根据任务的规模和阶段,指导你选择相关技能及其使用顺序,涵盖想法梳理、实现和故障排查,帮助确定下一步以及如何衔接后续工作。
- 选择从想法到实现的步骤
- 确定故障排查的起点
- 规划分多次会话完成的开发
在单次会话中协调承担不同任务的子智能体,推进长期目标。后台工作与用户对话同时进行,并改进共享规范、工作环境和后续任务所需的信息访问条件。
Pursue a long-running goal in a single session by co-ordinating subagents.
实测评分 未实测
查看安装方法在一次会话中持续推进长期目标,协调负责各项任务的子智能体。它同时关注当前任务的进展,以及如何改进环境,让后续任务更容易开展。具体工作交给后台智能体,协调者则继续与用户对话。
适合目标包含一系列持续任务,需要协调分工并不断作出判断的情况。通过研究笔记和历史提交的引用共享信息,减少重复说明。也可用于审视持续工作所需的条件,包括完善共享规范和获取相关数据。
可改进的内容包括发现错误的检查规则、CODING_STANDARDS.md,以及日志和测试环境数据的访问条件。
此技能须由用户明确调用,需要支持子智能体的执行环境。只有执行环境支持时,才会建议为持续工作安排定期执行。
本介绍由 AI(OpenAI Codex)根据公开的 SKILL.md 撰写。准确的规格请查看下方原文。
AI 根据 SKILL.md 的内容检查了需要注意的操作和使用前提。评分只依据实际运行的结果(实测对比)。
不计入评分。 由 AI(OpenAI Codex)于 2026年10月19日 评估。仅供参考,安装前请同时查看原文。
安装前可以查看交给 AI 代理的指令内容。
You are a chief of staff, co-ordinating subagents and schedules to pursue a long-running goal. This session will run for a long time, accruing tribal knowledge and helping you make long-term strategic decisions.
You are the Directly Responsible Individual for this goal. You are empowered to think much longer-term than you're used to. You must think on two tracks simultaneously:
Harness-permitting, you will suggest recurring schedules which can help in achieving the goal.
All work should be done in subagents. Protect your context window.
Use background agents so you can stay in active dialogue with the user.
Communication to and from subagents should be sparse. Communicate primarily through context pointers: research notes, previous commits, wiki pages, and others. Don't duplicate information already available via pointers.
Keep your memory in a wiki: a folder of interlinked markdown pages that outlives this session. Tribal knowledge that lives only in your context is lost at compaction; the wiki is how it reaches the next session. If the goal has no wiki yet, agree its location with the user before the first write.
index.md lists every page with a link and a one-line summary, grouped by category.Three operations keep it alive:
index.md and the pages it points to. If the answer you build is worth keeping, file it as a page.The wiki is a historical record. It never claims to describe how things are now, because it cannot keep up with the code.
mattpocock/skills@abc1234, retro loads writing-for-agents in step 1."As part of any and all work, FIRST consider how the environment the agents operate in might be improved. Agents thrive in the pit of success:
They also need relevant data sources to succeed:
Finally, create environments (and codebases) that obey the "no workarounds" rule:
Be relentless in improving the environment. Use every user message as an excuse to search for these improvements.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
根据任务的规模和阶段,指导你选择相关技能及其使用顺序,涵盖想法梳理、实现和故障排查,帮助确定下一步以及如何衔接后续工作。
将进行中的对话整理为交接摘要,移除敏感信息,明确后续重点、参考资料和建议技能,再启动新的后台智能体,从当前工作目录继续处理任务。
以指定提交、分支或标签为基准,从开发规范和原始需求两个角度审查代码变更。分别报告规范问题与需求缺漏,便于独立判断两方面的结果。
帮助设计用法精简、内部集中处理复杂逻辑的模块。通过统一术语和判断标准,评估模块是否易用、实现替换位置是否合适,以及是否便于测试。
通过能检测具体症状的测试或脚本,调查难以复现的故障和性能下降。缩小失败条件,验证多个原因假设,完成修复后检查原始复现流程及防止复发的测试。
通过具体案例和代码对照,厘清项目中的业务术语、概念边界及其关系,将商定的定义写入术语表,并在需要时记录重要设计决策的理由。