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 1xiaoyueryuer/boss-hr-agent-toolkit --skill boss-hr-autogit clone --depth 1 https://github.com/1xiaoyueryuer/boss-hr-agent-toolkitWrote 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/1xiaoyueryuer/boss-hr-agent-toolkit/boss-hr-auto)<a href="https://agentmods.dev/skills/1xiaoyueryuer/boss-hr-agent-toolkit/boss-hr-auto"><img src="https://agentmods.dev/badge/skills/1xiaoyueryuer/boss-hr-agent-toolkit/boss-hr-auto/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/1xiaoyueryuer/boss-hr-agent-toolkit/boss-hr-auto"><img src="https://agentmods.dev/badge/skills/1xiaoyueryuer/boss-hr-agent-toolkit/boss-hr-auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00211 | $0.03860 |
| Opus 5 | $0.00105 | $0.01930 |
| Sonnet 5 | $0.00042 | $0.00772 |
| Haiku 4.5 | $0.00021 | $0.00386 |
Grade A, and why
boss-hr-auto 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 12d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BOSS HR 统一筛选流程（v1.1+）
入口：
boss-hr统一 CLI。下文按步骤顺序调用 8 个公开命令。本 Skill 是纯文档。智能体按步骤顺序逐个调用统一命令。
行为边界
支持：
- 一次完整的新筛选任务；
- start → confirm → fetch → score → report；
- 用户明确要求时执行 greet。
不支持：
- continue / batch / 多批累计；
- 自动查找最新 run；
- 从其他 run 补数据；
- 自动跳过人工确认门。
公开命令（v1.1.1 起 8 个：含 doctor）
| 命令 | 作用 |
|---|---|
boss-hr doctor |
环境健康检查 + 启动辅助（首次或环境未知时先调） |
boss-hr start |
创建新 run，停在人工确认门 |
boss-hr confirm |
把 confirmed 翻 true |
boss-hr fetch --count N |
拉候选人列表 + 下载 N 份简历 |
boss-hr score |
评分协调（一次返回 1 位候选人） |
boss-hr report |
生成 HTML 报告 |
boss-hr greet |
给 ≥70 分候选人自动打招呼（需用户明确批准） |
boss-hr status |
读 runs/<run_id>/run.json + process 目录 |
禁止调用旧脚本：boss_jd.py / confirm_run.py / recommend_list.py /
recommend_download.py / prepare_scoring_inputs.py / collect_llm_scores.py /
score_resumes.py / generate_html_report.py / auto_greet.py /
cli_runner.py / spec JSON。
浏览器与登录态（v1.1.3 不阻塞扫码等待）
正常流程直接 start。start / fetch / greet 都自动保证 Edge + BOSS
登录态可用，不需要先跑 doctor：
- start 检查 9222 端口；未监听 → 自动启动专用 Edge
（
--user-data-dir=%LOCALAPPDATA%\boss-hr-edge-profile+--remote-debugging-port=9222， 不污染用户日常 Edge profile）。 - 自动启动后连接 CDP，只等待 CDP 端口/连接就绪（秒级，不阻塞扫码等待）。
- 已登录 → 继续执行 start 业务（实时解析岗位 → 创建 run）。
- 未登录 → 自动打开 BOSS 招聘者登录页 + 立即返回
status=waiting_user_login（不是错误，ok=true）。 - start 不在 CLI 内阻塞轮询扫码——避免 Agent / 用户被卡 20s。
用户在专用 Edge 窗口扫码登录后，重新执行完全相同的
boss-hr start命令 （不传任何新参数），让 CLI 复核登录态。 - start 收到
waiting_user_login时不创建 run、不抓 JD、不写 confirmed。
doctor 仍是独立诊断工具，但不再是 start 的必经前置。仅当：
- 自动启动 Edge 失败（
EDGE_LAUNCH_FAILED/CDP_NOT_RUNNING超时）； - CDP 可连但 BOSS 始终判定未登录；
- Edge 缺失或版本不匹配；
这些才用 doctor 排查。普通首次使用不需要先 doctor。
调试时可加 --no-auto-launch：缺 CDP 时直接返回 CDP_NOT_RUNNING，
跳过自动启动 Edge。--login-wait-seconds N（N>=1）启用旧 v1.1.2 阻塞轮询
路径；Agent 不应传该参数，仅作为人工调试兼容选项；
N<=0（含默认值 0）→ start 立即返回 waiting_user_login，不阻塞。
岗位解析规则（v1.1.1 强制）
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.
- 12d ago First seen · 297 lines · 211 tokens per session scan A 2324a85bd4d6
boss-hr-auto is a skill published in the GitHub repository 1xiaoyueryuer/boss-hr-agent-toolkit (46 stars, last pushed 1mo ago), licensed MIT. It adds 211 tokens to every session and 3,860 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
resume-tailor
I help you customize your resume for specific job applications. Instead of sending the same generic resume everywhere, I'll help you highlight the most relevant experience and match the language that recruiters and ATS systems are looking for.
cv-builder
This skill enables creation of professional CVs/resumes from structured YAML using rendercv. Define your experience once, generate beautiful PDFs in multiple themes.
liepin-cli
A command-line job-search tool for Liepin, a Chinese recruitment website, focused on jobs and résumés. It includes instructions for authentication and using search results correctly.
resume-modern
Modern minimal resume, single A4 page, ready for print or PDF export.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.