聘才猫(Pincaimao)模拟面试

v1.0.1

聘才猫 - 模拟面试 Use when calling Pincaimao Mock Interview API to simulate a real interview scenario with multi-turn conversation. Supports text and video modes, c...

1· 170·0 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-mock-interview.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "聘才猫(Pincaimao)模拟面试" (pincaimao/pincaimao-mock-interview) from ClawHub.
Skill page: https://clawhub.ai/pincaimao/pincaimao-mock-interview
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: PCM_MOCK_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-mock-interview

ClawHub CLI

Package manager switcher

npx clawhub@latest install pincaimao-mock-interview
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the declared requirements: PCM_MOCK_INTERVIEW_KEY, curl, and python3 are reasonable and expected for calling the Pincaimao API and parsing JSON. The SKILL.md's example API calls line up with the stated purpose.
Instruction Scope
Instructions are scoped to uploading resumes and driving multi-turn chat to api.pincaimao.com and require preserving conversation_id. Two notes: (1) it asks you to have 'pincaimao-basic' installed (an external dependency that increases surface area — inspect that skill separately), and (2) the optional inputs.url_callback feature can cause results to be POSTed to an arbitrary callback URL if the user supplies one, which could be used to forward data to third parties.
Install Mechanism
Instruction-only skill with no install spec or external downloads; nothing is written to disk or fetched at install time by the skill itself (lowest risk install model).
Credentials
Only a single API key (PCM_MOCK_INTERVIEW_KEY) is required, which is appropriate for an authenticated API client. No unrelated secrets, config paths, or excessive env variables are requested.
Persistence & Privilege
always:false and no indications the skill modifies other skills or system-wide settings. It does not request persistent system privileges.
Assessment
This skill appears to do what it claims, but review these before installing: 1) Keep PCM_MOCK_INTERVIEW_KEY secret — the agent will send it as a Bearer token to api.pincaimao.com. 2) The skill transmits resumes, job descriptions, and uploaded files to Pincaimao's API/COS; treat those as sensitive PII and confirm the service's retention/privacy policy. 3) Be cautious with the optional url_callback: do not provide untrusted callback URLs (they could receive your reports). 4) The SKILL.md asks you to install 'pincaimao-basic' — inspect that skill's instructions and permissions before installing it. 5) If you need stricter control, avoid autonomous invocation or limit what data you pass (omit sensitive fields or avoid file uploads).

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

Runtime requirements

🎭 Clawdis
Binscurl, python3
EnvPCM_MOCK_INTERVIEW_KEY
Primary envPCM_MOCK_INTERVIEW_KEY
latestvk97ecw36y32qjexazdsc67nksx842655
170downloads
1stars
2versions
Updated 3w ago
v1.0.1
MIT-0

聘才猫 - 模拟面试

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_MOCK_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(可选)。

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(均有默认值,可跳过):

  • 面试官角色:1 HR综合面试 / 2 专业面试
  • 是否生成参考答案:0 不生成 / 1 生成
  • 题目数量(默认 5)

多轮对话说明

模拟面试是多轮对话,必须使用 conversation_id 保持上下文

  • 第一轮:不传 conversation_id,从响应保存返回的 conversation_id
  • 后续轮次:每次都带上同一个 conversation_id
  • query 第一次传 job_info 前 20 字符(或 "请开始面试"),后续传用户回答

请求参数

字段必填类型说明
inputs.job_infostring职位描述全文
inputs.file_urlstring简历文件 cos_key
inputs.file_namestring简历文件名
inputs.resume_contentstring简历文本,JSON 字符串或纯文本
inputs.job_titlestring职位名称
inputs.video_urlstring视频文件 cos_key 或公网地址,视频面试每轮都需传
inputs.question_numberstring题目总数,字符串类型,默认 "5"
inputs.question_liststring自定义题目,JSON 字符串数组,如 "[\"问题1\",\"问题2\"]"
inputs.interview_roleint面试角色:1 HR综合面试,2 专业面试
inputs.reference_answerint参考答案:0 不生成,1 生成
inputs.url_callbackstring报告回调 URL(POST,返回 base64 编码报告)
querystring第一轮:job_info 前 20 字符;后续:用户回答
conversation_id第二轮起必填string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 $PCM_MOCK_INTERVIEW_KEY" \
  -F "file=@$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 $PCM_MOCK_INTERVIEW_KEY" \
  -H 'Content-Type: application/json' \
  -d "{
    \"query\": \"$QUERY\",
    \"inputs\": {
      \"job_info\": \"$JOB_INFO\",
      \"job_title\": \"$JOB_TITLE\",
      \"file_url\": \"$COS_KEY\",
      \"file_name\": \"$FILE_NAME\",
      \"question_number\": \"5\",
      \"interview_role\": 1,
      \"reference_answer\": 0
    },
    \"response_mode\": \"blocking\"
  }")

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
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 $PCM_MOCK_INTERVIEW_KEY" \
  -H 'Content-Type: application/json' \
  -d "{
    \"query\": \"$USER_ANSWER\",
    \"inputs\": {},
    \"conversation_id\": \"$CONV_ID\",
    \"response_mode\": \"blocking\"
  }" | python3 -c "import sys,json; print(json.load(sys.stdin)['answer'])"

与在线面试的区别

特性模拟面试在线面试
interview_role支持(HR/专业)不支持
reference_answer支持不支持
定位求职者练习用企业招聘用

常见错误

问题原因解决
401Key 错误检查 PCM_MOCK_INTERVIEW_KEY
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 "5",不是数字 5
interview_role 无效传了字符串必须是数字类型 12

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...