聘才猫(Pincaimao)在线面试

v1.0.1

聘才猫 - 在线面试 Use when calling Pincaimao Online Interview API to conduct a multi-turn AI interview session. Supports text and video interview modes, custom ques...

1· 166·0 current·0 all-time
by聘才猫(Pincaimao)@pincaimao

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for pincaimao/pincaimao-online-interview.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "聘才猫(Pincaimao)在线面试" (pincaimao/pincaimao-online-interview) from ClawHub.
Skill page: https://clawhub.ai/pincaimao/pincaimao-online-interview
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: PCM_ONLINE_INTERVIEW_KEY
Required binaries: curl, python3
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install pincaimao-online-interview

ClawHub CLI

Package manager switcher

npx clawhub@latest install pincaimao-online-interview
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (online interview) match the declared requirements: one API key (PCM_ONLINE_INTERVIEW_KEY), curl and python3 for HTTP calls and simple JSON parsing, plus expected parameters for job info, resume upload, video, and conversation_id.
Instruction Scope
SKILL.md instructs the agent to upload local resume files and to pass the user's API key in Authorization headers to api.pincaimao.com — this is appropriate for the feature. It also references installing/loading a related 'pincaimao-basic' skill for shared interfaces. The doc allows the user/agent to set a url_callback (arbitrary URL) which means the final report can be posted to any endpoint the user supplies; that's functional but a privacy/exfiltration risk if an untrusted callback is used.
Install Mechanism
Instruction-only skill with no install spec and no downloaded code. No files are written by the skill itself and no external archives/third-party packages are fetched by the skill.
Credentials
Only one required environment variable (PCM_ONLINE_INTERVIEW_KEY) is declared and is the primary credential used in Authorization headers. No unrelated secrets, extra credentials, or config paths are requested.
Persistence & Privilege
always:false and no instructions to modify other skills or system settings. The skill runs network calls scoped to the Pincaimao API and does not claim persistent installation or cross-skill modification.
Assessment
This skill appears to do what it says: it will call api.pincaimao.com using the PCM_ONLINE_INTERVIEW_KEY and can upload local resume files. Before installing or invoking: (1) only set PCM_ONLINE_INTERVIEW_KEY if you trust the Pincaimao service and avoid placing the key in shared/public environments; (2) be cautious about uploading sensitive files (resumes, transcripts) — those are sent to Pincaimao and stored in their COS; (3) only provide a url_callback you control or trust, since the platform will POST the generated report there; (4) review or audit any referenced prerequisite skill (pincaimao-basic) before loading it. If you need higher assurance, ask for the pincaimao-basic SKILL.md and any network/debug logs to verify exactly what endpoints will be called.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🎥 Clawdis
Binscurl, python3
EnvPCM_ONLINE_INTERVIEW_KEY
Primary envPCM_ONLINE_INTERVIEW_KEY
latestvk975jn8tvpnprbzer8119d41fs843qc7
166downloads
1stars
2versions
Updated 3w ago
v1.0.1
MIT-0

聘才猫 - 在线面试

REQUIRED: 请先检查是否已安装 pincaimao-basic,若未安装请先安装,然后加载它了解通用接口(文件上传、鉴权、响应格式、SSE 解析模板)。

环境变量PCM_ONLINE_INTERVIEW_KEY(智能体专属 key)

还没有密钥?通过邀请链接注册并完成认证即可免费获取:pincaimao.com/agents/login?invite_code=uwqc

调用前的信息确认

执行前需要确认:职位描述(job_info)简历文件

确认策略:

  • 上下文中已有相关信息 → 展示摘要并询问是否使用
  • 上下文中没有 → 直接请用户提供

同时可询问:

  • 面试题总数(question_number,默认 5)
  • 是否使用自定义题目(question_list
  • 是否视频面试(需要 video_url
  • 报告回调地址(url_callback

多轮对话说明

在线面试是多轮对话,必须使用 conversation_id 保持上下文

  • 第一轮:不传 conversation_id,从响应中保存返回的 conversation_id
  • 后续轮次:每次都传入同一个 conversation_id
  • query 第一次传 job_info 前 20 字符,后续传用户回答内容(视频面试传视频转写文字)

请求参数

字段必填说明
inputs.job_info职位描述全文
inputs.file_url简历文件 cos_key
inputs.file_name简历文件名
inputs.resume_content简历文本,JSON 字符串或纯文本,AI 自动解析
inputs.job_title职位名称
inputs.video_url视频文件 cos_key 或公网地址,视频面试每轮都需传
inputs.question_number面试题总数,默认 5,字符串类型
inputs.question_list自定义题目,JSON 字符串数组,如 "[\"问题1\",\"问题2\"]"
inputs.url_callback报告生成后的回调 URL(POST,返回 base64 编码报告)
query第一轮:job_info 前 20 字符;后续:用户回答
conversation_id第二轮起必填保持多轮对话上下文

完整示例

#!/bin/bash
JOB_INFO="高级销售专员 / 销售主管,行业领先平台,完善晋升通道"
JOB_TITLE="高级销售专员"
RESUME_FILE="/path/to/resume.docx"

# Step 1: 上传简历(可选)
UPLOAD=$(curl -s -X POST 'https://api.pincaimao.com/agents/v1/files/upload' \
  -H "Authorization: Bearer $PCM_ONLINE_INTERVIEW_KEY" \
  -F "file=@$RESUME_FILE")
COS_KEY=$(echo "$UPLOAD" | python3 -c "import sys,json; print(json.load(sys.stdin)['cos_key'])")
FILE_NAME=$(echo "$UPLOAD" | python3 -c "import sys,json; print(json.load(sys.stdin)['filename'])")

# Step 2: 第一轮 - 开始面试
QUERY=$(echo "$JOB_INFO" | cut -c1-20)
ROUND1=$(curl -s -X POST 'https://api.pincaimao.com/agents/v1/chat/chat-messages' \
  -H "Authorization: Bearer $PCM_ONLINE_INTERVIEW_KEY" \
  -H 'Content-Type: application/json' \
  -d "{
    \"query\": \"$QUERY\",
    \"inputs\": {
      \"job_info\": \"$JOB_INFO\",
      \"job_title\": \"$JOB_TITLE\",
      \"file_url\": \"$COS_KEY\",
      \"file_name\": \"$FILE_NAME\",
      \"question_number\": \"5\"
    },
    \"response_mode\": \"blocking\"
  }")

# 保存 conversation_id 用于后续轮次
CONV_ID=$(echo "$ROUND1" | python3 -c "import sys,json; print(json.load(sys.stdin)['conversation_id'])")
echo "面试官:$(echo "$ROUND1" | python3 -c "import sys,json; print(json.load(sys.stdin)['answer'])")"

# Step 3: 后续轮次 - 提交回答
USER_ANSWER="我有5年销售经验,擅长大客户开拓..."
curl -s -X POST 'https://api.pincaimao.com/agents/v1/chat/chat-messages' \
  -H "Authorization: Bearer $PCM_ONLINE_INTERVIEW_KEY" \
  -H 'Content-Type: application/json' \
  -d "{
    \"query\": \"$USER_ANSWER\",
    \"inputs\": {},
    \"conversation_id\": \"$CONV_ID\",
    \"response_mode\": \"blocking\"
  }" | python3 -c "import sys,json; print(json.load(sys.stdin)['answer'])"

任务结束检测

面试结束时,streaming 模式下会收到:

node_finished 且 data.title 包含"聘才猫任务结束"

此时停止轮询,面试报告将通过 url_callback 回调(如已配置)。

常见错误

问题原因解决
401Key 错误检查 PCM_ONLINE_INTERVIEW_KEY
第二轮面试官不记得上文未传 conversation_id每轮必须传第一轮返回的 conversation_id
question_number 无效传了数字类型此字段需传字符串,如 "5"
回调未收到报告面试未正常结束检查是否收到任务结束事件

输出模式

  • 默认:AI 对 API 返回结果进行整理表述,输出更易读的内容
  • 原始输出:用户说"显示原始输出"或"raw output"时,将 API 返回的原始内容用代码块原样展示,不作任何改动
    • Blocking 模式:直接取 answer 字段内容原样输出
    • Streaming 模式:将所有 message / agent_message 事件的 answer 片段拼接完整后,原样输出,不作重述

External Endpoints

  • https://api.pincaimao.com — Pincaimao platform API (chat, file upload, conversations)

Security & Privacy

  • API key is read from environment variable and passed via Authorization header; never hardcoded
  • Resume files, job descriptions, and contract text are transmitted to api.pincaimao.com for AI processing
  • Uploaded files are stored on Pincaimao's COS (Cloud Object Storage); returned cos_key paths should be treated as sensitive
  • This skill does not store, log, or transmit data to any endpoint other than api.pincaimao.com
  • Safe to invoke autonomously; all network calls are scoped to the authenticated user's API key

Comments

Loading comments...