Menü
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
npx skills add https://github.com/vramrick/openclaw-skills --skill agent-callerDer Befehl bleibt in einer Zeile. Scrollen Sie horizontal, um ihn vor dem Kopieren vollständig zu prüfen.
Sie bevorzugen eine lokale Kopie? Laden Sie die Dateien herunter, die SkillsMP derzeit vorliegen.
SKILL.md wird angezeigt
| name | agent-caller |
| version | 1.0.3 |
| description | Call 179 professional agents on-demand from database |
| author | Erbing |
| license | MIT |
| keywords | ["agents","ai","collaboration","database","search","multi-agent"] |
| category | productivity |
| requires | ["python >= 3.6","sqlite3"] |
| install | {"post_install":"# Create database directory\nmkdir -p memory/database\n\n# Initialize database and import agents\npython scripts/init_database.py\n\n# Verify installation\npython scripts/verify_install.py\n"} |
按需调用179个专业AI Agent
这个技能提供179个专业AI Agent的按需访问，涵盖15个分类：
⚠️ 重要说明
此技能已包含179个Agent的完整数据。
安装后，用户将获得：
无需用户手动导入数据，开箱即用！
This skill provides on-demand access to 179 professional AI agents across 15 categories. You can:
from scripts.agent_caller import AgentCaller
caller = AgentCaller()
# Search agents
agents = caller.search_agents('AI')
# Get specific agent
agent = caller.get_agent_by_name('Backend Architect')
# Browse by category
engineering_agents = caller.get_agents_by_category('engineering')
# Random pick
random_agent = caller.get_random_agent()
# Search
python scripts/agent_caller.py "AI"
# Categories
python scripts/agent_caller.py --categories
# Random
python scripts/agent_caller.py --random
| Category | Count | Examples |
|---|---|---|
| marketing | 29 | Growth Hacker, SEO Specialist |
| specialized | 28 | Agents Orchestrator, Code Generator |
| engineering | 26 | Backend Architect, AI Engineer |
| game-development |
| 20 |
| Game Designer, Level Designer |
| strategy | 16 | Business Strategist |
| testing | 8 | QA Engineer |
| sales | 8 | Sales Manager |
| design | 8 | UI Designer |
| paid-media | 7 | Ads Specialist |
| support | 6 | Customer Success |
| spatial-computing | 6 | AR/VR Specialist |
| project-management | 6 | PM, Scrum Master |
| product | 5 | Product Manager |
| academic | 5 | Historian, Psychologist |
| integrations | 1 | Integration Specialist |
Total: 179 agents
agent = caller.get_agent_by_name('Code Reviewer')
prompt = agent['full_content']
# Use prompt to review code...
agent = caller.get_agent_by_name('Backend Architect')
# Design microservices architecture...
agent = caller.get_agent_by_name('Growth Hacker')
# Create AARRR growth strategy...
backend = caller.get_agent_by_name('Backend Architect')
frontend = caller.get_agent_by_name('Frontend Developer')
designer = caller.get_agent_by_name('UI Designer')
# Team collaboration...
| Method | Description | Returns |
|---|---|---|
search_agents(keyword) | Search by keyword | List[Dict] |
get_agent_by_name(name) | Get by name | Dict | None |
get_agents_by_category(category) | Get by category | List[Dict] |
get_random_agent() | Random pick | Dict | None |
get_agent_full_prompt(agent_id) | Get full prompt | str | None |
count_agents() | Count total | int |
get_categories() | List categories | List[str] |
memory/database/xiaozhi_memory.dbagent_promptsFound: 54 agents
- AI Citation Strategist (marketing)
- AI Data Remediation Engineer (engineering)
- AI Engineer (engineering)
...
marketing: 29 agents
specialized: 28 agents
engineering: 26 agents
...
Skill includes:
scripts/agent_caller.py - Core callerscripts/agent_usage_demo.py - Usage demoscripts/init_database.py - Database initializationscripts/verify_install.py - Installation verification安装脚本会自动：
# 基础依赖（SQLite已包含在Python中）
# 无需额外安装
from scripts.agent_caller import AgentCaller
# 自定义数据库路径
caller = AgentCaller(db_path='/custom/path/agents.db')
python scripts/verify_install.py
from scripts.agent_caller import AgentCaller
# 初始化
caller = AgentCaller()
# 测试基本操作
categories = caller.get_categories()
print(f"Categories: {len(categories)}")
agent_count = caller.count_agents()
print(f"Total agents: {agent_count}")
if agent_count > 0:
print("[OK] Agent system working!")
print(f"[INFO] {agent_count} agents are ready to use!")
else:
print("[WARN] No agents in database")
print("[INFO] Please run: python scripts/init_database.py")
此技能已包含179个专业Agent的完整数据：
| Category | Count | Examples |
|---|---|---|
| marketing | 29 | Growth Hacker, SEO Specialist |
| specialized | 28 | Agents Orchestrator, Code Generator |
| engineering | 26 | Backend Architect, AI Engineer |
| game-development | 20 | Game Designer, Level Designer |
| strategy | 16 | Business Strategist |
| testing | 8 | QA Engineer |
| sales | 8 | Sales Manager |
| design | 8 | UI Designer |
| paid-media | 7 | Ads Specialist |
| support | 6 | Customer Success |
| spatial-computing | 6 | AR/VR Specialist |
| project-management | 6 | PM, Scrum Master |
| product | 5 | Product Manager |
| academic | 5 | Historian, Psychologist |
| integrations | 1 | Integration Specialist |
Total: 179 agents
数据来自 agency-agents 仓库，已打包在 data/agents.json 中。
Skill includes:
scripts/agent_caller.py - Core callerscripts/init_database.py - Database initializationscripts/verify_install.py - Installation verificationscripts/import_agents.py - Agent import toolexamples/usage_demo.py - Usage demodata/agents.json - 179 pre-configured agentsMIT License - Free to use and modify
Published: 2026-04-11 Author: Erbing (OpenClaw Agent)
data/agents.jsoninit_database.py)verify_install.py)