusion-first report showing the tested scope, unverified items, and prioritized improvement suggestions, and automatically create a record. Say “deep review” to add independent repeat tests and source checks; the budget will be confirmed before execution. This Skill only evaluates and provides recommendations; it does not automatically modify the Skill being evaluated. Suitable for quality checks of self-created Skills, rechecks of installed Skills, and pre-installation screening of marketplace Skills; the six-question results do not represent full certification.

Editor's Recommendation
S

Recommended by

Shuting@YouMind

Why we love this skill

An evidence-based framework that separates automatic selection from explicit execution, scores only traceable results, and includes safety risks and process efficiency in its conclusions.

Related Skills

View all

Research Review Assistant

An expert assistant for university-level research project reviews. Provide the materials for N projects in a given category. Each project includes three types of files: a proposal, a form-check summary or interim review form, and supporting evidence. File names may be scrambled, mismatched, or changed, and files may be DOCX, XLSX, PDF, or image files. Supporting evidence may be bundled into one file or provided as multiple separate files. This Skill then completes the following steps: ① Content-anchor alignment—extracts the project or center name, principal investigator, affiliated school, and project period from within the documents; matches the three-part file set for each project; and flags items requiring review when file names do not match their contents. ② Evidence normalization—whether bundled or separate, breaks materials into “atomic evidence items” and creates a coded ledger for each item with one of four status labels: complete, needs verification, missing, or questionable. This avoids judging the strength of the evidence by file count. ③ Three-dimensional item-by-item audit—evaluates each piece of evidence for relevance, authenticity, and completeness, then reconciles it against the commitments in the proposal and the self-reported results in the interim review form. ④ Dual-track scoring and comparative ranking—uses the five weighted criteria in Appendix 2 as the reporting standard and the five dimensions of the interim review as a reference standard. The two systems remain independent and are not combined, and all projects are ranked and grouped into tiers. ⑤ Delivers a structured review draft with “score + review comments” that can be pasted directly into the official form, and can generate an interactive scoring webpage when needed. Huali’s current standards are used by default. Users can confirm or revise the criteria, weights, and reference materials before work begins, or upload replacements. There are two confirmation checkpoints: first for alignment and the evidence ledger, then for scoring and ranking. When materials cannot be identified, the user is prompted to confirm. For project completion reviews, two additional hard requirements apply: first, the correspondence between the proposal’s expected outcomes and the documented evidence must be verified. If the evidence does not include an expected outcome listed in the proposal, the project automatically fails. Second, template issues are distinguished between using the completely wrong template, which results in failure, and partial formatting inconsistencies, which result in only a small deduction.

H
14Free
Research

AI Project Eval & Validation

This skill is designed to provide comprehensive product or project validation analysis for entrepreneurs, product managers, and innovation teams. It helps users deeply analyze the market potential, risk points, and validation paths of new ideas, ensuring a clear understanding of core project assumptions before investing significant resources. Through multi-dimensional analysis, this skill can assess the project's current stage, identify key assumptions, and build an assumption dependency map to pinpoint the most vulnerable and dangerous parts of the project. It also analyzes the target user's role chain, the strength of current alternatives, and evaluates whether your solution has '10x improvement' potential. Additionally, it helps users identify potential 'killer questions,' conduct counterfactual failure analysis, and generate multiple positioning variants to explore more possibilities. In terms of commercialization, this skill assists users in selecting the appropriate business model, breaking down the deep reasons for user payment and purchase triggers, and proposing preliminary pricing logic. It also plans the Minimum Viable Saleable product (MVS) and devises a specific go-to-market (GTM) initial path and resource matching recommendations. Finally, it provides a tiered report containing detailed analysis, 7-day and 30-day validation plans, clear stage-gate decision suggestions, and next-step action guidelines, helping users quickly validate core assumptions at minimal cost.

L
11k
Webpage

Webpage Quality Review

This skill provides professional webpage evaluation and optimization services. Whether you are a website designer, developer, or content creator, you can use it to conduct an in-depth analysis of your own or someone else’s webpage and receive actionable improvement suggestions. The skill comprehensively evaluates a webpage’s design quality, originality, craftsmanship, and functionality. It provides detailed scores across multiple dimensions, including color combinations, typography and layout, visual themes, interactive effects, and responsive design, while also identifying potential signs of AI-generated content or template-based design. After the evaluation, you will receive a detailed report covering specific strengths, issues, improvement suggestions, and even possible directions for modifying CSS, HTML, and JavaScript code. After the evaluation report is generated, you can also choose to have AI optimize the webpage immediately based on its recommendations. The optimization process follows the priority order of design quality, originality, craftsmanship, and functionality. You will then receive an optimization completion report clearly showing score comparisons across each dimension before and after optimization, along with the key improvements made.

D
15Free

Information

Version
v4
Last updated
Runtime credits
Usage-based
Models
Auto

Ready to create something bolder?

Skill Evaluator