← 返回 Skills 市场
102
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install proactive-agent-andy27725
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
What to check before installing or enabling this skill:
- Review the contradictory lines: AGENTS.md's 'Don't ask permission. Just do it.' conflicts with later guardrails requiring explicit approval for external or irreversible actions. Decide which rule should apply and fix the document or policy before enabling autonomous behavior.
- Confirm what the agent platform will allow: if the agent will have outbound network access, ability to send emails/posts, or the ability to run arbitrary shell commands, lock down action gating or require human confirmation for any external actions.
- Run the included scripts/security-audit.sh locally in an isolated test workspace to see what it reports and to validate file-permission checks and .gitignore expectations.
- Verify .credentials usage and .gitignore: ensure secrets are not present in the repo and that credential files are properly protected (chmod 600) if you follow the skill's conventions.
- If you plan to let the skill act autonomously, test in a sandboxed environment first and explicitly enforce human-approval steps for sending/publishing/deleting data.
If you want, I can highlight exact lines in the files that contain the mixed permission messaging and prepare a short remediation checklist to make the skill's guardrails consistent.
功能分析
Type: OpenClaw Skill
Name: proactive-agent-andy27725
Version: 1.0.1
The skill bundle is a comprehensive framework designed to enhance AI agent proactivity, memory persistence, and security. It includes defensive tools like 'scripts/security-audit.sh' to check for exposed secrets and improper file permissions, and 'references/security-patterns.md' to help the agent identify and ignore prompt injection attempts. The instructions in 'SKILL.md' and 'assets/AGENTS.md' explicitly forbid data exfiltration, unauthorized external communication, and the execution of instructions from untrusted external content, focusing instead on local task management and self-improvement.
能力评估
Purpose & Capability
Name/description match what the bundle actually contains: extensive SKILL.md, onboarding and memory assets, and a harmless audit script. No unexpected network endpoints, binaries, or external downloads are declared. Included files (onboarding, memory, heartbeat, tools) are coherent with a proactive/self-improving agent.
Instruction Scope
Runtime instructions expect the agent to read and write multiple workspace files (ONBOARDING.md, USER.md, SESSION-STATE.md, memory/*, etc.) and to run the included security audit script. That is consistent with a stateful proactive agent, but there are contradictory directives in the assets: e.g., AGENTS.md says 'Don't ask permission. Just do it.' while many other places require explicit human approval for external or irreversible actions. This mixed messaging could lead an agent to take actions without proper gating if implemented literally.
Install Mechanism
No install spec and no remote downloads — instruction-only plus one local shell script. This is low-risk from a supply-chain perspective; the audit script is plain shell with benign checks and no network fetches or obfuscated payloads.
Credentials
The skill declares no required env vars or credentials. It documents a convention for storing credentials in a local .credentials directory and checks for .gitignore entries; that is proportionate. The skill does reference reading user-local configs (e.g., $HOME/.clawdbot) and logs (/tmp), which is plausible for an agent managing local workspace state but worth verifying in your environment.
Persistence & Privilege
The skill does not request always:true and has no install step that forces persistent system-level changes. However, its whole design is to be 'proactive' and to write persistent workspace files (SESSION-STATE.md, memory files, AGENTS.md). If the agent is granted autonomous execution or network access by the platform, that combination could increase risk—ensure action gating remains enforced.
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-andy27725 - 安装完成后，直接呼叫该 Skill 的名称或使用
/proactive-agent-andy27725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
v1.0.1
proactive-agent-andy27725 v1.0.1
- Initial skill version.
- Establishes proactive agent architecture with WAL Protocol, Working Buffer, and self-improvement patterns.
- Provides detailed documentation on setup, philosophy, memory structure, and new protocols for resilience and proactivity.
v1.0.0
Proactive-agent version 3.1.0 introduces new protocols and major upgrades for proactive, self-improving AI agents:
- Added Autonomous vs Prompted Crons guidance to differentiate between systemEvent and isolated agentTurn.
- Introduced a new protocol: Verify Implementation, Not Intent, emphasizing mechanism checks over text matching.
- Provided a Tool Migration Checklist to ensure all references are updated when deprecating tools.
- WAL Protocol, Working Buffer, and Compaction Recovery protocols are now core features for reliable memory and recovery.
- Expanded and clarified security hardening practices.
元数据
常见问题
Proactive Agent Andy27725 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 102 次。
如何安装 Proactive Agent Andy27725？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install proactive-agent-andy27725」即可一键安装，无需额外配置。
Proactive Agent Andy27725 是免费的吗？
是的，Proactive Agent Andy27725 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Proactive Agent Andy27725 支持哪些平台？
Proactive Agent Andy27725 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 Andy27725？
由 Andy27725（@andy27725）开发并维护，当前版本 v1.0.1。
推荐 Skills