Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计提醒

supervisorsupervisor 开发

Agent Skill

supervisor 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

5,508

周安装

225

GitHub Stars

1

下载量

1,782
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:supervisor(supervisor 开发)
来源仓库:https://github.com/netanel-abergel/supervisor
安装命令:
openclaw skills install supervisor
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install supervisor

简介

作为 PA 代理的中央状态仪表板,回答状态相关问题。

  • 适合查询“您在做什么”、“发生了什么”等概述请求。
  • 提供实时任务进度和资源使用情况。适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。
  • 需确保 Agent 定期更新状态信息。
  • 建议结合日志系统查看历史活动。supervisor 属于开发类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
supervisor
description
Central status dashboard for the PA agent. Use when: owner asks 'what's the status', 'what are you working on', 'what's happening', or any status/overview question. Aggregates active tasks, open issues, monitored groups, pending follow-ups, and system health into one structured report.

Supervisor Skill

The single source of truth for what the agent is currently tracking.


When to Use

Trigger phrases:

  • "מה הסטטוס" / "what's the status"
  • "מה קורה" / "what's going on"
  • "תתני לי סיכום" / "give me a summary"
  • "על מה את עובדת" / "what are you working on"
  • "supervisor"

Status Report Format

Always structure the report by category. Only include categories with active items.

📊 Status Report — [DATE TIME]

🔴 URGENT / BLOCKING
• [issue] — [who is affected] — [what's needed]

🟡 IN PROGRESS
• [task] — [status] — [next step]

⚠️ OPEN ISSUES
• [issue] — [group/person] — [since when]

👥 GROUP ACTIVITY
• [Group Name]: [last significant event]

📬 PENDING FOLLOW-UPS
• [person] — [what you're waiting for]

✅ COMPLETED TODAY
• [task] — [outcome]

🔧 SYSTEM HEALTH
• Model: [current model]
• WhatsApp: [connected/disconnected]
• API Billing: [OK / issue with which PAs]
• Last backup: [time]

Data Sources

The supervisor reads from these files to build the report:

build_status_report() {
  WORKSPACE="$HOME/.openclaw/workspace"
  TODAY=$(date -u +%Y-%m-%d)
  
  echo "📊 Status Report — $(date -u '+%Y-%m-%d %H:%M UTC')"
  echo ""

  # Open tasks / blockers from daily notes
  echo "🔴 URGENT / BLOCKING"
  grep -i "blocked\|urgent\|waiting\|מחכה\|חסום" \
    "$WORKSPACE/memory/$TODAY.md" 2>/dev/null | tail -5
  echo ""

  # Pending follow-ups from DM memory
  echo "📬 PENDING FOLLOW-UPS"
  grep -r "follow.up\|pending\|לעקוב\|להחזיר" \
    "$WORKSPACE/memory/whatsapp/dms/" 2>/dev/null \
    --include="*.md" | grep "$(date +%Y-%m)" | tail -5
  echo ""

  # Group highlights
  echo "👥 GROUP ACTIVITY"
  for group_dir in "$WORKSPACE/memory/whatsapp/groups"/*/; do
    [ -d "$group_dir" ] || continue
    NAME=$(python3 -c "import json; print(json.load(open('${group_dir}meta.json')).get('name','?'))" 2>/dev/null)
    LAST=$(tail -1 "${group_dir}context.md" 2>/dev/null)
    [ -n "$LAST" ] && echo "• $NAME: $LAST"
  done
  echo ""

  # System health
  echo "🔧 SYSTEM HEALTH"
  
  # API billing check
  API_STATUS=$(curl -s -o /dev/null -w "%{http_code}" \
    -H "x-api-key: ${ANTHROPIC_API_KEY:-none}" \
    -H "anthropic-version: 2023-06-01" \
    https://api.anthropic.com/v1/models 2>/dev/null)
  case "$API_STATUS" in
    200) echo "• Billing: ✅ OK" ;;
    402) echo "• Billing: ⚠️ OUT OF CREDITS" ;;
    401) echo "• Billing: ❌ Invalid API key" ;;
    *)   echo "• Billing: ? ($API_STATUS)" ;;
  esac
  
  # Last git backup
  LAST_COMMIT=$(git -C "$WORKSPACE" log -1 --format="%ar" 2>/dev/null)
  echo "• Last backup: $LAST_COMMIT"
}

Tracked Categories

Tasks

Store active tasks in memory/tasks.md:

## Active Tasks
- [ ] [task description] | owner: [person] | since: [date] | next: [action]
- [x] [completed task] | done: [date]

Update this file whenever a task starts, progresses, or completes.

Billing Status

Store known billing issues in memory/billing-status.json:

{
  "last_checked": "2026-04-01T10:00:00Z",
  "issues": [
    {"pa": "Aria", "owner": "Jane Smith", "since": "YYYY-MM-DD", "status": "out_of_credits"},
    {"pa": "Rex", "owner": "John Doe", "since": "YYYY-MM-DD", "status": "resolved"}
  ]
}

Groups

For each WhatsApp group in memory/whatsapp/groups/, the supervisor shows:

  • Group name
  • Last logged event
  • Any open decisions or pending actions

Pending Follow-ups

Log these in the relevant DM memory file when you're waiting on someone:

[YYYY-MM-DD HH:MM] WAITING: Calendar access fix from [Owner Name]

Close-the-loop rule: When the owner asks you to check on someone, your job is:

  1. Contact that person directly
  2. Report back to the owner what they said

❌ Do NOT ask the owner instead of the person ❌ Do NOT swallow the answer — the owner asked because they want to know ✅ Always report back, even if the answer is "no update yet"


Quick Status (Short Version)

If owner just wants a quick overview:

📊 Quick Status — [TIME]

🔴 Blocking: [count] items
🟡 In Progress: [count] tasks  
⚠️ Open Issues: [count]
💡 Top item: [most important thing right now]

Say "full status" for details.

Updating the Status

After completing any significant action, update the relevant tracking file:

ActionUpdate
Task completedMark [x] in tasks.md
Billing error resolvedUpdate billing-status.json
Group decision madeLog to group's decisions.md
Owner confirmed somethingLog to DM notes.md
Follow-up receivedRemove from pending, log outcome

Cost Tips

  • Cheap: Reading files and formatting the report — any small model
  • Expensive: Summarizing many long files — batch the reads, summarize per file not all at once
  • Avoid: Calling external APIs for status checks every time — cache results for 15+ minutes
  • Batch: Build the full report in one pass, don't call build_status_report multiple times

Minimum Model

Any model that can:

  1. Read files
  2. Follow a template
  3. Fill in blanks from file content

No reasoning required. No external API calls needed for basic status. Use a larger model only if summarizing very long conversation histories.


Integration

  • After each task → update tasks.md
  • After each group message → update whatsapp-memory
  • On billing error → update billing-status.json
  • On heartbeat → run quick status check, alert if anything urgent
  • On "supervisor" → run full build_status_report and send to owner

Scope Rules

Always check who is asking and from where before generating the status report:

ContextScope
DM from ownerFull report — all tasks, all groups, all issues, system health
Group messageFilter to THIS GROUP ONLY — topics, decisions, open items from this group
DM from someone elseFilter to items relevant to this person only

Never send the full supervisor report in a group.

Example — if asked in the PA Team group:

📊 PA Team Status — [date]
• PA Operating Standard: sent and acknowledged by most PAs ✅
• Open: [PA Name] calendar write access — pending [Owner]'s response
• Open: [PA Name] calendar access — awaiting gog error output

Example — if asked in a DM from owner: → Full report (all categories)


PA Network Health (Merged from pa-status skill)

Use this section to check the health of all PA agents in the network. Reads from data/pa-directory.json.

Status Checks (per PA)

CheckFieldHealthy State
Last activelast_seenWithin 24 hours
Billingbilling_errorfalse
Calendarcalendar_connectedtrue
Statusstatus"active"

Network Report Script

#!/usr/bin/env python3
import json, datetime

try:
    with open('data/pa-directory.json') as f:
        d = json.load(f)
except FileNotFoundError:
    print("ERROR: data/pa-directory.json not found"); exit(1)

today = datetime.date.today().isoformat()
online, issues, offline = [], [], []

for pa in d.get('pas', []):
    name, owner = pa['name'], pa['owner']
    status = pa.get('status', 'unknown')
    model = pa.get('model', 'unknown')
    calendar = "✅" if pa.get('calendar_connected') else "❌"
    billing_ok = not pa.get('billing_error', False)

    if status == 'active' and billing_ok:
        online.append(f"• {name} ({owner}) — {model}, cal {calendar}")
    elif status == 'inactive':
        offline.append(f"• {name} ({owner})")
    else:
        billing = "✅" if billing_ok else "⚠️ billing error"
        issues.append(f"• {name} ({owner}) — {billing}")

total = len(d.get('pas', []))
print(f"📊 PA Network Status — {today}\
")
print(f"✅ ONLINE ({len(online)}/{total})")
for line in online: print(line)
if issues:
    print("\
⚠️ ISSUES")
    for line in issues: print(line)
if offline:
    print("\
❌ OFFLINE")
    for line in offline: print(line)
if not issues and not offline:
    print("\
All PAs are healthy 🎉")

Quick Ping (Reachability)

Only ping PAs flagged with issues (not healthy ones — avoids noise):

For each PA in issues list:
  Send: "ping 🏓" → wait up to 5 minutes
  Response received → ONLINE
  No response → check whatsapp-diagnostics section + billing-monitor skill

Schedule

  • Daily at 09:00 — Full network report to admin
  • On billing error — Immediate partial report for affected PA
  • On demand — When admin asks "what's the status?"

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

76.7%
按下载量换算1,367

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills