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-greetgit 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-greet)<a href="https://agentmods.dev/skills/1xiaoyueryuer/boss-hr-agent-toolkit/boss-hr-greet"><img src="https://agentmods.dev/badge/skills/1xiaoyueryuer/boss-hr-agent-toolkit/boss-hr-greet/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-greet"><img src="https://agentmods.dev/badge/skills/1xiaoyueryuer/boss-hr-agent-toolkit/boss-hr-greet.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 | $0.00228 | $0.04144 |
| Opus 5 | $0.00114 | $0.02072 |
| Sonnet 5 | $0.00046 | $0.00829 |
| Haiku 4.5 | $0.00023 | $0.00414 |
Grade A, and why
boss-hr-greet 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BOSS 直聘 HR · 自动打招呼
本 Skill 是 boss-hr-auto 主流程的 Step 5，在评分报告生成后由智能体调用（默认真点击 BOSS，不 dry-run、不二次确认）。
也支持单独运行（精准点名 / 回头招呼老名单 / 仅刷新位置表）。
实现脚本：
scripts/auto_greet.py（本目录内）。
安装 / 工作区假设
本 Skill 默认按以下约定运行（不硬编码任何用户的本地路径）：
| 环境项 | 默认值 | 怎么改 |
|---|---|---|
| 工作区根 | ~/Desktop/boss-hr-output/<encryptJobId>/ |
设环境变量 BOSS_HR_OUTPUT_DIR=<你想要的路径>，整个 toolkit 都会用新路径（shared/output_manager.py 已支持） |
| 岗位目录名 | BOSS 的 encryptJobId（不再用中文岗位名） |
通过 --encrypt-job-id 显式传，或设 env BOSS_HR_ENCRYPT_JOB_ID |
| shared 路径 | 自动按 scripts/ 的相对路径定位（../../shared） |
无需配，跟仓库走 |
| 浏览器 CDP | http://localhost:9222 |
暂无 env 覆盖；如需改请改 auto_greet.py 顶部 CDP_URL 常量 |
其他机器 / WSL / Linux 部署：先
export BOSS_HR_OUTPUT_DIR=/your/path，然后按下面的命令直接跑即可。
主流程调用（推荐）
智能体跑完 Step 4（HTML 报告）后调本步，必须传与前面各 Step 相同的 --run-id 和 --encrypt-job-id。
- 默认行为：CDP 真实点击 BOSS 打招呼按钮（按 score≥70 推荐 tier 招呼，最多 10 人）
- 跳过：不调用本 Skill 即可
单独招呼（不走主流程）
🚨 新接口必传
--encrypt-job-id：与 Step 1/2/3 保持一致。也可以设 envBOSS_HR_ENCRYPT_JOB_ID作为 fallback。缺则直接ValueError退出（严格模式）。
# 公共参数
export ENCRYPT_ID="9a7759badfd95d350nFz3d-_F1NX"
export JOB_NAME="线控底盘制动、转向工程师"
# === 模式 1：默认（一键：自动扫位置 + 倒序招呼）===
python -X utf8 "<项目根>/boss-hr-greet/scripts/auto_greet.py" \
--job-name "$JOB_NAME" \
--encrypt-job-id "$ENCRYPT_ID" \
--run-id "$RUN_ID" \
--only-names "朱子睿,孙庆乐"
# === 模式 2：默认按分招呼（≥70 推荐 tier 自动招呼，最多 10 人）===
python -X utf8 "<项目根>/boss-hr-greet/scripts/auto_greet.py" \
--job-name "$JOB_NAME" \
--encrypt-job-id "$ENCRYPT_ID" \
--run-id "$RUN_ID"
# === 模式 3：只扫描（不下发，用于调试 / 刷新位置表）===
python -X utf8 "<项目根>/boss-hr-greet/scripts/auto_greet.py" \
--job-name "$JOB_NAME" \
--encrypt-job-id "$ENCRYPT_ID" \
--run-id "$RUN_ID" \
--only-names "朱子睿" --scan-only
# === 模式 4：用已有位置表直接招呼（list 状态未变时省 2 秒扫描）===
python -X utf8 "<项目根>/boss-hr-greet/scripts/auto_greet.py" \
--job-name "$JOB_NAME" \
--encrypt-job-id "$ENCRYPT_ID" \
--run-id "$RUN_ID" \
--only-names "朱子睿" --skip-scan
What ships with it
1 file 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.
- 12d ago First seen · 346 lines · 228 tokens per session scan A 32ffdbf049b0
boss-hr-greet is a skill published in the GitHub repository 1xiaoyueryuer/boss-hr-agent-toolkit (46 stars, last pushed 1mo ago), licensed MIT. It adds 228 tokens to every session and 4,144 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
computer-use
OS/window-level inspection and input in visible local app windows through orca computer: native apps, external browser windows (Chrome, Edge, Safari), and app webviews. Not for Orca's embedded browser (use orca-cli) or page-only automation (use Playwright or CDP).
opencli-browser
Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing…
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
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.
opencli-browser-sitemap
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.