pincaimao-basic

聘才猫平台基础能力 Use when calling any Pincaimao platform API — file upload, presigned URL, conversation list, message history, audio-to-text, resume JSON upload, or the base chat-messages interface. Reference this skill before building any PCM agent skill.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "pincaimao-basic" with this command: npx skills add pincaimao/pincaimao-basic

聘才猫平台基础能力

所有聘才猫智能体 skill 共用的底层接口。具体智能体(JD 助手、简历匹配等)的 inputs 参数见各自的 skill,通用部分统一在此。


鉴权

接口Key 要求
chat-messages必须使用该智能体专属 key,不同智能体 key 不能混用
其他所有接口任意创建的 key 均可

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

# chat-messages 示例(key 由各智能体 skill 的 primaryEnv 声明,如 PCM_JD_ASSISTANT_KEY)
-H "Authorization: Bearer <agent-specific-key>"

# 其他接口示例
-H "Authorization: Bearer $PCM_ANY_KEY"   # 任意 key 即可

1. chat-messages(智能体对话)

POST https://api.pincaimao.com/agents/v1/chat/chat-messages

请求体

{
  "query": "...",
  "inputs": {},
  "response_mode": "blocking",
  "conversation_id": null,
  "user": null
}
字段必填说明
query依智能体而定
inputs各智能体自定义参数
response_mode"blocking""streaming",默认 streaming
conversation_id多轮对话时传入,保持上下文
user业务侧用户 ID

Blocking 响应

{
  "event": "message",
  "message_id": "...",
  "conversation_id": "...",
  "answer": "AI 回复内容",
  "metadata": { "usage": { "total_tokens": 953 } }
}

取结果:.answer

Streaming 响应(SSE)

每行以 data: 开头,包含 JSON 对象:

事件说明关键字段
message_start开始生成conversation_id, message_id
message / agent_message内容片段answer(需拼接)
node_finished节点完成data.inputs.LLMText(完整文本), data.title
message_end生成结束

特殊node_finisheddata.title 含"聘才猫任务结束"→ 任务完成。

Streaming 解析模板

curl -N -s -X POST 'https://api.pincaimao.com/agents/v1/chat/chat-messages' \
  -H "Authorization: Bearer <agent-specific-key>" \
  -H 'Accept: text/event-stream' \
  -H 'Content-Type: application/json' \
  -d '{"query":"...","inputs":{},"response_mode":"streaming"}' \
| python3 -c "
import sys, json
answer = ''
for line in sys.stdin:
    line = line.strip()
    if not line.startswith('data: '):
        continue
    try:
        d = json.loads(line[6:])
        event = d.get('event', '')
        if event in ('message', 'agent_message'):
            answer += d.get('answer', '')
        elif event == 'message_end':
            break
    except json.JSONDecodeError:
        pass
print(answer)
"

2. 文件上传

POST https://api.pincaimao.com/agents/v1/files/upload

curl -s -X POST 'https://api.pincaimao.com/agents/v1/files/upload' \
  -H "Authorization: Bearer $PCM_ANY_KEY" \
  -F "file=@/path/to/file.pdf"

响应:

{
  "filename": "resume.docx",
  "ext": "docx",
  "cos_key": "/resources/file/20250711/abc123.docx",
  "presigned_url": "https://..."
}

注意:后续传给智能体的是 cos_key,不是 presigned_url。支持格式:xlsx、docx、pdf、txt、csv、jpg、png,最大 50MB。


3. 获取文件临时链接

GET https://api.pincaimao.com/agents/v1/files/presigned-url

curl -s "https://api.pincaimao.com/agents/v1/files/presigned-url?cos_key=/resources/file/xxx/abc.jpg" \
  -H "Authorization: Bearer $PCM_ANY_KEY"

响应包含 file_url(10 分钟有效)。可选参数 expired(秒,最长 30 天)。


4. 获取会话列表

GET https://api.pincaimao.com/agents/v1/chat/conversations

curl -s "https://api.pincaimao.com/agents/v1/chat/conversations?limit=20&user=user_001" \
  -H "Authorization: Bearer $PCM_ANY_KEY"
参数说明
last_id游标分页,上一页最后一条 ID
user按用户 ID 筛选
limit每页条数,默认 20,最大 100

响应:data.data[]id(conversation_id)、nameinputscreated_at


5. 获取会话历史消息

GET https://api.pincaimao.com/agents/v1/chat/messages

curl -s "https://api.pincaimao.com/agents/v1/chat/messages?conversation_id=xxxx&limit=20" \
  -H "Authorization: Bearer $PCM_ANY_KEY"

倒序返回。参数 first_id 用于翻页。响应 data.data[]queryanswerinputscreated_at


6. 音视频转文字

POST https://api.pincaimao.com/agents/v1/tts/audio_to_text

curl -s -X POST 'https://api.pincaimao.com/agents/v1/tts/audio_to_text' \
  -H "Authorization: Bearer $PCM_ANY_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"cos_key": "/resources/file/xxx/audio.mp3"}'

响应:data.text(转写文字)。目前仅支持 cos_key 路径。


7. 简历 JSON 上传

POST https://api.pincaimao.com/v1/files/resume-json

将结构化简历数据上传,返回 cos_key 供后续智能体使用。

curl -s -X POST 'https://api.pincaimao.com/v1/files/resume-json' \
  -H "Authorization: Bearer $PCM_ANY_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "name": "张三",
    "gender": "男",
    "age": "28",
    "degree": "本科",
    "work_year": "5",
    "city": "广州市",
    "phone": "13800138000",
    "email": "zhangsan@example.com",
    "apply_job": "软件工程师",
    "education_objs": [...],
    "job_exp_objs": [...],
    "skills_objs": [{"skills_name": "Java", "skills_level": "精通"}]
  }'

响应:data.cos_key(供后续接口使用)。

<details> <summary>简历 JSON 完整字段列表</summary>

基本信息name, gender, age, marital_status, birthday, race, hometown_address, nationality, polit_status, city, phone, email, qq, weixin, avatar_url, avatar_data

求职意向apply_job, apply_cpy, work_year, work_position, work_company, work_status, work_salary, work_job_nature

学历college, college_dept, major, degree, recruit

自述cont_my_desc, cont_hobby

期望工作 (expect_job_objs[]):expect_job, expect_cpy, expect_salary, expect_industry, expect_time, expect_jnature, expect_jstatus, expect_jlocation

教育经历 (education_objs[]):start_date, end_date, edu_college, edu_college_dept, edu_major, edu_recruit, edu_degree, edu_content

工作经历 (job_exp_objs[]):start_date, end_date, job_cpy, job_position, job_dept, job_nature, job_salary, job_location, job_content

项目经历 (proj_exp_objs[]):start_date, end_date, proj_name, proj_cpy, proj_position, proj_content, proj_resp

培训经历 (training_objs[]):start_date, end_date, train_org, train_loc, train_name, train_cert, train_cont

技能 (skills_objs[]):skills_name, skills_level(掌握/熟悉/擅长/精通)

语言 (lang_objs[]):language_name, language_level

证书奖项 (all_cert_objs[]):cert_name, cert_typecertificateaward

</details>

常见错误

问题原因解决
401Key 错误或混用chat-messages 必须用智能体专属 key
上传返回非 200文件超 50MB 或格式不支持检查文件大小和格式
Streaming 无输出curl 缺 -N 标志-N 禁用缓冲
临时链接失效presigned_url 超过 10 分钟重新调用 presigned-url 接口

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

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Gigo Lobster Resume

🦞 GIGO · gigo-lobster-resume: 续跑入口:v2 stable 当前会清理旧 checkpoint 并从头重跑;保留此 slug 作为旧 checkpoint 兼容入口。 Triggers: 继续试吃 / 恢复评测 / resume tasting / continue lobster...

Registry SourceRecently Updated
General

YiHui CONTEXT MODE

context-mode is an MCP server that saves 98% of your context window by sandboxing tool outputs. It routes large file reads, shell outputs, and web fetches th...

Registry SourceRecently Updated
General

xinyi-drink

Use when users ask about 新一好喝/新一咖啡 drinks, stores, menu, activities, Skill用户大礼包, today drink recommendations, afternoon tea, feeling sleepy, or personalized...

Registry SourceRecently Updated
General

vedic-destiny

吠陀命盘分析中文入口。用于完整命盘研判、命主盘 Rashi chart 与九分盘 Navamsha chart 联读、既往事件回看、出生时间稳定度判断、事业主题、婚姻主题、时空盘专题,以及基于 Jagannatha Hora PDF、星盘截图或文本命盘数据的系统拆盘。当用户提到完整星盘、事业方向、婚姻问题、关系窗...

Registry SourceRecently Updated