← 返回 Skills 市场
Multi Agent Pipeline
作者
Nissan Dookeran
· GitHub ↗
· v1.0.1
· MIT-0
367
总下载
0
收藏
2
当前安装
2
版本数
在 OpenClaw 中安装
/install multi-agent-pipeline
功能描述
Generic multi-agent content pipeline — sequential and parallel agent stages with status tracking, error recovery, and progress callbacks. Use when building m...
安全使用建议
This package contains runnable API routes that call external LLM/TTS/STT services and write to a database, but its metadata omits the required API keys and says outbound networking is disabled. Before installing: (1) do not provide ELEVENLABS_API_KEY or MISTRAL_API_KEY to unknown code without review — confirm why those keys are needed; (2) ask the publisher for an explicit manifest listing required env vars and Python dependencies; (3) inspect the database and prompt_cache modules referenced (they could read/write broader data); (4) run in an isolated environment or container and limit keys to least privilege / scoped test keys; (5) consider requiring the skill author to remove or clearly document concrete external calls if you only wanted a framework. The mismatch between declared metadata and actual code is the primary reason to treat this as suspicious.
功能分析
Type: OpenClaw Skill
Name: multi-agent-pipeline
Version: 1.0.1
The skill implements a multi-agent story generation pipeline using FastAPI, Mistral, and ElevenLabs APIs. The code in `scripts/pipeline.py` handles audio transcription, story generation, and text-to-speech narration, using environment variables for API keys and parameter-binding for database queries. While the `SKILL.md` metadata incorrectly flags outbound network access as false, the documentation and code explicitly describe and implement these external API calls for their stated purpose, and no evidence of malicious intent or data exfiltration was found.
能力评估
Purpose & Capability
The SKILL.md describes a generic pipeline framework, but the shipped Python implements concrete HTTP endpoints that call external services (ElevenLabs and Mistral) and persists data to a DB. The metadata claims no required env vars and network outbound is false, yet the code requires ELEVENLABS_API_KEY and MISTRAL_API_KEY and performs external requests. That mismatch is disproportionate to the stated 'framework-only' purpose.
Instruction Scope
SKILL.md examples are framework-level, but the code contains full FastAPI routes that read UploadFile, call external STT/TTS/LLM endpoints, and read/write a database and prompt_cache. The instructions/metadata do not call out these concrete behaviors (file uploads, DB writes, external endpoints), giving the agent broader runtime scope than documented.
Install Mechanism
No install spec is provided (instruction-only), but the bundle includes code that depends on third-party packages (httpx, fastapi, pydantic, mistralai, prompt_cache, database). Lack of an install spec means dependencies and their provenance are unspecified, increasing operational risk though not necessarily malicious.
Credentials
Declared requirements list no env vars, yet the code reads ELEVENLABS_API_KEY and MISTRAL_API_KEY from environment and raises errors when missing. These unnamed secrets are required for live behavior and are central to the skill's network activity — they should be declared and justified in metadata.
Persistence & Privilege
The skill does not request always:true and is user-invocable. It persists intermediate results to a database and caches audio/images; that is consistent with a pipeline but means installing this skill will give it access to any DB backend the agent exposes. Autonomous invocation plus undeclared secret use increases blast radius — verify deployment isolation and secret scope before enabling.
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 multi-agent-pipeline - 安装完成后，直接呼叫该 Skill 的名称或使用
/multi-agent-pipeline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
v1.0.1
- Added a dedicated "security_notes" field to metadata clarifying patterns that may trigger automated security scanners.
- Updated skill version to 1.0.1.
- No changes to the core pipeline logic or behavior.
v1.0.0
- Initial release of multi-agent-pipeline skill.
- Provides a reusable framework for building multi-step AI workflows with sequential and parallel agent stages.
- Supports robust status tracking, error recovery, and real-time progress callbacks.
- Integrates easily with any LLM provider; actual API calls depend on your stage functions.
- Features caching support (with prompt-cache skill) and handles various workflow patterns such as generate-validate-transform-deliver.
- Designed for production-grade scenarios, including parallel concurrency and safe error handling.
元数据
常见问题
Multi Agent Pipeline 是什么？
Generic multi-agent content pipeline — sequential and parallel agent stages with status tracking, error recovery, and progress callbacks. Use when building m... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 367 次。
如何安装 Multi Agent Pipeline？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install multi-agent-pipeline」即可一键安装，无需额外配置。
Multi Agent Pipeline 是免费的吗？
是的，Multi Agent Pipeline 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Multi Agent Pipeline 支持哪些平台？
Multi Agent Pipeline 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Multi Agent Pipeline？
由 Nissan Dookeran（@nissan）开发并维护，当前版本 v1.0.1。
推荐 Skills