← 返回 Skills 市场
982
总下载
1
收藏
3
当前安装
12
版本数
在 OpenClaw 中安装
/install travel-cog
功能描述
AI travel planning and itinerary generation powered by CellCog. Vacation planning, travel research, flight planning, hotel recommendations, visa requirements...
安全使用建议
This skill is internally consistent with its purpose: it uses the CellCog SDK and asks only for CELLCOG_API_KEY and python3. Before installing or running anything: 1) Verify the CellCog package (pip name and project homepage) to ensure you're installing the official library; 2) Inspect any setup helper (/cellcog-setup or clawhub scripts) before executing them — they may run additional commands; 3) Treat your CELLCOG_API_KEY like a secret (don't paste it into untrusted places) and review CellCog's privacy/data-retention policy because itinerary generation may send travel plans and personal details to their API; 4) If you prefer tighter control, avoid granting the agent autonomous invocation for this skill or limit its use until you confirm the SDK behavior. Overall, nothing unexpected was found, but exercise standard caution with third-party API keys and installers.
功能分析
Type: OpenClaw Skill
Name: travel-cog
Version: 1.0.11
The travel-cog skill bundle consists of metadata and documentation for an AI travel planning tool. It relies on an external Python dependency 'cellcog' and requires a 'CELLCOG_API_KEY'. The SKILL.md file provides standard usage instructions and examples for travel research without any signs of malicious code, data exfiltration, or prompt-injection attacks.
能力标签
能力评估
Purpose & Capability
Name/description (travel planning with CellCog) align with requested resources: python3 and CELLCOG_API_KEY. The SKILL.md consistently references the CellCog SDK and producing itineraries, which justifies the single API key and Python dependency.
Instruction Scope
Instructions focus on using the CellCog client (create_chat examples) and output formats (PDF/HTML/Markdown). They ask users/agents to refer to a separate 'cellcog' skill for the full SDK. There is no instruction to read arbitrary system files or unrelated environment variables. Note: SKILL.md references helper commands (/cellcog-setup, clawhub install cellcog) and suggests pip install -U cellcog — you should verify what those setup helpers do before running them.
Install Mechanism
There is no built-in install spec (instruction-only), so nothing will be downloaded automatically by the skill. The README suggests using pip install -U cellcog or provided setup commands; this is a normal, expected approach. Because installation remains manual, the install risk is low, but you should confirm the package source (PyPI/project homepage) before running installers.
Credentials
Only CELLCOG_API_KEY is required, which is appropriate for a remote-API-based travel planning SDK. No additional credentials, passwords, or config paths are requested. The skill does not ask for unrelated secrets.
Persistence & Privilege
always is false and the skill does not request elevated or persistent platform privileges. disable-model-invocation is default (false) which is normal; autonomous invocation is platform-default and not by itself a concern here.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install travel-cog - 安装完成后，直接呼叫该 Skill 的名称或使用
/travel-cog触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.11
- Added requirements for Python 3 and the CELLCOG_API_KEY environment variable to the skill metadata.
- No other content or functional changes.
v1.0.10
- Streamlined skill description for brevity and clarity.
- Updated SDK usage instructions for agents other than OpenClaw.
- Improved installation guidance with clearer steps for each agent/platform.
- Removed references to "hidden gems" in the summary and focused feature list.
- No functional changes; documentation and onboarding improved for clarity.
v1.0.9
- Updated description for clarity and emphasis on research-driven travel planning and DeepResearch Bench ranking.
- Improved and expanded SDK usage instructions, including sample import for CellCogClient.
- Wording and content refinements for accuracy and conciseness throughout.
- No functional or code changes—documentation/SKILL.md improvements only.
v1.0.8
- Simplified and condensed the skill description for clarity and brevity.
- Streamlined the usage instructions with separate guides for OpenClaw and other agents.
- Moved advanced SDK and setup information to the cellcog skill, referencing it directly.
- Added clear instructions for installing CellCog in Cursor, OpenClaw, and other environments.
- Minor reorganization and formatting improvements for easier reading.
v1.0.7
- Overhauled description and documentation for clarity and detail on capabilities and output formats.
- Added prominent positioning as "#1 on DeepResearch Bench (Apr 2026)" and emphasized research-driven planning (not blog listicles).
- Expanded sections with concrete example prompts for various travel scenarios (city trips, multi-city tours, family, budget, business).
- Detailed new “Why CellCog for Travel?” and “Output Formats” comparison charts.
- Included a "Tips for Better Travel Plans" section to help users get higher-quality, tailored itineraries.
- Updated chat mode guidance for typical travel planning and complex scenarios.
v1.0.6
travel-cog v1.0.6 Changelog
- SKILL.md rewritten and significantly condensed for clarity and brevity.
- Description shortened, with marketing copy and detailed feature lists removed.
- Output formats now summarized (PDF, HTML dashboards).
- Practical usage and code examples retained.
- Feature highlights reorganized into concise, bulleted sections.
- Reference to related skills added.
v1.0.5
- Added example Python code for integrating with OpenClaw agents (fire-and-forget), including usage of notify_session_key for long-running tasks.
- Clarified agent usage, specifying differences between OpenClaw agents (async/notify) and all other agents (blocking).
- Removed SDK file handling and timeout details from skill documentation, pointing instead to the main cellcog skill for those topics.
- No changes to travel planning features or outputs.
v1.0.4
- Updated the SDK usage section to feature a simpler "Quick start" code example.
- Clarified reference to the cellcog skill for API details, delivery modes, and advanced options.
- Removed deprecated session notification parameters from setup instructions.
- Improved instructions for finding comprehensive SDK documentation.
- No functional changes; documentation improvements only.
v1.0.3
- Updated DeepResearch Bench ranking date from February 2026 to April 2026 in the description and main documentation.
- No functional or feature changes; documentation only.
v1.0.2
- Updated the SKILL.md description for clarity and conciseness.
- Added supported operating systems (darwin, linux, windows) to metadata.
- Added a homepage URL to metadata.
- Improved formatting and organization of documentation.
- No changes to functionality—documentation update only.
v1.0.1
- Clarified that PDF is the default output format when no format is specified.
- No changes to code or core features. This update refines documentation for greater clarity.
v1.0.0
- Initial release of travel-cog, a travel research and planning skill powered by CellCog.
- Generates custom trip itineraries and deep travel research (current prices, visa, weather, local events, hidden gems).
- Outputs in PDF, interactive HTML, or Markdown formats based on user preference.
- Supports detailed travel logistics, local recommendations, and practical guides.
- Requires the cellcog skill as a dependency for setup and API access.
元数据
常见问题
Travel Cog 是什么？
AI travel planning and itinerary generation powered by CellCog. Vacation planning, travel research, flight planning, hotel recommendations, visa requirements... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 982 次。
如何安装 Travel Cog？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install travel-cog」即可一键安装，无需额外配置。
Travel Cog 是免费的吗？
是的，Travel Cog 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Travel Cog 支持哪些平台？
Travel Cog 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux, windows）。
谁开发了 Travel Cog？
由 CellCog（@nitishgargiitd）开发并维护，当前版本 v1.0.11。
推荐 Skills