← 返回 Skills 市场
78
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install nerua1-ralph
功能描述
Persistence loop until task completion with verification - "don't stop until it's done
安全使用建议
This skill implements what it claims (a persistence loop that verifies completion) but there are several issues to consider before installing:
- Inconsistencies to check: README path (~/.claude/...) differs from SKILL.md (~/.openclaw/...). Confirm the intended install location and ownership before cloning or running scripts.
- Ambiguous agent interactions: the script references delegating to other agents and invokes an unexplained '/cancel' command. Ask the author what those do and how they interact with your agent runtime.
- File system and command execution: Ralph will create state under your home directory and run project commands (npm test/build, grep across your working tree). npm scripts can execute arbitrary code from the repository — run only in projects you trust or within an isolated environment.
- Long-running loops: the skill can iterate repeatedly (up to 10 times) performing builds/tests. Consider resource/time limits or running it in a sandbox (container/CI runner) rather than directly on your workstation.
- Source verification: the registry metadata lacks a verified homepage/source. If you plan to use it, inspect the GitHub repository the README points to (and review the full script) before cloning. Prefer running the script manually in a safe environment first.
If you need this capability, proceed after: verifying the repository, adjusting/confirming the install paths, running the script in an isolated sandbox the first time, and confirming the meaning and safety of the '/cancel' and 'delegate' behaviors.
功能分析
Type: OpenClaw Skill
Name: nerua1-ralph
Version: 1.0.0
The 'ralph' skill is a persistence wrapper designed to ensure task completion through iterative verification (up to 10 attempts). It uses standard Bash scripting in SKILL.md to monitor project state, run tests (npm test), and check builds (npm run build). No evidence of data exfiltration, unauthorized persistence, or malicious prompt injection was found; the logic is transparent and includes safety limits (MAX_ITERATIONS) and user-override conditions ('cancel' or 'stop').
能力评估
Purpose & Capability
Name/description match the implementation: a persistence loop that saves state and runs verification steps. However there are small incoherences: README suggests a clone path under ~/.claude/skills/... while the SKILL.md uses ~/.openclaw/... — inconsistent install locations/names. README also advertises a GitHub repo for install but the registry reported 'Source: unknown' and no homepage. These discrepancies suggest sloppy packaging or incomplete metadata.
Instruction Scope
The instructions and example script instruct the agent to read/write state under the user's home (~/.openclaw/state/ralph), run commands in the workspace (grep across files), and execute npm test/build if package.json exists. The skill also speaks of 'delegat[ing] to appropriate agents' and 'run long ops in background' — vague instructions that give the agent wide discretion. The script calls a '/cancel' command (unexplained) which may be an action intended to interact with the agent runtime; its behavior is ambiguous. These behaviors are coherent with a developer automation tool but broaden the agent's access to the filesystem and to executing arbitrary project scripts (npm scripts can run arbitrary code).
Install Mechanism
This is an instruction-only skill with no install spec or bundled binaries, which is low risk from install mechanics. README suggests cloning a GitHub repo (a normal pattern). No third-party downloads or extract steps are present in the registry metadata.
Credentials
The skill declares no required environment variables or credentials. Its requested access (read/write under the user's home and running local build/test commands) is proportionate to a tool that verifies builds/tests in a project. However, lack of declared requirements means the agent will rely on existing system tooling (npm, grep) which may execute project-provided code.
Persistence & Privilege
The skill writes persistent state to ~/.openclaw/state/ralph and suggests creating a script under ~/.openclaw/skills/ralph/ralph.sh (and README suggests an alternate path). always:false (not force-included) so it won't be auto-enabled for all agents, which is appropriate. Still, it will create files under the user's home and may run repeated long-running operations up to 10 iterations; users should be aware of disk/CPU/network implications.
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 nerua1-ralph - 安装完成后，直接呼叫该 Skill 的名称或使用
/nerua1-ralph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
Ralph skill v1.0.0 — Initial Release
- Introduces a "persistence loop" that keeps working on a task until fully complete and verified
- Implements multi-step verification: checks tests, build, TODOs, and quality before completion
- Caps at 10 iterations per task, with fresh evidence and state recorded for each attempt
- Provides clean exit on success, or marks as needs help if maximum iterations reached
- Includes clear guidelines for usage, example commands, integration instructions, and stop conditions
元数据
常见问题
Ralph 是什么？
Persistence loop until task completion with verification - "don't stop until it's done. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 78 次。
如何安装 Ralph？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nerua1-ralph」即可一键安装，无需额外配置。
Ralph 是免费的吗？
是的，Ralph 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Ralph 支持哪些平台？
Ralph 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？
由 nerua1（@nerua1）开发并维护，当前版本 v1.0.0。
推荐 Skills