用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill clawdbot-skill-update命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
正在显示 SKILL.md
基于 SOC 职业分类
| name | clawdbot-skill-update |
| description | Comprehensive backup, update, and restore workflow with dynamic workspace detection |
| homepage | https://github.com/pasogott/clawdbot-skill-update |
| metadata | {"clawdbot":{"emoji":"💾","requires":{"bins":["bash","jq","tar","git"]},"tags":["backup","restore","update","multi-agent"]}} |
Comprehensive backup, update, and restore workflow for Clawdbot installations.
origin/main~/code/clawdbot (default)This skill provides a complete, modular update workflow for Clawdbot with dynamic workspace detection:
✅ Dynamic Workspace Detection - Reads workspace paths from config
✅ Multi-Agent Support - Handles multiple agents automatically
✅ Safe Rollback - Full restore capability
✅ Git Integration - Tracks versions and remotes
✅ Validation - Pre/post checks included
✅ Dry Run - Preview before backup
config.json - Skill configuration (repo URLs, paths)backup-clawdbot-dryrun.sh - Dry run preview (no changes)backup-clawdbot-full.sh - Dynamic full backup scriptrestore-clawdbot.sh - Dynamic restore scriptvalidate-setup.sh - Pre/post update validationcheck-upstream.sh - Check for available updatesUPDATE_CHECKLIST.md - Step-by-step update checklistQUICK_REFERENCE.md - Quick command referenceSKILL.md - This fileREADME.md - Quick start guideBoth backup and restore scripts now:
~/.clawdbot/clawdbot.jsonTrigger this skill when asked to:
~/.skills/clawdbot-update/backup-clawdbot-dryrun.sh
Shows:
No files are created or modified!
~/.skills/clawdbot-update/backup-clawdbot-full.sh
Backs up:
~/.clawdbot/clawdbot.json (config)~/.clawdbot/sessions/ (session state)~/.clawdbot/agents/ (multi-agent state)~/.clawdbot/credentials/ (auth tokens)~/.clawdbot/cron/ (scheduled jobs)~/.clawdbot/sandboxes/ (sandbox state)Output: ~/.clawdbot-backups/pre-update-YYYYMMDD-HHMMSS/
Follow the checklist:
cat ~/.skills/clawdbot-update/UPDATE_CHECKLIST.md
Key steps:
~/.skills/clawdbot-update/restore-clawdbot.sh ~/.clawdbot-backups/pre-update-YYYYMMDD-HHMMSS
Restores:
This skill is designed for multi-agent setups with:
CRITICAL:
pairing policy instead of opentelegram.groups and whatsapp.groups are now allowlists"agent" from implicitAfter backup, always verify:
BACKUP_DIR=~/.clawdbot-backups/pre-update-YYYYMMDD-HHMMSS
cat "$BACKUP_DIR/BACKUP_INFO.txt"
ls -lh "$BACKUP_DIR"
Should contain:
clawdbot.jsoncredentials.tar.gzworkspace-*.tar.gz (one per agent)Example: Switch WhatsApp to pairing:
jq '.whatsapp.dmPolicy = "pairing"' ~/.clawdbot/clawdbot.json | sponge ~/.clawdbot/clawdbot.json
Example: Set explicit sandbox scope:
jq '.agent.sandbox.scope = "agent"' ~/.clawdbot/clawdbot.json | sponge ~/.clawdbot/clawdbot.json
# 1. Check for updates
~/.skills/clawdbot-update/check-upstream.sh
# 2. Validate current setup
~/.skills/clawdbot-update/validate-setup.sh
# 3. Dry run
~/.skills/clawdbot-update/backup-clawdbot-dryrun.sh
# 4. Backup
~/.skills/clawdbot-update/backup-clawdbot-full.sh
# 5. Stop gateway
cd ~/code/clawdbot
pnpm clawdbot gateway stop
# 6. Update code
git checkout main
git pull --rebase origin main
pnpm install
pnpm build
# 7. Run doctor
pnpm clawdbot doctor --yes
# 8. Test
pnpm clawdbot gateway start # foreground for testing
# 9. Deploy
pnpm clawdbot gateway stop
pnpm clawdbot gateway start --daemon
# Quick rollback
~/.skills/clawdbot-update/restore-clawdbot.sh <backup-dir>
# Manual rollback
cd ~/code/clawdbot
git checkout <old-commit>
pnpm install && pnpm build
cp <backup-dir>/clawdbot.json ~/.clawdbot/
pnpm clawdbot gateway restart
pnpm clawdbot agents list
pnpm clawdbot logs --tail 50
pnpm clawdbot providers list --usage
pnpm clawdbot skills list
# Live logs
pnpm clawdbot logs --follow
# Or Web UI
open http://localhost:3001/logs
# Check status
pnpm clawdbot status
pnpm clawdbot gateway status
Gateway won't start:
pnpm clawdbot logs --grep error
pnpm clawdbot doctor
Auth errors:
# OAuth profiles might need re-login
pnpm clawdbot providers login <provider>
Sandbox issues:
# Check sandbox config
jq '.agent.sandbox' ~/.clawdbot/clawdbot.json
# Check per-agent sandbox
jq '.routing.agents[] | {name, sandbox}' ~/.clawdbot/clawdbot.json
If something goes wrong:
# 1. Stop gateway
pnpm clawdbot gateway stop
# 2. Full restore
LATEST_BACKUP=$(ls -t ~/.clawdbot-backups/ | head -1)
~/.skills/clawdbot-update/restore-clawdbot.sh ~/.clawdbot-backups/$LATEST_BACKUP
# 3. Restart
pnpm clawdbot gateway start
clawdbot skills install clawdbot-update
git clone <repo-url> ~/.skills/clawdbot-update
chmod +x ~/.skills/clawdbot-update/*.sh
MIT - see LICENSE
Pascal Schott (@pasogott)
Contribution for Clawdbot
https://github.com/clawdbot/clawdbot