jd-reading SKILL.md skillA
jd-reading from yanquan-dozzy/boss-claw is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add yanquan-dozzy/boss-claw/jd-reading@git:20260914.6698006Pins git:20260914.6698006 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- yanquan-dozzy/boss-claw
- Path
desktop-app/skills/jd-reading/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260914.6698006, committed Sep 14, 2026
- Size
- 11,692 bytes
- Repository stars
- 56
- License
- Apache-2.0
定制简历前先按四层拆解 JD（硬门槛/优先条件/职责信号/团队信号），再据此改写简历；覆盖要点提取、经历重排、结果表达与顶部摘要.
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
# AI 技能 · JD 拆解方法（读 JD 再定制） 调用 AI 生成岗位定制简历时，以下指令由 BossClaw skills 层注入 system prompt，与内置「岗位定制简历」共同生效，必须遵守。本技能只规定**怎么读 JD、怎么把 JD 翻译成简历改写动作**；涉及事实的一切约束仍以「岗位定制简历」技能与系统提示词的事实红线为准（本技能不授权编造任何经历、技能、数字或承诺）。 **执行顺序要求：先按本技能把 JD 读完（四层拆解 + 关键词 + 顺序 + 结果表达），再开始输出定制内容。** 允许在内部完成拆解，不要求把拆解过程写进输出；但输出的 `jdPoints`、`resume`、`rewrites`、`highlightedSkills` 必须是读完 JD 之后的结论，不得跳过拆解直接润色。 --- ## 一、怎么读懂招聘 JD：把岗位要求拆成简历、投递和面试的 3 次改写 很多求职者看招聘 JD 时，只会做两件事：一是扫一眼职位名称，二是盯着「要求 3-5 年」「熟悉 XX 工具」「有相关经验」这种硬条件。结果是，能不能投递主要靠感觉，简历怎么改靠猜，面试怎么答靠临场发挥。这样做的问题不是不努力，而是把一份 JD 只看成了「岗位说明」，没有把它当成一张可执行的求职地图。 真正高效的求职方式，是把 JD 拆成三次改写。第一次，改写你的判断，决定值不值得投；第二次，改写你的简历，让招聘方一眼看到匹配点；第三次，改写你的面试表达，把岗位要求翻译成你自己的经历和结果。只要这三次改写到位，同一份岗位信息就会变成简历、投递和面试三个阶段的共同答案。 --- ## 二、先读懂 JD 里最重要的四层信息 一份 JD 看起来内容很多，但真正有价值的信息通常只分成四层。 ### 1. 硬门槛 这是不能绕开的部分，比如学历、年限、语言、行业背景、是否接受远程、是否接受出差。这类信息的作用不是让你「证明自己很努力」，而是让你快速判断自己是否具备进入下一步的资格。 ### 2. 优先条件 很多 JD 会写「优先」「加分」「有过 XX 经验者更佳」。这部分不是装饰，而是招聘方在告诉你：如果你不完全匹配，至少要拿出一段可迁移经历去补位。比如「优先有 B 端经验」，你就要在简历里强化流程复杂度、沟通链路和交付结果。 ### 3. 职责信号 职责部分最值得读。因为它不是在描述岗位名字，而是在描述这个人每天到底要做什么。一个岗位如果反复提「沟通」「推进」「复盘」「数据」「协同」，说明它更看重项目推进能力；如果反复提「转化」「留存」「增长」「投放」，说明它更偏结果导向；如果反复提「方案」「需求」「产品迭代」，说明它更关注结构化思考。 ### 4. 团队信号 …
Read the whole file at its exact version.
How to install
mdr add yanquan-dozzy/boss-claw/jd-reading@sha256:1d258921ad644731The line at the top of this page pins the label git:20260914.6698006, 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_t7ql35yocnjr25uv)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 14, 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 (11692 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
yanquan-dozzy/boss-claw · 56 stars · license Apache-2.0 · pushed 2026-10-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_t7ql35yocnjr25uv GET https://markdownregistry.com/api/v1/resolve?ref=yanquan-dozzy/boss-claw/jd-reading GET https://markdownregistry.com/api/v1/blob/1d258921ad644731f6a6c58a8babd7ad441aeb9f8905d625fec7a5aaf704f997
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.