每日简报机器人教程涵盖了基础内容。本指南会进一步深入 —— 提供五种真实场景中的自动化模式,你可以根据自己的工作流进行调整。
完整功能参考请参见 Scheduled Tasks(Cron)。
模式 1:网站变更监控
Section titled “模式 1:网站变更监控”监控一个 URL 的变化,并且只有在内容不同时才收到通知。
这里的 script 参数是秘密武器。每次执行前会先运行一个 Python 脚本,它的 stdout 会成为 agent 的上下文。脚本负责机械性工作(获取、diff);agent 负责推理(这个变化是否重要?)。
创建监控脚本:
mkdir -p ~/.hermes/scripts~/.hermes/scripts/watch-site.py
import hashlib, json, os, urllib.request
URL = "https://example.com/pricing"STATE_FILE = os.path.expanduser("~/.hermes/scripts/.watch-site-state.json")
# Fetch current contentreq = urllib.request.Request(URL, headers={"User-Agent": "Hermes-Monitor/1.0"})content = urllib.request.urlopen(req, timeout=30).read().decode()current_hash = hashlib.sha256(content.encode()).hexdigest()
# Load previous stateprev_hash = Noneif os.path.exists(STATE_FILE): with open(STATE_FILE) as f: prev_hash = json.load(f).get("hash")
# Save current statewith open(STATE_FILE, "w") as f: json.dump({"hash": current_hash, "url": URL}, f)
# Output for the agentif prev_hash and prev_hash != current_hash: print(f"CHANGE DETECTED on {URL}") print(f"Previous hash: {prev_hash}") print(f"Current hash: {current_hash}") print(f"\nCurrent content (first 2000 chars):\n{content[:2000]}")else: print("NO_CHANGE")设置 cron job:
/cron add "every 1h" "If the script output says CHANGE DETECTED, summarize what changed on the page and why it might matter. If it says NO_CHANGE, respond with just [SILENT]." --script ~/.hermes/scripts/watch-site.py --name "Pricing monitor" --deliver telegram模式 2:每周报告
Section titled “模式 2:每周报告”将多个来源的信息汇总成格式化摘要。它每周运行一次,并投递到你的 home channel。
/cron add "0 9 * * 1" "Generate a weekly report covering:
1. Search the web for the top 5 AI news stories from the past week2. Search GitHub for trending repositories in the 'machine-learning' topic3. Check Hacker News for the most discussed AI/ML posts
Format as a clean summary with sections for each source. Include links.Keep it under 500 words — highlight only what matters." --name "Weekly AI digest" --deliver telegram从 CLI:
hermes cron create "0 9 * * 1" \ "Generate a weekly report covering the top AI news, trending ML GitHub repos, and most-discussed HN posts. Format with sections, include links, keep under 500 words." \ --name "Weekly AI digest" \ --deliver telegram0 9 * * 1 是一个标准 cron 表达式:每周一上午 9:00。
模式 3:GitHub 仓库监控器
Section titled “模式 3:GitHub 仓库监控器”监控一个仓库是否有新的 issues、PRs 或 releases。
/cron add "every 6h" "Check the GitHub repository NousResearch/hermes-agent for:- New issues opened in the last 6 hours- New PRs opened or merged in the last 6 hours- Any new releases
Use the terminal to run gh commands: gh issue list --repo NousResearch/hermes-agent --state open --json number,title,author,createdAt --limit 10 gh pr list --repo NousResearch/hermes-agent --state all --json number,title,author,createdAt,mergedAt --limit 10
Filter to only items from the last 6 hours. If nothing new, respond with [SILENT].Otherwise, provide a concise summary of the activity." --name "Repo watcher" --deliver discord模式 4:数据收集 Pipeline
Section titled “模式 4:数据收集 Pipeline”按固定间隔抓取数据,保存到文件,并随时间检测趋势。这个模式将脚本(用于收集)与 agent(用于分析)结合起来。
~/.hermes/scripts/collect-prices.py
import json, os, urllib.requestfrom datetime import datetime
DATA_DIR = os.path.expanduser("~/.hermes/data/prices")os.makedirs(DATA_DIR, exist_ok=True)
# Fetch current data (example: crypto prices)url = "https://api.coingecko.com/api/v3/simple/price?ids=bitcoin,ethereum&vs_currencies=usd"data = json.loads(urllib.request.urlopen(url, timeout=30).read())
# Append to history fileentry = {"timestamp": datetime.now().isoformat(), "prices": data}history_file = os.path.join(DATA_DIR, "history.jsonl")with open(history_file, "a") as f: f.write(json.dumps(entry) + "\n")
# Load recent history for analysislines = open(history_file).readlines()recent = [json.loads(l) for l in lines[-24:]] # Last 24 data points
# Output for the agentprint(f"Current: BTC=${data['bitcoin']['usd']}, ETH=${data['ethereum']['usd']}")print(f"Data points collected: {len(lines)} total, showing last {len(recent)}")print(f"\nRecent history:")for r in recent[-6:]: print(f" {r['timestamp']}: BTC=${r['prices']['bitcoin']['usd']}, ETH=${r['prices']['ethereum']['usd']}")/cron add "every 1h" "Analyze the price data from the script output. Report:1. Current prices2. Trend direction over the last 6 data points (up/down/flat)3. Any notable movements (>5% change)
If prices are flat and nothing notable, respond with [SILENT].If there's a significant move, explain what happened." \ --script ~/.hermes/scripts/collect-prices.py \ --name "Price tracker" \ --deliver telegram脚本负责机械性收集;agent 添加推理层。
模式 5:多 Skill 工作流
Section titled “模式 5:多 Skill 工作流”将 skills 串联起来,用于复杂的定时任务。Skills 会在 prompt 执行前按顺序加载。
# Use the arxiv skill to find papers, then the obsidian skill to save notes/cron add "0 8 * * *" "Search arXiv for the 3 most interesting papers on 'language model reasoning' from the past day. For each paper, create an Obsidian note with the title, authors, abstract summary, and key contribution." \ --skill arxiv \ --skill obsidian \ --name "Paper digest"直接从工具调用:
cronjob( action="create", skills=["arxiv", "obsidian"], prompt="Search arXiv for papers on 'language model reasoning' from the past day. Save the top 3 as Obsidian notes.", schedule="0 8 * * *", name="Paper digest", deliver="local")Skills 会按顺序加载 —— 先加载 arxiv(教 agent 如何搜索论文),再加载 obsidian(教它如何写笔记)。prompt 会把它们串联起来。
管理你的 Jobs
Section titled “管理你的 Jobs”# List all active jobs/cron list
# Trigger a job immediately (for testing)/cron run <job_id>
# Pause a job without deleting it/cron pause <job_id>
# Edit a running job's schedule or prompt/cron edit <job_id> --schedule "every 4h"/cron edit <job_id> --prompt "Updated task description"
# Add or remove skills from an existing job/cron edit <job_id> --skill arxiv --skill obsidian/cron edit <job_id> --clear-skills
# Remove a job permanently/cron remove <job_id>--deliver flag 控制结果发送到哪里:
| 目标 | 示例 | 使用场景 |
|---|---|---|
| origin | --deliver origin | 创建该 job 的同一个聊天(默认) |
| local | --deliver local | 仅保存到本地文件 |
| telegram | --deliver telegram | 你的 Telegram home channel |
| discord | --deliver discord | 你的 Discord home channel |
| slack | --deliver slack | 你的 Slack home channel |
| 指定聊天 | --deliver telegram:-1001234567890 | 指定的 Telegram 群组 |
| 线程化 | --deliver telegram:-1001234567890:17585 | 指定的 Telegram topic thread |
让 prompts 自包含。cron job 中的 agent 不记得你的对话。请直接在 prompt 中包含 URLs、repo names、格式偏好和投递说明。
大量使用 [SILENT]。对于监控 jobs,始终包含类似“如果没有变化,回复 [SILENT]”这样的指令。这可以防止通知噪音。
使用 scripts 进行数据收集。script 参数可以让 Python 脚本处理无聊的部分(HTTP requests、file I/O、state tracking)。agent 只会看到脚本的 stdout,并对其应用推理。相比让 agent 自己抓取内容,这种方式更便宜,也更可靠。
使用 /cron run 测试。在等待 schedule 触发之前,使用 /cron run <job_id> 立即执行,并确认输出看起来正确。
Schedule 表达式。支持的格式:相对延迟(30m)、间隔(every 2h)、标准 cron 表达式(0 9 * * *),以及 ISO 时间戳(2025-06-15T09:00:00)。不支持像 daily at 9am 这样的自然语言 —— 请改用 0 9 * * *。
完整的 cron 参考 —— 所有参数、边界情况和内部机制 —— 请参见 Scheduled Tasks(Cron)。