← 返回 Skills 市场
Output-Driven Dev
作者
amdf01-debug
· GitHub ↗
· v1.0.0
· MIT-0
143
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install sw-output-driven-dev
功能描述
Guides defining success criteria and verification before coding to ensure deliverables are proven complete through measurable, reproducible evidence.
安全使用建议
This skill is a benign, instruction-only template to help agents and humans define success criteria and verification steps. It doesn't request credentials or install anything. Practical considerations before installing: (1) verification steps may instruct the agent to run commands, access URLs, or read files — ensure the agent's runtime permissions and network access are appropriately limited so verification actions cannot access sensitive data or exfiltrate information; (2) review any concrete verification commands the agent intends to run before allowing autonomous invocation; (3) if you want to restrict automation, keep the skill user-invocable only or apply agent-level policies that require approval for actions that touch network, filesystem, or external services.
功能分析
Type: OpenClaw Skill
Name: sw-output-driven-dev
Version: 1.0.0
The skill bundle defines a methodology for 'Output-Driven Development' through markdown instructions in SKILL.md. It focuses on improving agent reliability by requiring success criteria and verification evidence before completing tasks. There is no executable code, network activity, or malicious prompt injection present.
能力评估
Purpose & Capability
Name/description (define success criteria and verification) align with the SKILL.md. There are no requested env vars, binaries, or installs that would be unrelated to its stated goal.
Instruction Scope
Runtime instructions are limited to defining outputs, writing verification steps, and documenting evidence. Example verification items mention running commands, opening URLs, and checking files as illustrative verification actions — which are appropriate for a verification template. The SKILL.md does not instruct reading unrelated system files, collecting secrets, or sending data to external endpoints outside normal verification activities.
Install Mechanism
No install spec and no code files — nothing is written to disk or downloaded. This is the lowest-risk model for a skill of this type.
Credentials
The skill declares no environment variables, credentials, or config paths. That is proportionate to an instruction-only checklist that only guides how to define and run verification.
Persistence & Privilege
always is false and the skill is user-invocable with normal autonomous-invocation allowed. That is expected for a helper skill; it does not request permanent presence or 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 sw-output-driven-dev - 安装完成后，直接呼叫该 Skill 的名称或使用
/sw-output-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
v1.0.0
Initial release
元数据
常见问题
Output-Driven Dev 是什么？
Guides defining success criteria and verification before coding to ensure deliverables are proven complete through measurable, reproducible evidence. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 143 次。
如何安装 Output-Driven Dev？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install sw-output-driven-dev」即可一键安装，无需额外配置。
Output-Driven Dev 是免费的吗？
是的，Output-Driven Dev 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Output-Driven Dev 支持哪些平台？
Output-Driven Dev 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 Output-Driven Dev？
由 amdf01-debug（@amdf01-debug）开发并维护，当前版本 v1.0.0。
推荐 Skills