车宿指南
trip-guide-pdf-car-sleep
by allensu0314
Research, plan, revise, and deliver car-sleep travel guides as HTML/PDF with verified overnight parking, charging, toilet access, next-morning route anchors, and formal copy. Use when the user plans to sleep in the car, skip hotels, use Tesla/EV camp mode, optimize for chargers and public parking, or asks whether the hiking/scenic route should change after removing lodging.
安装
claude skill add --url https://github.com/openclaw/skills文档
Trip Guide PDF Car Sleep
Build the guide in HTML first. Export PDF only after night-parking anchors, route logic, and screenshots are stable.
Treat night parking as the anchor for each day. For car-sleep trips, the real constraint is usually not the scenic spot—it is whether the user can park, charge, wash up, and leave smoothly the next morning.
Core rules
- Verify every hard number before writing it.
- Separate hard data from soft signal.
- Hard data: parking point, charger existence, toilet existence when relevant, route time, distance, tolls, scenic hours.
- Soft signal: quietness, comfort, crowding feel, scenic vibe, overnight confidence level.
- Distinguish
24h parking/charging accessfromovernight car-sleep explicitly allowed. - If overnight permission is not explicitly verified, label the spot as a candidate night anchor, permission unconfirmed rather than claiming it is allowed.
- Prefer anchors with explicit car-sleep / camping signal over generic public charger parking.
- Best: official campsite / campground / scenic camping area
- Next: repeatedly mentioned car-sleep / overnight stop in social results
- Next: service area with strong facilities
- Last resort: generic public parking + charger
- If the night parking anchor changes, recompute all dependent legs.
- Do not present a generic public charger parking lot as the main night anchor unless stronger overnight evidence is unavailable.
- Use formal, compact copy unless the user explicitly wants casual tone.
Workflow
1) Lock the planning frame
Extract:
- dates / trip length
- departure city
- vehicle type and whether EV charging matters
- trip style: solo, hiking, photography, family, etc.
- comfort vs scenery tradeoff
- output target: quick answer or polished HTML/PDF
2) Turn the request into car-sleep variables
Identify the variables that can change the whole plan:
- EV vs ICE
- charger dependence
- toilet dependence
- county-town first night vs scenic-adjacent first night
- main scenic line vs lighter backup line
- public parking vs scenic parking
Do not research these variables equally; prioritize the ones that make the trip operable.
3) Choose sources by job
Read references/source-selection.md when deciding what to trust.
Default split:
- maps / official scenic pages / structured listings for hard numbers
- notes and review sites for soft signal
- if Chinese travel/review sites are involved and normal search/fetch is weak, use
cn-review-sites-cdp - when Xiaohongshu detail pages degrade into 404 or blocked pages, still use search-result clustering as a soft-signal layer to detect which locations are repeatedly treated as camping / overnight spots
4) Verify hard data before drafting
Check the numbers and permissions that decide feasibility:
- origin → night parking anchor
- night parking anchor → main scenic spot
- scenic spot A → scenic spot B
- charger location and parking context
- nearby public toilet when the night plan depends on it
- scenic opening hours / latest entry
- whether overnight parking / overnight car-sleep permission is explicitly stated anywhere reliable
Re-run this verification after every night-anchor change.
5) Choose the night anchor before choosing the scenic order
For each night, rank anchors by:
- overnight certainty
- explicit camping / car-sleep signal strength
- charger / refill certainty
- next-morning route efficiency
- nearby toilet / basic food access
- scenic proximity
This order is intentional. “Closest to the scenic spot” is often not the best overnight point, and a generic 24-hour parking lot should lose to a repeatedly mentioned camping / overnight point.
6) Design the itinerary from the night anchor
For each day, choose the sleep point first, then build:
- arrival and recharge buffer
- dinner / wash-up window
- scenic entry window for the next morning
- return buffer
- holiday congestion buffer
If the user removes hotels, do not just delete the lodging section. Rebuild the schedule from the new sleep points.
7) Use screenshots as evidence
Keep only screenshots that support decisions:
- scenic proof image
- parking / charger context if the choice is non-obvious
- any visible sign or listing evidence about parking hours / overnight rules
- restaurant snippet only if it affects the overnight strategy
Reject screenshots that are blank, cluttered, QR-heavy, or mostly UI.
8) Run the QA gate before PDF export
Read references/qa-checklist.md and clear it.
Minimum gate:
- overnight anchors verified
- dependent route numbers recomputed
- screenshots clean
- tone formal enough
- filenames and variant names clear
9) Deliver and version clearly
Prefer scenario-specific filenames.
Examples:
*_tesla_sleep.html*_car-sleep.html*_parking-revision.html
When sending local files through OpenClaw messaging, prefer relative MEDIA:./... paths instead of absolute MEDIA:/abs/path paths.
Revision logic
- Visual-only feedback: clean screenshots and tighten prose.
- Sleep-point change: recompute all dependent legs and next-morning structure.
- Charging concern: elevate charger, toilets, and service-area fallback strength.
- Weak overnight evidence: demote generic public charger parking and replace it with a stronger camping / car-sleep signal point.
- Comfort concern: consider swapping the lighter scenic day to a more urban or public-facility-rich anchor.
Read these references when needed
references/source-selection.md— which source to trust for which car-sleep decisionreferences/qa-checklist.md— pre-export checklist for car-sleep guides
相关 Skills
PPT处理
by anthropics
处理 .pptx 全流程:创建演示文稿、提取和解析幻灯片内容、批量修改现有文件,支持模板套用、合并拆分、备注评论与版式调整。
✎ 涉及PPTX的创建、解析、修改到合并拆分都能一站搞定,连备注、模板和评论也能处理,做演示文稿特别省心。
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。
Word文档
by anthropics
覆盖Word/.docx文档的创建、读取、编辑与重排,适合生成报告、备忘录、信函和模板,也能处理目录、页眉页脚、页码、图片替换、查找替换、修订批注及内容提取整理。
✎ 搞定 .docx 的创建、改写与精排版,目录、批量替换、批注修订和图片更新都能自动化,做正式文档尤其省心。
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。