通过1Password CLI,将保存的密码和API密钥用于命令及配置模板,完成安装、认证、秘密值读取,并通过环境变量向命令传递凭据。
- 安装并配置1Password CLI
- 使用已保存的API密钥运行命令
- 向配置模板填入秘密值
汇总日历、任务和笔记,回顾一周的承诺、逾期工作与停滞项目,整理待回复事项,并结合期限和既定日程的工作量,制定下周的成果目标与下一步行动。
Weekly reset: commitments, stalled work, next-week plan.
跨日历、任务、笔记等指定信息源开展每周回顾。回顾过去一周的会议和承诺,并检查未来一至两周的期限、出行和准备需求。针对进行中的项目,整理成果目标、下一步行动、负责人、期限和阻碍,找出停滞事项及记录矛盾。还会汇总等待回复的事项和自己作出的承诺,形成符合既定日程负荷的下周计划。
适合任务与笔记分散在多个地方、担心遗漏承诺或搁置项目的时候。也适合明确优先完成的成果与需要推迟的工作,避免把所有未完成事项都直接带入下一周。
首先确认目标系统、时间范围、时区及作为准确信息依据的来源。需要与所用日历和笔记相应的连接器或相关技能。默认生成建议或草稿,仅在获批范围内更改任务、日程和笔记。回顾结果也会注明无法访问的信息。
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 仅根据 SKILL.md 的内容,从 4 个方面进行了评估。星标数和热度不计入评估。
总分按每项 A=25 分、B=15 分、C=5 分相加。 由 AI(OpenAI Codex)于 2026年10月20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。
Run a bounded weekly reset across the user's chosen systems. This is a concrete recurring task, not a generic productivity methodology — the weekly-review Automation Blueprint schedules it as a cron job.
Don't use for: daily briefs (see the google-workspace daily-brief reference) or single-inbox triage (email-inbox-triage).
Confirm timezone, review period, planning horizon, authoritative task/project store, calendars, inboxes, and allowed writes. Default to recommendations/drafts, not mutations. Done when source-of-truth conflicts have a declared winner.
Load google-workspace or the relevant calendar connector. Inspect the completed week for meetings and commitments, then the next 1-2 weeks for deadlines, travel, preparation, and capacity. Capture follow-ups implied by past events and conflicts ahead. Done when both retrospective and horizon are covered.
Review the task inbox, notes (obsidian, notion), flagged email (email-inbox-triage owns thread-level triage), and other declared capture points. Convert each item to next action, project, waiting, scheduled, someday, reference, archive, or delete proposal. Do not mutate until scope is approved. Done when remaining unprocessed items are counted and stated.
For each project identify desired outcome, next action, owner, deadline, blocker, last meaningful activity, and source link. Flag projects with no next action, missed dates, duplicate records, or contradictory status. Done when every active project is actionable or explicitly paused.
Find promises made by the user and items owed by others. Propose follow-ups with dates and channels. Do not infer that silence means completion. Done when each waiting item has an owner and next review/follow-up date.
Estimate fixed calendar load and select a small set of weekly outcomes plus near-term next actions. Rank by consequence, deadline, dependency, and effort; do not fill every free hour. Done when the plan fits actual capacity and names deferred work.
Update tasks/projects, create calendar holds, archive processed items, and draft follow-ups only as approved. Read every changed record back from the provider. Done when verified writes match the review summary.
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。
通过1Password CLI,将保存的密码和API密钥用于命令及配置模板,完成安装、认证、秘密值读取,并通过环境变量向命令传递凭据。
创建用公式联动利润表、资产负债表和现金流量表的 Excel 模型,分阶段填入历史实际数据与预测假设,比较不同情景,并检查三张报表之间的一致性。
以少量修改让现有PyTorch训练代码适用于多GPU或多台机器,指导混合精度、节省内存的DeepSpeed与FSDP配置,以及训练启动方法。
帮助配置Hermes,通过Actual Computer在自己的设备上运行AI模型。支持加密中继与本地连接,涵盖模型选择、响应测试,以及请求报错或空响应的排查。
扮演不擅长技术、容易不满的用户测试应用,发现难懂的操作和导致放弃使用的障碍。将实际可改进的问题与个人抱怨分开,整理截图、修复建议和任务单。
从中立立场解决两个智能体分别修改代码产生的Git冲突,对照双方差异和意图,记录每处冲突的取舍理由,并通过构建或测试验证合并结果。