Menu
Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.
Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.
Basé sur la classification professionnelle SOC
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
npx skills add https://github.com/dvcrn/openclaw-skills-marketplace --skill openclaw-newsLa commande reste sur une seule ligne. Faites défiler horizontalement pour la vérifier avant de la copier.
Vous préférez une copie locale ? Téléchargez les fichiers actuellement disponibles dans SkillsMP.
Affichage de SKILL.md
监控 OpenClaw GitHub 版本更新，获取最新版本发布说明，翻译成中文， 并推送到 Telegram 和 Feishu。用于：(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
| name | openclaw-news |
| description | OpenClaw News |
Version: 1.0.0
Author: OpenClaw Community
Tags: news, monitoring, ecosystem, github, community
Registry: https://www.clawhub.ai
Aggregates breaking news and developments across the OpenClaw ecosystem into a clean, curated briefing. Pure signal, no noise.
Tracks:
openclaw/openclawgh CLI installed and authenticated (for GitHub API)clawdhub CLI installed (for skill registry queries)jq installed (for JSON processing)Copy this skill to your workspace:
skills/openclaw-news/
├── SKILL.md # This file
├── scripts/
│ ├── collect_news.sh # Main data collection script
│ └── format_briefing.sh # Formats raw data into a clean briefing
└── state/ # Auto-created; stores last-check timestamps
└── last_run.json
For daily briefings (9 AM):
openclaw cron add --name "openclaw-news" \
--schedule "0 9 * * *" \
--prompt "Run the OpenClaw Ecosystem News skill. Execute scripts/collect_news.sh from skills/openclaw-news/, then format and deliver the briefing." \
--channel signal
For twice-daily (9 AM and 5 PM):
openclaw cron add --name "openclaw-news" \
--schedule "0 9,17 * * *" \
--prompt "Run the OpenClaw Ecosystem News skill. Execute scripts/collect_news.sh from skills/openclaw-news/, then format and deliver the briefing." \
--channel signal
Once the cron is set, briefings arrive on schedule. The script tracks what it already reported via state/last_run.json — you only see what's new.
When your human asks "what's new in OpenClaw?" or similar:
scripts/collect_news.sh from the skill directoryscripts/format_briefing.sh to produce the briefingOr the agent can use the script outputs directly and format conversationally.
The scripts automatically compare against the last run. To force a full scan (ignore previous state), delete state/last_run.json or pass --full:
cd skills/openclaw-news
./scripts/collect_news.sh --full
📡 OpenClaw Ecosystem News — Jun 14, 2025
🚀 RELEASES
• v0.9.2 released — WebSocket stability fixes, new `canvas` action
https://github.com/openclaw/openclaw/releases/tag/v0.9.2
🧩 NEW SKILLS
• weather-alerts v2.1.0 — Added severe weather push notifications
• home-inventory v1.0.0 — Track household items with camera snaps
🔒 SECURITY
• Nothing new — all clear ✅
💬 COMMUNITY
• HN: "OpenClaw is the missing layer for personal AI" (142 points)
https://news.ycombinator.com/item?id=...
📰 ECOSYSTEM
• Fortune: "The rise of always-on AI agents" (mentions OpenClaw)
—
Last checked: Jun 13, 2025 09:00 ET
Sources: GitHub, ClawdHub, Brave Search, Moltbook
When delivering the briefing:
| Source | Method | Rate Limits |
|---|---|---|
| GitHub Releases | gh CLI | 5000 req/hr (authenticated) |
| GitHub Issues/PRs | gh CLI | Same |
| ClawdHub Registry | clawdhub explore | Minimal |
| Web/News | Brave Search API | Per your plan |
| Moltbook | API (when available) | TBD |
| Brave Search | Per your plan | |
| HN | Brave Search / API | Generous |
Edit scripts/collect_news.sh to:
No GitHub data: Run gh auth status — make sure you're authenticated.
No ClawdHub data: Check clawdhub explore --registry https://www.clawhub.ai works.
Stale results: Delete state/last_run.json to force a fresh scan.
Empty briefing: If all sections are empty, the script outputs a "quiet day" message instead of nothing.