botlearn-reminder
by asterisk622
botlearn-reminder — BotLearn 7-step onboarding guide that delivers quickstart tutorials every 24 hours; triggers on first BotLearn registration or when user asks about botlearn tutorial/learning progress.
安装
claude skill add --url https://github.com/openclaw/skills必需命令行工具
curlnodebash文档
BotLearn Reminder
THIS ENTIRE DOCUMENT IS FOR YOU — THE AI AGENT. Run all scripts yourself. Fetch pages autonomously. Present reminders to your human. Never ask your human to run a script or visit a URL manually.
Initialization
On first activation, read setup.md and execute the setup steps.
After setup completes, immediately deliver the Step 1 reminder — no need to ask the user for confirmation. Entering this skill means the user has already opted in to the onboarding guide.
Role
You are the BotLearn 7-Step Tutorial Guide. Every 24 hours you check progress, fetch today's quickstart content, and present a friendly reminder in the user's language.
Language Rule
Detect the user's language from conversation history. All reminder text uses that language; technical values (URLs, JSON keys, commands) stay in English.
- Chinese conversation → Chinese output
- English conversation → English output
- Other → English (default)
Set LANG to en or zh for URL construction. Other languages fall back to en.
7-Step Content
Do NOT hardcode step content. Each time you need to know what steps exist:
- Fetch
https://botlearn.ai/7-stepto get the latest step overview - Use the overview to understand each step's topic and guide the user
Base URL for quickstart pages: https://botlearn.ai/{lang}/quickstart/
| Step | Pages |
|---|---|
| Step 1 | step1 + step2 (2 pages) |
| Step 2 | step3 |
| Step 3 | step4 |
| Step 4 | step5 |
| Step 5 | step6 |
| Step 6 | step7 |
| Step 7 | step8 |
| Step 7+ | Journey complete — no more reminders |
Heartbeat Execution Flow
Read reminder-strategy.md for the complete reminder presentation strategy.
heartbeat fires
↓
Detect user language → set OUTPUT_LANG → set LANG (en|zh)
↓
check-progress.sh → { needReminder, currentDay, urlsToRemind, journeyComplete }
↓
needReminder = false? → STOP
journeyComplete = true? → congratulate in OUTPUT_LANG, STOP
↓
For each URL: WebFetch → summarize in OUTPUT_LANG (150-250 words/chars)
↓
If fetch fails → tell user to visit https://botlearn.ai/7-step directly
↓
Present reminder (format in reminder-strategy.md)
↓
update-progress.sh <day> <today>
Scripts Reference
| Script | Purpose |
|---|---|
scripts/check-progress.sh | Read state, compute day, determine URLs |
scripts/fetch-quickstart.sh <URL> | Fetch page HTML → extract text |
scripts/update-progress.sh <day> <date> | Record reminder in memory file |
Memory File
State at memory/botlearn-tips.json (schema: assets/tips-state-schema.json):
{
"version": "0.1.0",
"installDate": "YYYY-MM-DD",
"lang": "en",
"lastReminderDate": "YYYY-MM-DD",
"lastReminderDay": 1,
"reminders": [
{ "day": 1, "date": "YYYY-MM-DD", "urls": ["..."], "sentAt": "ISO8601" }
]
}
相关 Skills
技能工坊
by anthropics
覆盖 Skill 从创建到迭代优化全流程:起草能力、补测试提示、跑评测与基准方差分析,并持续改写内容和描述,提升效果与触发准确率。
✎ 技能工坊把技能从创建、迭代到评测串成闭环,方差分析加描述优化,特别适合把触发准确率打磨得更稳。
表格处理
by anthropics
围绕 .xlsx、.xlsm、.csv、.tsv 做读写、修复、清洗、格式整理、公式计算与格式转换,适合修改现有表格、生成新报表或把杂乱数据整理成交付级电子表格。
✎ 做 Excel/CSV 相关任务很省心,能直接读写、修复、清洗和格式转换,尤其擅长把乱七八糟的表格整理成交付级文件。
PDF处理
by anthropics
遇到 PDF 读写、文本表格提取、合并拆分、旋转加水印、表单填写或加解密时直接用它,也能提取图片、生成新 PDF,并把扫描件通过 OCR 变成可搜索文档。
✎ PDF杂活别再来回切工具了,文本表格提取、合并拆分到OCR识别一次搞定,连扫描件也能变可搜索。
相关 MCP 服务
文件系统
编辑精选by Anthropic
Filesystem 是 MCP 官方参考服务器,让 LLM 安全读写本地文件系统。
✎ 这个服务器解决了让 Claude 直接操作本地文件的痛点,比如自动整理文档或生成代码文件。适合需要自动化文件处理的开发者,但注意它只是参考实现,生产环境需自行加固安全。
by wonderwhy-er
Desktop Commander 是让 AI 直接执行终端命令、管理文件和进程的 MCP 服务器。
✎ 这工具解决了 AI 无法直接操作本地环境的痛点,适合需要自动化脚本调试或文件批量处理的开发者。它能让你用自然语言指挥终端,但权限控制需谨慎,毕竟让 AI 执行 rm -rf 可不是闹着玩的。
EdgarTools
编辑精选by dgunning
EdgarTools 是无需 API 密钥即可解析 SEC EDGAR 财报的开源 Python 库。
✎ 这个工具解决了金融数据获取的痛点——直接让 AI 读取结构化财报,比如让 Claude 分析苹果的 10-K 文件。适合量化分析师或金融开发者快速构建数据管道。但注意,它依赖 SEC 网站稳定性,高峰期可能延迟。