Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
OpenClaw onboarding guide for new users. Activate when a user asks how to get started with OpenClaw, says they are new, asks for a quickstart or tutorial, wa...
OpenClaw onboarding guide for new users. Activate when a user asks how to get started with OpenClaw, says they are new, asks for a quickstart or tutorial, wa...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Guides new users through 8 hands-on tasks covering OpenClaw's core features. Each task takes under 5 minutes and produces something immediately useful.
#Task (中文)Task (EN)Reference1给 AI 取个名字Initialize AI Identityreferences/task-01-identity.md2让 AI 记住你Save Your Preferencesreferences/task-02-memory.md3查今天天气Check the Weatherreferences/task-03-weather.md4写一篇日报Generate a Reportreferences/task-04-report.md5建一个日历提醒Set a Reminderreferences/task-05-reminder.md6用浏览器收集信息Browser Info Gatheringreferences/task-06-browser.md7让 AI 做一张 PPTGenerate a PPTreferences/task-07-ppt.md8安装一个新 SkillInstall a Skill from ClawHubreferences/task-08-skill.md
Before doing anything else, check if this is the first time the skill is running: # Check if already installed test -f ~/.openclaw/workspace/.quickstart-progress.json && echo "installed" || echo "fresh" If the result is fresh (no progress file yet) → silently run the installer first: node {baseDir}/scripts/install.js --workspace ~/.openclaw/workspace Do not ask the user — just run it. The installer is idempotent and safe. After it completes, proceed normally.
Always start by running: node scripts/check_progress.js --workspace ~/.openclaw/workspace Parse JSON output to get current task status and next_task.
Display current progress: 📋 你的 OpenClaw 新手任务进度(3/8) ✅ 任务1:给 AI 取个名字 ✅ 任务2:让 AI 记住你 ✅ 任务3:查今天天气 ⬜ 任务4:写一篇日报 ← 下一步 ⬜ 任务5:建一个日历提醒 ⬜ 任务6:用浏览器收集信息 ⬜ 任务7:让 AI 做一张 PPT ⬜ 任务8:安装一个新 Skill Ask if they want to do the next task now, or jump to a specific one.
Read the task's reference file Walk the user through it step by step — do it with them, don't just explain After the task action succeeds → immediately call mark_done.js (see below) Confirm completion, then offer the next task
On first activation (no .quickstart-progress.json yet), run the installer immediately: node scripts/install.js --workspace ~/.openclaw/workspace The installer does two things in one shot: HEARTBEAT.md — appends a quickstart progress-check block (runs every 30 min via heartbeat) Cron — creates quickstart-reminder (daily 9 AM push notification for pending tasks) Optional: customize reminder time: node scripts/install.js --workspace ~/.openclaw/workspace --hour 9 --minute 30 Preview without applying: node scripts/install.js --workspace ~/.openclaw/workspace --dry-run Note: The installer is idempotent — safe to run multiple times. It skips steps already done.
After performing any of the following actions, immediately run mark_done.js: node scripts/mark_done.js --task <N> --workspace ~/.openclaw/workspace TaskTrigger condition1SOUL.md or IDENTITY.md written with AI name/rules2USER.md updated with user's name/preferences3Weather query successfully returned results to user4A report/daily-log file saved to workspace5A cron/reminder successfully created6browser tool used and returned scraped content7A .pptx file saved to workspace8A skill successfully installed via clawhub If all_done: true is returned → immediately run: node scripts/cleanup_crons.js Then send the graduation message (see below).
node scripts/check_progress.js --mark-done --workspace ~/.openclaw/workspace --mark-done flag: auto-persists newly detected completions to progress.json If all_done: true → run cleanup_crons.js + send graduation message If newly_completed has entries → send brief completion notification Otherwise → stay silent (no message)
🦐 嗨!你的 OpenClaw 新手任务还有 N 个待完成: ✅ 任务1:给 AI 取个名字 ✅ 任务2:让 AI 记住你 ⬜ 任务3:查今天天气 ← 今天来试试? 直接说「帮我完成任务3」就开始了!
Send this, then run cleanup_crons.js: 🎓 恭喜!你已完成全部 8 个新手任务! OpenClaw 你玩明白了 🦐 以后有任何问题,随时问我。 (每日提醒和自动检测已自动关闭)
Do, don't just explain — actively help complete each task Mark immediately — call mark_done.js right after task success, don't wait Heartbeat is silent — only speak up when something changes or all done Cleanup on finish — all crons must be removed when all_done: true
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.