← 返回 Skills 市场
Match Loop by John Perry
作者
rocketship4545-a11y
· GitHub ↗
· v1.0.0
· MIT-0
127
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install match-loop
功能描述
Two-agent iterative vibe-coding loop for OpenClaw. Use when the user wants one sub-agent to generate/build/code an app or artifact and a second analyst agent...
安全使用建议
This skill appears coherent for running a generator ↔ analyst visual QA loop. Before using it, be aware that the loop expects agents to: run project commands (install dependencies, start dev servers), open browsers and take screenshots, and potentially invoke OS-level UI automation (AppleScript/Hammerspoon/macbot) if needed. Those actions require filesystem, process, and UI automation privileges on the host and could execute code produced by the generator agent — which is normal for this workflow but carries the usual risk of running untrusted code. If you plan to allow autonomous runs, consider sandboxing the agent, restricting network access, or reviewing generated code before execution; do not provide secrets or credentials to the skill unless explicitly required and justified.
功能分析
Type: OpenClaw Skill
Name: match-loop
Version: 1.0.0
The `match-loop` skill defines an iterative workflow where one agent generates code and another performs visual QA. It explicitly instructs agents to execute shell commands (starting dev servers), automate browsers (Playwright), and use desktop control tools (macbot, Hammerspoon, AppleScript) as described in `SKILL.md` and `references/loop-patterns.md`. While these high-risk capabilities are aligned with the stated purpose of "vibe-coding" and UI refinement, they involve the execution of and interaction with potentially untrusted, auto-generated code, which poses an inherent security risk without evidence of intentional malice.
能力评估
Purpose & Capability
Name/description (generator + visual analyst loop) align with the SKILL.md instructions: the skill only asks agents to build, preview, inspect, and iterate on frontend artifacts. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
The SKILL.md explicitly instructs agents to run dev servers, open apps in a browser, take screenshots, and (if necessary) escalate to desktop automation tools like AppleScript/Hammerspoon/macbot. This stays within the declared purpose but implies the agent will need filesystem, process, and UI automation access at runtime — the user should be aware the agent may install/run project dependencies and spawn browsers or automation tools.
Install Mechanism
There is no install spec and no code files; the skill is instruction-only so nothing is written to disk by the skill itself. Any installs would be performed by the generator actor as part of running a project (e.g., npm/yarn) — which is expected for this use case.
Credentials
The skill declares no environment variables, credentials, or config paths. The runtime instructions do not request secrets or unrelated credentials. This is proportionate to a local dev/visual QA loop.
Persistence & Privilege
always is false and autonomous invocation is allowed (platform default). The skill does not ask for permanent presence or 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 match-loop - 安装完成后，直接呼叫该 Skill 的名称或使用
/match-loop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 of the match-loop skill.
- Enables an iterative generator ↔ analyst loop for building and refining apps, with concrete feedback cycles.
- Unique analyst role: visually inspects the frontend in a browser, not just code review, and reports UI/UX defects.
- Designed for tasks where visual/functional accuracy matters, such as web apps or landing pages.
- Workflow continues until all major visual and functional issues are resolved or user stops the loop.
- Final output summarizes rounds, checks performed, and key improvements.
元数据
常见问题
Match Loop by John Perry 是什么？
Two-agent iterative vibe-coding loop for OpenClaw. Use when the user wants one sub-agent to generate/build/code an app or artifact and a second analyst agent... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 127 次。
如何安装 Match Loop by John Perry？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install match-loop」即可一键安装，无需额外配置。
Match Loop by John Perry 是免费的吗？
是的，Match Loop by John Perry 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Match Loop by John Perry 支持哪些平台？
Match Loop by John Perry 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 Match Loop by John Perry？
由 rocketship4545-a11y（@rocketship4545-a11y）开发并维护，当前版本 v1.0.0。
推荐 Skills