← 返回 Skills 市场
84
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install proactive-trigger
功能描述
主动触发引擎v4：基于兴趣衰减、沉默检测、话题热度，决定何时进行主动干预。触发条件：用户沉默、兴趣衰减、主动干预时机成熟。
安全使用建议
What to check before installing:
- Understand where it writes: it stores state, signals and logs at ~/.openclaw/workspace/.soul (or /tmp fallback). If you want to limit exposure, run it in a sandbox or container and inspect that directory.
- Review the code paths that call external commands: openclaw-tool calls execSync with interpolated parameters. If an openclaw CLI is present, untrusted signal payloads could lead to shell injection. Consider removing/locking out the OpenClaw CLI or running with limited privileges.
- If you will run npm install, prefer doing so in an isolated environment and review package.json. The dependencies are standard (date-fns, commander, chalk) and there are no external download URLs.
- Audit where signals originate in your agent/system. If external/untrusted sources can create signals or payload fields, make sure to sanitize them or disable CLI invocation (check openclaw-tools.js callTool) before enabling automatic processing.
- Run the included tests (npm test) in a safe environment, inspect generated files, and consider setting processSignalsOnStartup=false in the config until you’re confident about behavior.
If you need, I can point to the exact lines that create the command-injection risk and suggest concrete code fixes (use child_process.spawn with argument array, or strictly validate/escape inputs).
能力评估
Purpose & Capability
Name/description match the code: it implements a proactive trigger/decision engine (topic heat, silence index, cooldowns, signal handling). It reasonably reads/writes local state and integrates with an optional 'openclaw' CLI; no unrelated cloud credentials or external services are requested.
Instruction Scope
SKILL.md is minimal (CLI invocation examples) and does not fully call out that the skill will read/write persistent state under ~/.openclaw/workspace/.soul, append logs and signal files, and may invoke an external CLI. The runtime code will process arbitrary 'signals' (payloads) and use those values when building commands for execSync, which could lead to command injection if inputs are malicious or untrusted.
Install Mechanism
No install spec provided (instruction-only in registry), but a package.json and package-lock.json are included — the module expects npm dependencies (date-fns, commander, chalk). There are no remote downloads or obscure URLs; typical npm install from registry is expected. The lack of an explicit install step in SKILL.md is a minor mismatch (user is advised in test script to run npm install).
Credentials
The skill requests no env vars or credentials. It does rely on process.env.HOME to determine workspace (defaults to /tmp if unset) and intentionally reads/writes files under ~/.openclaw/workspace/.soul and logs. That is proportional for a local stateful trigger engine, but users should be aware of the filesystem footprint and location.
Persistence & Privilege
The skill persists state and logs under the user's HOME and registers periodic behavior via config (processSignalsOnStartup, signalProcessingInterval). always:false (good). However, because it can execute the external 'openclaw' CLI via execSync and constructs shell commands by interpolating parameter values, combined with autonomous invocation allowed by the platform, there is a non-trivial blast radius if malicious inputs reach the CLI invocation path.
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 proactive-trigger - 安装完成后，直接呼叫该 Skill 的名称或使用
/proactive-trigger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
v0.4.0
proactive-trigger 0.4.0
- 更新组件描述，增加“主动干预时机成熟”为触发条件，突出v4特性
- 简化文档结构，突出直接命令调用和信号处理两种使用方式
- 优化命令说明和示例，增加全部参数形式展示
- 新增与proactive-engine信号系统集成说明
v0.3.1
- Added detailed usage instructions and command examples to SKILL.md.
- Documented trigger evaluation and signal processing commands.
- Clarified data storage locations for trigger-state and interest-graph.
- Updated description for proactive intervention triggers (interest decay, silence detection, topic heat).
v0.3.0
- Added detailed usage instructions for installation, commands, and signal processing in the new SKILL.md.
- Documented trigger conditions: user silence and interest decay.
- Included data storage locations for trigger state and interest graph.
- Provided command examples and a description table for main features.
v0.6.1
**Value-aware-guard system integrated into proactive-trigger skill as a major upgrade.**
- Added executable guard scripts for real-time value drift and boundary checks, with multi-level interventions.
- Introduced automatic signal publishing and handling for smoother collaboration with other skills.
- Provided detailed CLI and integration usage, including configuration, silent/temporary disable options, and troubleshooting.
- Enhanced documentation and quickstart guide for self-hosted, OpenClaw, or CLI use.
- Supports user-controlled sensitivity, boundaries, and intervention levels for flexible personal value protection.
元数据
常见问题
Proactive Trigger 是什么？
主动触发引擎v4：基于兴趣衰减、沉默检测、话题热度，决定何时进行主动干预。触发条件：用户沉默、兴趣衰减、主动干预时机成熟。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 84 次。
如何安装 Proactive Trigger？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install proactive-trigger」即可一键安装，无需额外配置。
Proactive Trigger 是免费的吗？
是的，Proactive Trigger 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Proactive Trigger 支持哪些平台？
Proactive Trigger 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 Proactive Trigger？
由 Louis Z.（@zhaoguoqiang-hub）开发并维护，当前版本 v0.4.0。
推荐 Skills