travel-plan
生成旅行规划 HTML 网页 —— 通过 delegate_travel_planner 委托后台 Peer Agent 执行
Skill by hazewarm
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hazewarm-travel-plan
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: frontend, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/travel-plan
What's inside
- Skill name
travel-plan- Description
- 生成旅行规划 HTML 网页 —— 通过 delegate_travel_planner 委托后台 Peer Agent 执行
- License
- MIT
- Instructions
- 38 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## 何时触发 ★ 判断标准: **用户是否要一份完整的旅行规划网页(HTML)** 需要 delegate: - "帮我规划北京3日游" - "生成一份杭州旅行攻略" - "下周五去成都4天,做个行程" (这些是重任务:天气 + 多轮 POI + 酒店 + 小红书 = 数十次工具调用, raven 自己做会阻塞 5-10 分钟且质量不可靠) **不需要** delegate: - "杭州有什么好吃的?" → 普通问答,自己搜一下文字回复 - "推荐几个西湖边的景点" → 普通问答 - "北京天气怎么样" → 普通问答 (这些不需要 HTML,直接文字回答即可) ## 工作流(一个路径) ``` 1. 确认目的地、日期、偏好 - 如果用户没给全,追问补齐(城市、起止日期、旅行偏好) - 不要问太多轮,基本信息够了就提交 2. 立即委托 - 调 delegate_travel_planner(goal="<用户原始请求>") - 告知用户: "规划已提交,3-5分钟后通知您。您可以继续聊其他话题。" 3. 等待系统通知(Phase 3 会自触发,不需要你记) - ★ 系统通知中已包含 JSON 文件路径和 render_trip_html 调用指令 - 你不需要回忆这条 SKILL——通知文本会直接告诉你该做什么 ``` ## 关于 render_trip_html 同一份 JSON 可无限次重渲染不同风格——换风格只需调 render_trip_html 并传入 style 参数,不需要重新规划。
From hazewarm/raven-agent, MIT.
More from hazewarm/raven-agent
- 0.488score
review-drift-gaps
hazewarm
定期回顾 drift 全局行动历史,发现停滞方向,维护有界 backlog
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
rss-health-check
hazewarm
定期检查 RSS 订阅源健康状态,发现异常源时推送 Telegram 通知
SkillCFreshness: C★ 1Claude Code +9 - 0.485score
explore-curiosity
hazewarm
在空闲时像朋友随口一问,了解用户偏好和生活化信息
SkillCFreshness: C★ 1Claude Code +9 - 0.483score
health-log
hazewarm
定期查询健康数据(health MCP),记录时间戳和关键指标到日志。
SkillCFreshness: C★ 1Claude Code +9 - 0.453score
hello-world
hazewarm
一个示例 Drift skill,练习文件读写和 finish_drift
SkillCFreshness: C★ 1Claude Code +9 - 0.268score
rss-manage
hazewarm
管理 RSS 订阅源
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 19, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/hazewarm/raven-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hazewarm
- 0.488score
review-drift-gaps
hazewarm
定期回顾 drift 全局行动历史,发现停滞方向,维护有界 backlog
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
rss-health-check
hazewarm
定期检查 RSS 订阅源健康状态,发现异常源时推送 Telegram 通知
SkillCFreshness: C★ 1Claude Code +9 - 0.485score
explore-curiosity
hazewarm
在空闲时像朋友随口一问,了解用户偏好和生活化信息
SkillCFreshness: C★ 1Claude Code +9 - 0.483score
health-log
hazewarm
定期查询健康数据(health MCP),记录时间戳和关键指标到日志。
SkillCFreshness: C★ 1Claude Code +9 - 0.453score
hello-world
hazewarm
一个示例 Drift skill,练习文件读写和 finish_drift
SkillCFreshness: C★ 1Claude Code +9
Cite this page
travel-plan skill. Agent Mart. https://agentmart.dev/skills/hazewarm-travel-plan (last updated 2026-10-24)