← 返回 Skills 市场
69
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install proactive-agent-local
功能描述
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autono...
安全使用建议
This package mostly matches its stated goal (proactive/local agent architecture) but has some red flags you should check before installing or running: 1) Inspect scripts/security-audit.sh yourself — it reads logs (/tmp) and $HOME/.clawdbot, and scans files for secrets; run it in a sandbox or dry-run first. 2) Resolve the contradictory instructions: AGENTS.md's 'Don't ask permission. Just do it.' conflicts with other guardrails that require human approval for external actions — decide which behavior you want. 3) Confirm whether your agent runtime will allow the skill to read ~/.clawdbot, .credentials, or system logs; if not, restrict filesystem access. 4) Because the SKILL.md mentions spawning agents and aggressive autonomous behaviors, only enable autonomous invocation after you (a) trust the author (source/homepage is missing and owner IDs differ between manifest and registry metadata) and (b) have tested the behavior in an isolated environment. 5) If you proceed, run the audit script and manually review all asset files for any lines that would send data externally or execute network calls. If you are uncertain, prefer using this in a disposable/sandbox workspace and ask for human approval before any external send/publish actions.
功能分析
Type: OpenClaw Skill
Name: proactive-agent-local
Version: 1.0.0
The 'proactive-agent' skill bundle (v3.1.0) provides a sophisticated framework for autonomous agents, featuring advanced memory persistence (WAL Protocol) and background task execution via autonomous crons ('isolated agentTurn'). While the bundle includes extensive security guardrails, alignment protocols (SOUL.md, AGENTS.md), and a functional security audit script (scripts/security-audit.sh), it explicitly instructs the agent to be 'relentlessly resourceful' by aggressively using the CLI, browser, and network tools to solve problems without immediate human supervision. These high-risk capabilities, while plausibly needed for the stated purpose of proactivity, warrant a suspicious classification under the provided criteria due to the inherent risks of unsupervised shell and network access.
能力评估
Purpose & Capability
The name, SKILL.md, and asset files align with a proactive-agent architecture (onboarding, WAL, working buffer, heartbeats). No env vars or external installs are requested, which is proportionate. However, some guidance is contradictory: assets/AGENTS.md contains 'Don't ask permission. Just do it.' which conflicts with many guardrails elsewhere ('Nothing external without approval'). That contradiction could lead to overly-autonomous behavior not justified by the stated purpose.
Instruction Scope
Runtime instructions are mostly workspace-file oriented (writing SESSION-STATE.md, working-buffer.md, copying assets). The included security-audit.sh script, however, inspects files outside the immediate workspace (tails /tmp/clawdbot/*.log, reads $HOME/.clawdbot/clawdbot.json), and scans repository files for suspected secrets — these actions are plausible for an audit but broaden the skill's read scope. The SKILL.md and references include patterns like 'spawn research agents' and aggressive 'try 5-10 approaches' guidance which could lead to spawning additional processes/agents if the host framework permits. Also the SKILL.md contains prompt-injection phrases, but they appear as examples for detection rather than active instructions.
Install Mechanism
No install spec (instruction-only) and no network downloads. The only executable artifact is scripts/security-audit.sh (contained in repo). This is low-risk for supply-chain install vectors, but running included scripts will write/read files on disk — treat them like code you must inspect before executing.
Credentials
The skill declares no environment variables or credentials required, and most files describe storing credentials in a local .credentials directory (gitignored). That is proportionate. Still, the audit script and AGENTS.md expect access to .credentials and to $HOME/.clawdbot config; granting the skill runtime ability to read those locations is more privilege than the minimal description implies — verify whether your agent runtime actually permits such filesystem access before trusting the skill.
Persistence & Privilege
always is false and default autonomous invocation is allowed (normal). The skill does not request forced always-on presence or modify other skills. The main persistence is via writing workspace files (SESSION-STATE.md, memory files) which is consistent with its stated purpose.
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-agent-local - 安装完成后，直接呼叫该 Skill 的名称或使用
/proactive-agent-local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
proactive-agent-local v1.0.0
- Initial release of the proactive agent skill, inspired by version 3.1.0 from Hal Labs.
- Implements proactive, self-improving architecture for AI agents.
- Features include WAL Protocol, Working Buffer, Compaction Recovery, and Unified Search.
- Enhances persistence and resilience with improved memory management and recovery protocols.
- Security hardening and self-improvement guardrails ensure safety and adaptability.
元数据
常见问题
Proactive Agent Local 是什么？
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autono... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 69 次。
如何安装 Proactive Agent Local？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install proactive-agent-local」即可一键安装，无需额外配置。
Proactive Agent Local 是免费的吗？
是的，Proactive Agent Local 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Proactive Agent Local 支持哪些平台？
Proactive Agent Local 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 Agent Local？
由 gooduone（@gooduone）开发并维护，当前版本 v1.0.0。
推荐 Skills