← 返回 Skills 市场

Coze 工作流执行 / Coze Workflow

Name: Coze 工作流执行 / Coze Workflow
Author: noah-1106

作者 noah · GitHub ↗ · v1.1.4 · MIT-0

cross-platform ⚠ suspicious

564

总下载

当前安装

版本数

在 OpenClaw 中安装

/install coze-workflow

功能描述

Coze Workflow Executor | Coze 工作流执行技能 Execute Coze workflows with workflow_id and parameters. 接收参数调用工作流，返回执行结果。 Pure invocation layer with no business logic....

使用说明 (SKILL.md)

Coze Workflow | Coze 工作流执行技能

纯净的调用层技能。接收 workflow_id 和 parameters，执行工作流，返回结果。这是其他 Coze 工作流技能依赖的基础技能。

Pure invocation layer skill. Receives workflow_id and parameters, executes the workflow, and returns results. This is the base skill that other Coze workflow skills depend on.

依赖关系 / Dependencies

本技能被以下技能依赖 / This skill is a dependency for：

image-gen-coze - 图像生成 / Image generation via Coze workflows
其他自定义 Coze 工作流技能 / Other custom Coze workflow skills

配置 / Configuration

~/.openclaw/skills/coze_workflow/config.json：

{
  "api_key": "pat_xxx",
  "base_url": "https://api.coze.cn"
}

职责边界 / Responsibility Boundaries

职责 / Responsibility	coze_workflow	业务技能 / Business Skill
执行工作流 / Execute workflow	✅	❌
参数构建 / Parameter building	❌	✅
结果解析 / Result parsing	❌	✅

调用方式 / Usage

输入 / Input

{
  "workflow_id": "string",
  "parameters": {}  // 任意 JSON / Any JSON
}

输出 / Output

返回 Coze API 的原始响应 / Returns Coze API raw response：

{
  "execute_id": "string",
  "status": "Success|Fail|Running",
  "output": "string",  // 工作流输出（JSON字符串）/ Workflow output (JSON string)
  "debug_url": "string"
}

执行方法 / Execution Methods

方法 1：流式执行（推荐）/ Method 1: Stream (Recommended)

curl -X POST "${COZE_BASE_URL}/v1/workflow/stream_run" \
  -H "Authorization: Bearer ${COZE_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "workflow_id": "xxx",
    "parameters": {...}
  }'

响应 / Response：SSE 流，提取 event: Message 的 data.content 字段

方法 2：轮询查询 / Method 2: Polling

curl "${COZE_BASE_URL}/v1/workflows/{workflow_id}/run_histories/{execute_id}" \
  -H "Authorization: Bearer ${COZE_API_KEY}"

版本历史 / Changelog

v1.1.3: 添加中英文对照 / Add bilingual support
v1.1.1: 明确职责边界 / Clarify responsibility boundaries
v1.1.0: 流式执行 + 轮询 / Stream + Polling
v1.0.0: 初始版本 / Initial version

安全使用建议

This skill appears to do what it says (invoke Coze workflows), but its metadata and instructions disagree about where and how the API key and base_url are provided. Before installing: (1) confirm how the agent will supply the Coze API key — prefer platform secret storage or declared environment variables rather than plaintext ~/.openclaw config files; (2) ask the publisher to update registry metadata to declare required env vars/config paths (COZE_API_KEY / COZE_BASE_URL or config path) so permissions are explicit; (3) verify network destination is the official https://api.coze.cn domain and not an unexpected endpoint; (4) avoid placing long-lived credentials in unencrypted skill config; (5) if you do not trust the publisher, do not provide secrets — test with a throwaway key first. The inconsistencies are not proof of malicious intent, but they reduce transparency and increase risk.

功能分析

Type: OpenClaw Skill Name: coze-workflow Version: 1.1.4 The skill is a standard integration layer for executing Coze workflows via the official Coze API (api.coze.cn). The documentation in SKILL.md and the configuration in config.json are purely functional, providing instructions for API interaction without any evidence of malicious intent, data exfiltration, or prompt injection.

能力评估

⚠ Purpose & Capability

The declared purpose (invoke Coze workflows) matches the instructions (curl POST to Coze endpoints). However the registry metadata lists no required credentials or config paths, while SKILL.md and the included config.json clearly expect an API key and a base_url — a mismatch between declared requirements and actual needs.

⚠ Instruction Scope

SKILL.md instructs the agent to read a config at ~/.openclaw/skills/coze_workflow/config.json and/or use environment vars (COZE_API_KEY, COZE_BASE_URL) and to perform network calls to api.coze.cn (SSE or polling). These actions are within the stated purpose, but SKILL.md references local config and env vars that were not declared in the skill metadata, and the bundled config.json sets base_url to a full stream_run URL (inconsistent with examples).

✓ Install Mechanism

No install spec and no code files — instruction-only. This is low-risk from an installation perspective (nothing is downloaded or executed beyond the agent following curl instructions).

⚠ Credentials

The skill logically needs one secret (Coze API key) and a base URL, but the registry lists no required env vars or primary credential. The included config.json contains an api_key field (placeholder) and a base_url pointing directly at a stream endpoint; requiring secrets but not declaring them in metadata is disproportionate/incoherent. Also storing API keys in plaintext config is risky.

ℹ Persistence & Privilege

always:false and no install means the skill won't force permanent inclusion. It does expect a config file under ~/.openclaw/skills/coze_workflow/, which is a normal place for skill config but was not declared in the metadata; there is no indication it modifies other skills or system-wide configs.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install coze-workflow
安装完成后，直接呼叫该 Skill 的名称或使用 /coze-workflow 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.1.4

Add bilingual documentation support

v1.1.3

Added dependency documentation | 添加依赖关系说明

v1.1.2

Bilingual description: English + 中文

v1.1.1

通用Coze工作流调用技能，纯净调用层设计，支持流式执行和轮询查询

元数据

Slug coze-workflow

版本 1.1.4

许可证 MIT-0

累计安装 5

当前安装数 5

历史版本数 4

常见问题