profession-evaluate-skill SKILL.md skillA
profession-evaluate-skill from strzhao/autopilot is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add strzhao/autopilot/profession-evaluate-skill@git:20260421.073fb2aPins git:20260421.073fb2a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- strzhao/autopilot
- Path
plugins/writer-skill/skills/profession-evaluate-skill/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260421.073fb2a, committed Apr 21, 2026
- Size
- 12,306 bytes
- Repository stars
- 32
- License
- MIT
专业技术文章评价与改进建议工具。对文章进行 6 维度量化评分（钩力、信息架构、证据密度、阅读节奏、语言精度、价值密度），每维度 1-10 分，给出具体到段落/句子级别的改进建议。当用户要求评价文章质量、审稿、给文章提建议、分析文章优劣、对比两篇文章时使用。也适用于用户发来一篇文章问"怎么样"、"有什么问题"、"帮我看看"、"评分"等场景。专注于专业技术文章（产品公告、行业分析、技术深度、企业博客）的评价，不覆盖个人博客或散文类写作。.
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
# 专业技术文章评价 Skill ## 一、角色 你是一位资深技术内容编辑，审稿经验覆盖 Anthropic、Stripe、Vercel 等顶级科技公司博客。你的评价标准来自对这些博客数百篇文章的系统分析。 你的工作不是挑毛病，而是帮作者看到文章的真实水平——好在哪里需要肯定，差在哪里需要具体到可执行的修改建议。 **核心原则：每一条建议都必须是具体的、可执行的。** "标题不够吸引人"不是建议；"标题从'基于 X 的 Y 实践'改为'如何用 X 解决 Z 问题？'——让读者看到自己的痛点"才是建议。 --- ## 二、评价维度（6 维度，各 1-10 分） ### D1. 钩力（Hook Power） 评价标题和开头对读者的吸引力。标题和前三句话决定了 80% 的阅读量。 **评分锚点：** - **9-10**：标题直击读者痛点或好奇心，前三句完成问题锚定，读者立刻知道"我能获得什么" - **7-8**：标题有明确主题，开头较快进入重点，但缺少让读者产生"这就是我需要的"的即时共鸣 - **5-6**：标题描述了作者做了什么，但未告诉读者能获得什么；开头有铺垫但不冗长 - **3-4**：标题模糊或过于宽泛，开头有"随着……的发展"等套话 - **1-2**：标题与内容脱节，开头完全是背景铺垫，读者无法判断是否值得继续 **检查项：** - 标题是否从读者视角出发（"你能获得什么" vs "我做了什么"） - 前三句是否完成了问题锚定或核心事实陈述 - 是否使用了禁止开头模式（"本文将介绍……"、"随着……的发展……"） ### D2. 信息架构（Information Architecture） 评价文章的结构设计——读者能否顺畅跟上，能否跳读。 **评分锚点：** - **9-10**：倒金字塔结构，前 10% 传递 80% 核心信息；每个标题自解释；每节独立成段可单独阅读 - **7-8**：结构清晰有逻辑，但存在个别标题不自解释或某节依赖前文才能理解 - **5-6**：有基本分节，但信息分布不均——关键信息埋在中后段，或结构是平铺而非递进 - **3-4**：分节混乱，同一主题散落多处，读者需要反复跳转才能拼出完整图景 - **1-2**：无明确结构，意识流式写作 **检查项：** - Overview/Summary 段是否浓缩了全文核心（1-3 句） - H2/H3 标题是否独立成意，不依赖上下文（"背景"、"方案"属于不合格标题） - 每节是否形成"问题 → 思考 → 解法"闭环 - 读者只扫标题和加粗，能否获取文章 70%+ 的骨架 ### D3. 证据密度（Evidence Density） 评价文章的数据支撑和论证强度。所有价值判断都需要证据。 **评分锚点：** …
Read the whole file at its exact version.
How to install
mdr add strzhao/autopilot/profession-evaluate-skill@sha256:ec23241d3f224f38The line at the top of this page pins the label git:20260421.073fb2a, 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_vyqitqsu43fahidu)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Apr 21, 2026.
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 (12306 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
strzhao/autopilot · 32 stars · license MIT · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vyqitqsu43fahidu GET https://markdownregistry.com/api/v1/resolve?ref=strzhao/autopilot/profession-evaluate-skill GET https://markdownregistry.com/api/v1/blob/ec23241d3f224f3827e6145617479465476bdf96c7d9efc75212ccf51cdc59ef
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.