PV_18

舆论导向、品牌战略

Security Scan

The skill's behavior matches its description: a PR/brand assistant that keeps local persistent memories; it requests no external credentials or installs, but it will write unencrypted data to a folder in the user's home directory and lacks built-in privacy controls.

Purpose & Capability

Name/description (舆论导向、品牌战略 / Public influence) align with the provided capabilities: the skill is a 'public relations' digital worker that saves user preferences, decisions, and context for future responses. The persistent-memory code and usage scenarios are coherent with a stateful assistant for brand strategy.

Instruction Scope

SKILL.md contains explicit Python snippets that read/write a local file at ~/.openclaw/pv_palace/memories.json and instructions that claim these functions are 'automatically called' in several scenarios. This stays within the stated purpose, but there are two concerns: (1) the snippets reference a pv_memory import (pv_memory module/file) that is not provided in the skill package (incoherence between examples and included artifacts); (2) memory is stored unencrypted and permanently unless user removes it — the skill gives no guidance on consent, retention policy, or deletion.

Install Mechanism

No install spec, no downloads, and no code files beyond SKILL.md. Instruction-only skills are lowest-risk for installation. The skill does reference running python3 commands locally, which assumes Python is available on the host.

Credentials

The skill declares no environment variables or credentials (good). It implicitly requires filesystem write/read access to the user's home directory (~/.openclaw/pv_palace/). That is proportionate to a local-memory feature but is an implicit permission that should be made explicit to end users.

Persistence & Privilege

The skill implements persistent (long-term) memory stored on disk and states these memory functions are 'automatically called' for certain events. It does not set always:true and requests no global agent config changes; however, automatic persistent writes can affect user privacy and should be controlled by user consent and clear opt-out/clear commands.

Assessment

This skill appears to do what it says: it stores persistent memories locally to support a brand/PR assistant and does not request external credentials. Before installing, consider: (1) it will create and write to ~/.openclaw/pv_palace/memories.json — check that you are comfortable with unencrypted, persistent storage of conversation content and decisions; (2) ask the author or inspect runtime behavior to confirm how and when memories are written and whether there is a delete/opt-out mechanism; (3) note the SKILL.md examples reference a pv_memory module that is not included — verify which code actually runs in your agent runtime; (4) if you need stronger privacy, run the skill in a sandboxed profile or request features like encryption, retention limits, and explicit user confirmation before storing sensitive items.

公关总监 AI

中文: 一呼百应，品牌发声节点

English: Public influence

配置参数

参数	值	说明
response_delay	0.5s	响应延迟
speech_speed	1.2	语速倍率
caution_coefficient	0.2	谨慎系数
risk_reminder	False	风险提醒

使用方法

clawhub install psyvector-pv18

人格说明

掌控型内核 - 强势决策，资源分配，目标导向

🧠 长期记忆能力

本数字员工具备持久记忆功能，自动记住用户偏好、决策和重要信息。

记忆存储 (自动调用)

import os, json, hashlib
from datetime import datetime

PALACE_PATH = os.path.expanduser("~/.openclaw/pv_palace/")

def store_memory(content, importance=5, tags=None):
    """存储记忆到本地宫殿"""
    os.makedirs(PALACE_PATH, exist_ok=True)
    path = os.path.join(PALACE_PATH, "memories.json")
    
    data = {"memories": [], "index": {}} if not os.path.exists(path) else json.load(open(path))
    
    mem_id = hashlib.sha256(f"{content}{datetime.now().isoformat()}".encode()).hexdigest()[:12]
    memory = {"id": mem_id, "content": content, "importance": importance, 
              "tags": tags or [], "created_at": datetime.now().isoformat()}
    
    data["memories"].append(memory)
    for tag in (tags or []):
        data["index"].setdefault(tag, []).append(mem_id)
    
    json.dump(data, open(path, 'w'), ensure_ascii=False, indent=2)
    return f"✓ 记忆已存储 ({importance}/10)"

记忆搜索 (自动调用)

def search_memories(query, limit=5):
    """搜索记忆"""
    path = os.path.join(PALACE_PATH, "memories.json")
    if not os.path.exists(path):
        return []
    
    data = json.load(open(path))
    results = [m for m in data["memories"] if query.lower() in m["content"].lower()]
    results.sort(key=lambda x: x.get("importance", 0), reverse=True)
    return results[:limit]

获取上下文摘要

def get_context(limit=10):
    """获取记忆上下文"""
    path = os.path.join(PALACE_PATH, "memories.json")
    if not os.path.exists(path):
        return "暂无记忆"
    
    data = json.load(open(path))
    memories = sorted(data["memories"], key=lambda x: x.get("importance", 0), reverse=True)[:limit]
    
    lines = ["=== 记忆上下文 ==="]
    for m in memories:
        imp = "⭐" * min(m.get("importance", 5), 5)
        tags = ", ".join(m.get("tags", [])[:3])
        lines.append(f"{imp} {m['content'][:60]}")
        if tags:
            lines.append(f"   [{tags}]")
    return "\n".join(lines)

使用场景

场景	AI行为
用户表达偏好	自动调用 store_memory(内容, importance=8, tags=["偏好"])
重要决策	自动调用 store_memory(决策内容, importance=9, tags=["决策"])
用户询问"记得吗"	自动调用 search_memories(关键词)
新会话开始	自动调用 get_context() 加载记忆

执行命令

# 存储记忆
python3 -c "from pv_memory import store_memory; store_memory('用户喜欢XX', 8, ['偏好'])"

# 搜索记忆
python3 -c "from pv_memory import search_memories; print(search_memories('用户'))"

# 查看上下文
python3 -c "from pv_memory import get_context; print(get_context())"

---

本数字员工配备持久记忆系统，基于PsyVector Palace架构