idea-evaluate SKILL.md skillA
idea-evaluate from kendrick-stein/mcislab_deepread is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kendrick-stein/mcislab_deepread/idea-evaluate@git:20260723.fb64ba4Pins git:20260723.fb64ba4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kendrick-stein/mcislab_deepread
- Path
skills/2-ideation/idea-evaluate/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260723.fb64ba4, committed Jul 23, 2026
- First version recorded
- Apr 28, 2026
- Size
- 7,157 bytes
- Repository stars
- 12
- License
- none declared
当用户说"评估一下这个 idea""这个可行吗"， 从 novelty/feasibility/impact/risk/evidence 五维评估研究 idea.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
## Purpose 给定一个研究 idea，它系统性地从五个维度进行评估： | 维度 | 含义 | | :--- | :--- | | **Novelty** | 与已有工作的差异化程度——这个 idea 是否真的新？ | | **Feasibility** | 当前资源条件下能否执行——有没有致命工程障碍？ | | **Impact** | 若成功，对领域的贡献——有多少人会在意这个结果？ | | **Risk** | 主要失败模式和概率——分越高代表风险越低 | | **Evidence** | 当前支撑假设的证据强度——有多少先验支撑这个方向？ | 评估结果包含五维评分、总分、Reasoning 和可选 Suggestions，供调用方决策使用。 ## 输入格式 idea-evaluate 支持两种输入： 1. **文件路径**: 如`[[Ideas/xxx.md]]`，用 Read 打开文件，提取信息。 2. **结构化文本**：候选 idea 描述。 ## Steps ### Step 1：读取相关 Paper 笔记 根据输入类型获取相关论文： - 若输入为文件路径，从提取Related Work的wikilinks，逐一 Read 对应的 Paper 笔记。 - 若输入为结构化文本，根据 idea描述 中的关键词，用 Grep 在 `Papers/` 中搜索最相关的 2-4 篇笔记并读取。 从每篇笔记中提取： - **Summary**：论文核心贡献一句话 - **Method**：方法要点（判断与 idea 的差异化） - **Key Results**：主要实验结果（判断 idea 的 Novelty 和 Evidence） - **Strengths & Weaknesses**：先前工作的局限（判断 idea 的 Feasibility 和 Impact） ### Step 2：Prior-art challenge（WebSearch 反向验证） 目标不是证明 idea 新颖，而是**尽最大努力推翻它的新颖性**。用 WebSearch 至少覆盖：idea 原始表述、核心机制的术语、应用场景变体、相邻学科的别名，以及 limitation / failed / replication 类反向词。 - 关键词从 hypothesis 与 approach sketch 提取；**机制层术语优先于方法名**（避免只搜当前流行词而漏掉旧名称/邻域工作）。 - 找到最接近的已有工作（closest prior art），据此给出 prior-art 状态标签： - **CONFIRMED_UNDEREXPLORED**：检索到少量相关工作，但核心问题仍缺系统研究或关键证据 …
Read the whole file at its exact version.
How to install
mdr add kendrick-stein/mcislab_deepread/idea-evaluate@sha256:9985c1bc1e6667e6The line at the top of this page pins the label git:20260723.fb64ba4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_tanxqm4jgyjwl4ae)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Apr 28, 2026 and Jul 23, 2026, about one every 86 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260723.fb64ba4 latest | 2026-07-23 | fb64ba4 | 7,157 B | A | view · diff |
| git:20260428.bf023ec | 2026-04-28 | bf023ec | 6,185 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7157 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kendrick-stein/mcislab_deepread · 12 stars · license none declared · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tanxqm4jgyjwl4ae GET https://markdownregistry.com/api/v1/resolve?ref=kendrick-stein/mcislab_deepread/idea-evaluate GET https://markdownregistry.com/api/v1/blob/9985c1bc1e6667e6d188c7e62e9daf4f45028f0e27ac537057c531513008a276
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.