← 返回 Skills 市场
shangyankeji

Super Dev Pipeline

作者 SYHUB · GitHub ↗ · v2.3.0 · MIT-0
cross-platform ⚠ suspicious
313
总下载
1
收藏
1
当前安装
3
版本数
在 OpenClaw 中安装
/install super-dev
功能描述
Super Dev pipeline governance: research-first, commercial-grade AI coding delivery with 10 expert roles, quality gates, and audit artifacts.
安全使用建议
This skill appears internally consistent for a local dev pipeline: it expects a local 'super-dev' CLI and operates on project files and outputs. Before installing or enabling it, do the following: (1) Verify the source and authenticity of the 'super-dev' package (inspect the PyPI/package repo, check maintainer and release history). (2) Review what the installed super-dev binary and the @super-dev OpenClaw plugin actually do (read their code or run in a sandbox) because the Skill grants the agent the ability to run CLI commands and access project files. (3) Avoid placing secrets or cloud credentials in knowledge/ or output/ directories the skill will read. (4) Consider running the package in an isolated environment (container or VM) first. If you cannot inspect the super-dev package or plugin source, treat activation as higher risk.
功能分析
Type: OpenClaw Skill Name: super-dev Version: 2.3.0 The skill bundle defines a comprehensive AI development pipeline but includes a high-risk tool, `super_dev_run`, which is described in `SKILL.md` as allowing the execution of arbitrary CLI commands. While the documentation in `references/commands.md` suggests this is intended for specific pipeline stages (e.g., `super-dev run frontend`), the unconstrained tool definition creates a significant Remote Code Execution (RCE) vulnerability. No clear evidence of intentional malice or data exfiltration was observed, but the broad execution capability is a major security concern.
能力评估
Purpose & Capability
Name/description, declared required binary (super-dev), the listed Tools and the SKILL.md all describe a dev pipeline/governance system and consistently require a local super-dev CLI. Reading project knowledge files and producing output docs is coherent with the stated purpose.
Instruction Scope
Instructions mandate reading local project knowledge (knowledge/, output/*, .super-dev state files) and enforce quality gates and manual confirmation — all reasonable for a pipeline. The skill (and its Tools) also allow running arbitrary CLI commands via super_dev_run, and the agent is expected to perform network research when not offline. That broad host-level capability is consistent with a dev tool but increases risk if the underlying CLI or plugin is malicious or misconfigured.
Install Mechanism
Install spec points to a package install (labelled 'pip install super-dev') rather than an arbitrary download; this is more traceable than a direct URL but still involves installing third‑party code from a package registry (moderate risk). No suspicious download URLs or archive extracts are present in the spec.
Credentials
The skill declares no required environment variables, credentials, or config paths beyond needing the super-dev binary. The files and instructions reference only project-local paths, which are proportionate to a pipeline/governance tool.
Persistence & Privilege
always:false and normal model invocation mean the skill is not force-included and does not request elevated platform privileges. It does instruct installing a plugin and using the local CLI, which is normal for this class of tool and confined to its own scope.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install super-dev
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /super-dev 触发
  4. 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
v2.3.0
No user-visible changes in this version (2.2.1); the SKILL.md remains unchanged.
v2.2.0
- Updated documentation to clarify separation between Plugin and Skill roles, emphasizing Plugin Tool orchestration via OpenClaw. - Stronger and clearer knowledge base contract: each pipeline stage must load and enforce relevant knowledge files and cache, with explicit mappings and constraints. - Step-by-step pipeline now described via Tool calls (e.g. super_dev_pipeline, super_dev_review, super_dev_spec) rather than CLI commands. - Revised first-response template; startup flow, confirmation gates, and recovery instructions streamlined for simpler user guidance. - Strict UI governance and return-workflow rules now summarized in clear tables, including prohibited patterns and recovery actions. - All references to numbered CLI stages and in-depth stage-by-stage descriptions have been simplified in favor of concise, actionable Tool-based workflow.
v1.0.0
super-dev 1.0.0 – Initial release - Introduces a comprehensive AI DevOps pipeline with 10 expert roles and 9 sequential stages, including quality gates and audit artifacts. - Enforces strict workflows: research, three core docs, user confirmation, spec/tasks, frontend-first, then backend/testing/delivery. - Mandates explicit user confirmation gates before proceeding at key stages (core docs, frontend preview, quality review). - Integrates local knowledge as strict constraints for every pipeline step. - Provides detailed user guidance and standard templates for every phase, including how to respond, resume, or revise. - Supports flexible recovery, stage-specific execution, and enforceable rework protocols based on user or quality feedback.
元数据
Slug super-dev
版本 2.3.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 3
常见问题

Super Dev Pipeline 是什么?

Super Dev pipeline governance: research-first, commercial-grade AI coding delivery with 10 expert roles, quality gates, and audit artifacts. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 313 次。

如何安装 Super Dev Pipeline?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install super-dev」即可一键安装,无需额外配置。

Super Dev Pipeline 是免费的吗?

是的,Super Dev Pipeline 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Super Dev Pipeline 支持哪些平台?

Super Dev 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 Super Dev Pipeline?

由 SYHUB(@shangyankeji)开发并维护,当前版本 v2.3.0。

💬 留言讨论