技能的上下文窗口
- 作者仓库星标 98
- 许可证 MIT
- 作者仓库 .context
- 领域
- 通用
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 94 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @forefy · MIT
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 运行环境要求
- 未检出明确要求
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
# Use Case:
User had finished working on his feature or task successfully, but had to tweak lots of stuff in the behavior of the agent prior to completion - we now want to create a skill that in the next time will make this task a breeze
Steps:
1. Analyze conversation and understand fully what the user tried to achieve
2. Analyze where were the pitfalls, user frustrations, and what pre-information would have made the results quicker to get with the most quality
3. Print to the user 10 (or more) top items you think are the core points to base the new skill upon
4. Consult with the user if questions still remain
5. Create a skill and place it on the ~/.claude/skills/ directory. comply to agent skill format and [https://code.claude.com/docs/en/skills](https://code.claude.com/docs/en/skills)
Results:
- Working new skill, that next time would do the job much better with all the tweaks needed to perfect it based on learned conversation and observation
- New skill should be reusable (e.g. think fixes also for future usecases other than the single one the user encountered) 章节与文件索引
按说明文件中的顺序排列。
文件/命令 -> .claude/skills · code.claude.com/docs/en/skills
内容校验值 -> 4e2285975660
当前原文的自动摘译,尚未人工审校。
步骤: 1. 分析对话并充分理解用户试图实现的目标 2. 分析陷阱、用户挫败感以及哪些预先信息可以使结果更快地获得最高质量 3. 向用户打印 10 个(或更多)您认为是新技能基础核心点的首要项目 4. 如果问题仍然存在,请咨询用户 5. 创建一项技能并将其放在 ~/.claude/skills/ 目录中。遵守代理技能格式和 https://code.claude.com/docs/en/skills
结果: - 使用新技能,下一次会根据学到的对话和观察进行完善所需的所有调整,从而更好地完成工作 - 新技能应该是可重用的(例如,除了用户遇到的单个用例之外,还可以考虑修复未来的用例)