Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add agentsope/career-skills --skill career-jd-analyzergit clone --depth 1 https://github.com/agentsope/career-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/agentsope/career-skills/career-jd-analyzer)<a href="https://agentmods.dev/skills/agentsope/career-skills/career-jd-analyzer"><img src="https://agentmods.dev/badge/skills/agentsope/career-skills/career-jd-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agentsope/career-skills/career-jd-analyzer"><img src="https://agentmods.dev/badge/skills/agentsope/career-skills/career-jd-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00261 | $0.03005 |
| Opus 5 | $0.00130 | $0.01503 |
| Sonnet 5 | $0.00052 | $0.00601 |
| Haiku 4.5 | $0.00026 | $0.00300 |
Grade A, and why
career-jd-analyzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Career JD Analyzer · 岗位需求拆解器
把一份招聘 JD——常常写得又虚又长、还夹着"黑话"——拆成看得懂、能行动的东西:这岗硬性要什么、核心能力是什么、什么是加分项、哪些话有潜台词,以及你到底该不该投、还缺什么。这是 career-skills pack「定位投哪」环节的关键一环。
核心原则:Decode the real JD, never invent one. 只解读用户提供或联网抓到的真实 JD;抓不到就明说请用户贴链接 / 文本,绝不编造 JD 内容或职位链接。潜台词解读基于常见招聘信号,标注为"提示"而非断言,提醒用户核实。
Activation Rules
触发(do):
- "帮我看看这份 JD 到底要什么 / 帮我拆解招聘要求。"
- "这个岗位我能投吗 / 我合不合适?"(给了 JD)
- "JD 写得太虚 / 看不懂,翻译成人话。"
- "这些要求里哪些是硬性卡的、哪些是加分?"
- "这 JD 有没有坑 / 潜台词?"
不触发(don't — 交给别的 skill):
- "有哪些岗位适合我 / 帮我找在招岗位" →
career-role-finder。 - "对照这个岗我该学什么" →
career-gap-planner。 - "帮我把简历改得对上这个岗" →
career-resume-tailor。 - "我这段经历能体现什么能力" →
career-experience-mapper。
Agentic Protocol
按顺序执行;每步有可验证产出。涉及方法细节时按需 Read 对应 reference。
Step 1 — 取真实 JD (Intake & Fetch · J1). 要到真实 JD:用户贴链接(牛客 / Boss / 实习僧等)→ 联网 WebFetch 抓正文;或用户贴 JD 文本。抓不到(登录墙 / 反爬 / 失效)→ 明说"没取到,请把 JD 正文贴给我",不编造。需要平台入口时 Read references/job-platforms.md。
→ 产出:真实 JD 正文(标注来源 + 时间)。
Step 2 — 解剖结构 (Parse · J2). Read references/jd-anatomy.md。把 JD 切成:岗位职责 / 任职要求 / 加分项 / 公司·团队·薪资·地点。区分硬性门槛(学历 / 专业 / 经验 / 必须技能)与软性 / 加分。
→ 产出:分类后的要求清单。
Step 3 — 提能力模型 (Competency · J3). Read references/competency-extraction.md。把要求映射到能力模型(与 career-experience-mapper 同一套词汇:NACE 8 + O*NET + 硬技能),并按"频率 × 位置"提关键词。
→ 产出:结构化能力模型(required / preferred / competencies / keywords)。
Step 4 — 解读潜台词 (Decode Subtext · J4). Read references/jd-subtext.md。识别招聘黑话 / 潜台词 / 红旗(如"抗压强"≈强度大),标为"提示,需核实",不臆断到极端。
→ 产出:潜台词提示 + 可问 HR 的核实问题。
Step 5 — 输出 + 判断 (Output · J5). 结果优先:先给"这岗要什么 + 你该不该投"的一句话判断,再按需展开。喂给下游(mapper / tailor / gap-planner)。 → 产出:能力模型 + 投递判断 + handoff。
Core Operation Models
| # | 模型 Model | When to use | Key action |
|---|---|---|---|
| J1 | Intake & Fetch 取真实 JD | 开始 | 链接→联网抓 / 文本;抓不到就要,不编 |
| J2 | Parse 解剖结构 | 拿到 JD | 切职责/要求/加分/公司;分硬性 vs 软性 |
| J3 | Competency 提能力模型 | 结构化 | 映射 NACE/O*NET(与 mapper 同词汇)+ 关键词 freq×position |
| J4 | Decode Subtext 解读潜台词 | 看懂言外之意 | 黑话/红旗→标"提示需核实"+ 给核实问题 |
| J5 | Output 判断+交接 | 输出 | 该不该投 + 缺什么 + 能力模型喂下游 |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 166 lines · 261 tokens per session scan A 74cf8e38a24f
career-jd-analyzer is a skill published in the GitHub repository agentsope/career-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 261 tokens to every session and 3,005 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ats-latex-cv
Build ATS-optimised, human-sounding CVs in LaTeX (Overleaf-ready code). Trigger this skill whenever a user asks to create, rewrite, reconstruct, or improve a CV, resume, or job application document — including when they upload an existing CV, paste raw experience, or describe a target role. Also trigger when the user…
Academic CV Builder
Format CVs for academic positions with publications, grants, and teaching.
vitaecontext-wiki-maintenance
Maintainer-only skill for refreshing VitaeContext wiki knowledge from official sources. Use only from a local repository clone when a maintainer asks to refresh one module, audit all module wiki entries, or audit module source lists.
vitaecontext-vitaegraph
Build, deepen, validate, index, and maintain a private hierarchical career knowledge graph from supplied career materials. Use when the user asks to create or update a VitaeGraph, model education with nested courses or thesis work, enrich projects from Git repositories, or supply deep selected career context to…
vitaecontext-build
Build, normalize, and maintain the user's Career Context file so downstream platform outputs stay factual and consistent. Use when the user wants an agent to consolidate CV data, LinkedIn exports, GitHub history, project summaries, bio facts, achievements, or positioning into one professional source of truth before…
vitaecontext-cv
Optimize CV and resume content for recruiter readability and parser-safe ATS handling without making unsupported claims about exact vendor scoring. Use when the user asks about resumes, CVs, ATS formatting, keyword strategy, bullets, section order, achievement metrics, or job-targeted resume tailoring.