← 返回 Skills 市场
Ralph Loops
作者
qlifebot-coder
· GitHub ↗
· v1.0.2
5692
总下载
1
收藏
25
当前安装
3
版本数
在 OpenClaw 中安装
/install ralph-loops
功能描述
Runs autonomous iterative AI loops for requirements, planning, or building phases using structured prompts and fresh context per iteration.
安全使用建议
Install only in an isolated development workspace with a disposable branch and limited credentials. Review or disable automatic git push, avoid using --check-cmd with untrusted input, do not run the dashboard on a shared network, and expect the loop to edit files, run commands, consume API budget, and keep running until stopped.
功能分析
Type: OpenClaw Skill
Name: ralph-loops
Version: 1.0.2
This skill is classified as suspicious due to its reliance on `--dangerously-skip-permissions` for the Claude CLI, which grants the AI agent full system access, bypassing all built-in safeguards. Additionally, the `scripts/ralph-loop.mjs` script includes a `checkCmd` argument that allows arbitrary command execution via `execSync`, creating a direct command injection vector if the agent's arguments can be manipulated. The skill also instructs the agent to perform `git push` operations and use the `browser` tool to open URLs (e.g., `browser action=open targetUrl="http://localhost:PORT"`), which are powerful capabilities that, while intended for development, significantly increase the attack surface for prompt injection or misuse. These risky capabilities are present in `SKILL.md`, `scripts/ralph-loop.mjs`, `templates/loop.sh`, and `templates/PROMPT_build.md`.
能力评估
Purpose & Capability
The core purpose is coherent: iterative AI development loops with planning, building, commits, and a dashboard. The concern is that the capability is high-impact by design, including autonomous file edits, command execution, commits, automatic git push, background execution, and stop controls.
Instruction Scope
The safety section discloses that autonomous mode bypasses Claude permissions, but the quick-start/build examples do not consistently foreground that build loops may mutate files, run commands, commit, and push remotely. Some trigger-phrase instructions also move quickly from conversational intent to shell execution.
Install Mechanism
Setup asks users to install dashboard npm dependencies and a specific global Claude Code version. This is disclosed and has no hidden installer, but it changes the local toolchain and should be done in an isolated development environment.
Credentials
The skill runs from the user's workspace, stores loop state in /tmp, archives history under ~/clawd/logs, may use git/network via git push, and includes code for reading local Clawdbot transcripts. Those accesses are partly purpose-aligned but broad for sensitive projects.
Persistence & Privilege
Loops are intended to run autonomously in the background, and the dashboard exposes unauthenticated local API actions that can stop loops using pgrep/pkill pattern matching. The process/session termination behavior is not tightly scoped to tracked Ralph-owned PIDs.
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 ralph-loops - 安装完成后，直接呼叫该 Skill 的名称或使用
/ralph-loops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
v1.0.2
Added warning: don't block conversation while monitoring loops
v1.0.1
Added credits/attribution
v1.0.0
Initial release: autonomous building with Geoffrey Huntley methodology
元数据
常见问题
Ralph Loops 是什么？
Runs autonomous iterative AI loops for requirements, planning, or building phases using structured prompts and fresh context per iteration. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 5692 次。
如何安装 Ralph Loops？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ralph-loops」即可一键安装，无需额外配置。
Ralph Loops 是免费的吗？
是的，Ralph Loops 完全免费（开源免费），可自由下载、安装和使用。
Ralph Loops 支持哪些平台？
Ralph Loops 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 Ralph Loops？
由 qlifebot-coder（@qlifebot-coder）开发并维护，当前版本 v1.0.2。
推荐 Skills