一键导入
general-experience
Cross-task runtime lessons, execution patterns, and reusable operational experience.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Cross-task runtime lessons, execution patterns, and reusable operational experience.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build-focused skill for creating, updating, and installing standard Agent Skills.
Manage SOP templates, scheduled automation tasks, and run history through AI-callable tools.
提供独立的命令执行与 skill 脚本执行能力。
Query chat history by keywords and date ranges.
Provides interaction capabilities with the user.
Meta skill for AI self-evolution. Invoke when recording lessons learned and improving skill guidance from execution feedback.
| name | general-experience |
| description | Cross-task runtime lessons, execution patterns, and reusable operational experience. |
| license | Apache-2.0 |
| type | system |
| created_by | system |
| kind | knowledge |
| capability_group | memory-meta |
| experience | [] |
| allowed-tools | ["record_general_experience"] |
Use this experience package to capture runtime lessons that do not naturally belong to a narrower skill.
Use it for cross-task execution patterns, error recovery rules, environment caveats, and general collaboration lessons.
Do not store narrow tool guidance here when it clearly belongs to a more specific skill.
Avoid promoting one-off debugging notes into durable lessons unless they are likely to recur.
Add reusable cross-task lessons here as the system evolves.
record_general_experienceupdate_experienceparallel_tools for independent read-only evidence gathering before deciding whether a lesson is general enough to recordUse record_general_experience when a lesson clearly belongs to cross-task runtime knowledge instead of a narrower skill.
Use update_experience when you also want a shared entry point that can route to a specific skill or to general experience.
Do not put sensitive secrets or ephemeral one-off debugging dumps into this experience package.
parallel_tools.沉淀为 Skill remains the preferred path for substantial reusable workflow knowledge.