← 返回 Skills 市场
Subagent-Driven Development
作者
user-wangjun
· GitHub ↗
· v1.0.1
· MIT-0
93
总下载
1
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install subagent-driven-dev
功能描述
Use when executing implementation plans with independent tasks in the current session
安全使用建议
This skill is an orchestration template for spawning implementer/spec/quality-review subagents and expects access to your repo and developer tools, but it doesn't explicitly declare those permissions. Before installing or using it: 1) Confirm what 'superpowers' and 'TodoWrite' integrations are and whether they require tokens or network endpoints; don't grant unknown tokens. 2) Run it first in an isolated/test workspace (or sandbox) so subagents only see non-sensitive files. 3) Ensure the agent runtime only has the minimum filesystem and git permissions needed (least privilege) and that commits/actions are audited. 4) Review the prompt templates to ensure they don't instruct subagents to leak session context or secrets (search for commands that send data to external URLs). 5) Ask the publisher for clarification about required permissions and expected external connectors; if they can't justify missing env/config declarations, treat the skill with extra caution.
功能分析
Type: OpenClaw Skill
Name: subagent-driven-dev
Version: 1.0.1
The skill bundle defines a structured workflow for 'Subagent-Driven Development,' focusing on task implementation followed by automated specification and code quality reviews. The provided markdown files (SKILL.md, implementer-prompt.md, spec-reviewer-prompt.md, and code-quality-reviewer-prompt.md) contain logic for managing subagent lifecycles, quality gates, and escalation protocols. There is no evidence of data exfiltration, malicious execution, or harmful prompt injection; all instructions are strictly aligned with the stated purpose of improving development efficiency and code quality.
能力评估
Purpose & Capability
Name/description match the instructions: the skill orchestrates fresh subagents per task with spec + quality reviews. However, the runtime behavior implies read/write access to the repository (read plans, read/write code, run tests, commit, obtain git SHAs) and potentially external integrations (TodoWrite, 'superpowers' tools) but the skill declares no required binaries, env vars, or config paths. The lack of stated required permissions is a design omission that should be clarified.
Instruction Scope
SKILL.md instructs agents to read plan files and project files, implement code, run tests, commit, inspect code line-by-line, and mark tasks complete in TodoWrite — all within-scope for a dev orchestration skill. However: (1) prompts explicitly tell implementer subagents to paste 'FULL TEXT' instead of reading files while examples show reading a plan file — inconsistent guidance; (2) the workflow grants broad access to repository contents and commit history and to any context provided to subagents, which can expose secrets or unrelated sensitive files if not confined; (3) the skill references external tools (superpowers:code-reviewer, TodoWrite, etc.) without describing where those endpoints live or what credentials they need.
Install Mechanism
Instruction-only skill with no install spec and no code files. This is low-risk from an installation/code distribution perspective because nothing is downloaded or written by an installer.
Credentials
The skill declares no required environment variables or credentials, yet its intended actions imply the need for: repository write access (git), possibly CI/test runners, and credentials for external services (TodoWrite, 'superpowers' tools). The omission means callers might need to grant broad runtime permissions implicitly; any unspecified external connectors or tokens are a risk because they could be used to exfiltrate data or make changes without explicit declaration.
Persistence & Privilege
always:false and user-invocable:true — normal and appropriate. The skill does instruct autonomous dispatch of subagents, but autonomous invocation is platform-default. There is no evidence the skill attempts to modify other skills or system-wide settings.
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 subagent-driven-dev - 安装完成后，直接呼叫该 Skill 的名称或使用
/subagent-driven-dev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
subagent-driven-dev 1.0.1
- No file changes detected in this release.
- Documentation, workflow, and process remain the same as previous version.
- No new features, fixes, or updates introduced.
v1.0.0
subagent-skill 1.0.0
- Initial release of the Subagent-Driven Development methodology.
- Introduces a two-stage review process (spec compliance first, then code quality) with a fresh subagent handling each task.
- Designed for use when executing implementation plans with mostly independent tasks in the same session.
- Includes detailed dot diagrams illustrating both when to use and the per-task workflow.
- Provides example workflows, advantages over manual and parallel plan execution, and outlines efficiency gains and review gates.
- Documents usage of three key prompt templates for implementer, spec reviewer, and code quality reviewer subagents.
元数据
常见问题
Subagent-Driven Development 是什么？
Use when executing implementation plans with independent tasks in the current session. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 93 次。
如何安装 Subagent-Driven Development？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install subagent-driven-dev」即可一键安装，无需额外配置。
Subagent-Driven Development 是免费的吗？
是的，Subagent-Driven Development 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Subagent-Driven Development 支持哪些平台？
Subagent-Driven Development 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 Subagent-Driven Development？
由 user-wangjun（@user-wangjun）开发并维护，当前版本 v1.0.1。
推荐 Skills