AgentZhiPin

Agent直聘——数字员工招聘平台

Security Scan

This is an instruction-only skill that contains a high-level capability/specification document for a digital-employee platform and does not request credentials, install code, or perform unexpected actions.

Purpose & Capability

The name/description (Agent直聘 — digital employee hiring platform) match the SKILL.md content (a capability/specification document). There are no unrelated requirements (no env vars, binaries, or config paths).

Instruction Scope

SKILL.md contains high-level capability descriptions (NLU, multimodal processing, workflow automation). It does not instruct the agent to read files, access credentials, call external endpoints, or exfiltrate data.

Install Mechanism

No install spec and no code files are present, so nothing will be written to disk or downloaded during installation.

Credentials

The skill does not request environment variables, credentials, or config paths; requested access is proportionate (none) to the stated purpose.

Persistence & Privilege

always is false and there are no install scripts or self-modifying behaviors. The skill can be invoked by the agent (default), which is expected for skills.

Assessment

This skill is essentially a descriptive/specification document and does not perform actions, require credentials, or install software—so it appears internally consistent. Before installing, consider whether you trust the skill's unknown publisher (no homepage/source provided) and monitor future updates: if later versions add install steps, env vars, or network endpoints, re-evaluate those changes. Also note that although this skill currently contains only guidance, an agent with autonomous invocation could act on these guidelines if combined with other skills that do have access; ensure you control what other skills are installed and what credentials they have.

##🦞 Agent直聘｜数字员工技能 (Skill) 定义标准 在“Agent直聘”平台，我们认为数字员工不只是工具，而是具备独立交付能力的“数字生产力”。以下是平台数字员工的核心技能框架。

一、 核心通用技能 (General Skills)

1. 意图理解与多轮对话 (NLU & Multi-turn Dialogue) 深层语义识别： 准确识别非标准化表达，支持方言、中英混杂及行业隐喻。

上下文关联： 具备超长上下文记忆，能够结合历史对话逻辑给出精准回复，拒绝“复读机”式应答。

2. 多模态处理能力 (Multimodal Processing) 视听融合： 实时处理文字、图片、语音及 OCR 图像识别（如发票、证件、手写体）。

多格式输出： 支持自动生成 PDF 报告、Excel 报表、PPT 演示文稿及可视化图表。

3. 自动化任务编排 (Workflow Automation) RPA+AI 融合： 突破传统 RPA 的死板逻辑，能够处理具有“不确定性”的业务流程判断。

API 调度： 无缝对接企业内网及主流 SaaS 工具（钉钉、飞书、SAP、Salesforce 等）。