jwb-recruit-coach SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
jwb-recruit-coach from chenxiang6663635/job-workbench is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add chenxiang6663635/job-workbench/jwb-recruit-coach@v26.11.0Pins v26.11.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- chenxiang6663635/job-workbench
- Path
integrations/dsh/skills/jwb-recruit-coach/SKILL.md- Versions recorded
- 2
- Latest version
- v26.11.0, committed Nov 1, 2026
- First version recorded
- Oct 8, 2026
- Size
- 5,246 bytes
- Repository stars
- 16
- License
- MIT
Use when 解析 JD、给岗位打分、改写简历或生成投递材料时，需要按本工作台的评分框架、硬门槛过滤与诚实红线行事。触发场景包括执行 jwb-jd、jwb-apply、jwb-track、jwb-resume 工作流，或用户粘贴岗位描述要求判断是否值得投递。English triggers：scoring framework, eligibility gate, hard filters, honesty red lines, rewrite resume, application materials.
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
# 岗位评估与材料纪律 ## 核心原则 **判断由 AI 做，脚本只做 IO 与校验。** 评分不是 Python 算出来的，是你读 JD 原文与用户档案后填进解析卡的；`jobws jd` 只校验加总自洽并套阈值。改评分标准不用改代码，只改领域插件。 **唯一事实源是用户的 `00_事实库/`。** 简历动词、行为故事、经历匹配打分都必须回查事实卡，不得以解析卡概述或档案摘要为准。 ## 领域插件 配置位于领域插件目录 `profiles/<domain-id>/`： - `lexicon.md` —— 三级词典（Primary / Secondary / Weak） - `directions/<direction-id>.md` —— 方向锚点表 + 方向特有词 通过 `--domain` 与 `--direction` 定位。插件只被读取，永不被脚本写入。 **方向不属于当前领域时**，回退该领域的第一个方向，并在解析卡末尾追加： ``` ⚠️ 该岗位不属于当前领域的预设方向，评分基于 <方向> 配置计算，结论仅供参考。 ``` ## 流程：先过滤，再打分 Eligibility Gate **明确不通过** → **不打分、不写材料**，直接输出「不建议投递 + 原因」并终止。 判定顺序：学历 → 专业 → 届数 → 英语 → 城市。事实取自用户档案的「硬门槛事实」小节。 **字段为 `[待填]` → 结论写「待补档案」，不终止**：显式提示「请补齐档案中的 X 字段」，解析卡「硬门槛」节登记 `缺失字段: …`，**仍不打分、不生成材料**——补齐后重新评分即可。禁止猜测，禁止按「可能满足」放行；「待补档案」不是放行，是把一次判定拆成两步，判定权在补完档案之后。 城市拆两级：**硬性不可行**（要求本地户籍、必须长期驻外、明确不接受异地）→ 不通过并终止；**偏好类**（"本地优先""周边亦可""可接受搬家"）→ 不判 fail，在「培养与稳定性」扣分（轻度 -3、较强 -5，**合计不超过 5**，判据见 `references/scoring.md`）。工作形态问题（长期驻场、倒班、长期出差）不在此判定，同样归该维度扣分。 ## 评分：四维度与阈值 维度权重、培养与稳定性分档、总分档位与动作见 `references/scoring.md`（表格较长，按需读取）。四条纪律： - **技术匹配**按插件词典比对：Primary 3 分/项、Secondary 1.5 分/项；Weak 登记不扣分但触发风险提示。 - **经历匹配**逐条比对用户的经验资产与 JD 职责，**必须回查 `00_事实库/`**。 - **方向契合**按插件的方向锚点表取值；岗位名与职责不一致时以职责为准并说明依据。 …
Read the whole file at its exact version.
How to install
mdr add chenxiang6663635/job-workbench/jwb-recruit-coach@sha256:fb8756337971321fThe line at the top of this page pins the label v26.11.0, 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_dq5zjilsh2sqxqgg)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Oct 8, 2026 and Nov 1, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v26.11.0 latest | 2026-11-01 | c62388d | 5,246 B | A | view · diff |
| v26.10.0 | 2026-10-08 | 71afb4a | 5,246 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 (5246 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
chenxiang6663635/job-workbench · 16 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_dq5zjilsh2sqxqgg GET https://markdownregistry.com/api/v1/resolve?ref=chenxiang6663635/job-workbench/jwb-recruit-coach GET https://markdownregistry.com/api/v1/blob/fb8756337971321f7acc569beb64dd3a5667dac3ea9bc3ddc7211dc7221c0d27
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.
More from chenxiang6663635/job-workbench
Every file in chenxiang6663635/job-workbench