activity-summary
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseActivity Summary — Read the Digest First
活动总结 — 优先读取摘要
Overview
概述
A relayfile workspace pre-computes deterministic daily activity digests at . These are produced by relayfile itself from the raw provider data, so they are complete over the time window (no API pagination gaps) and free for the agent to consume (one file read, no LLM generation step).
<mount>/digests/If you've been asked an activity-summary question, read the digest before doing anything else. Reaching for , , or per-provider exploration first is the most common reason these answers cost 20+ tool calls when they could cost 1.
lsgreprelayfile工作区会在目录下预先计算确定性的每日活动摘要。这些摘要由relayfile本身从原始供应商数据生成,因此覆盖整个时间窗口(无API分页遗漏),且Agent可以免费使用(仅需读取一个文件,无需LLM生成步骤)。
<mount>/digests/如果您被问到活动总结类问题,请先读取摘要,再进行其他操作。首先使用、或针对单个供应商的探索是导致这类回答原本只需1次工具调用却花费20+次的最常见原因。
lsgrepWhen to use this skill
何时使用本技能
Trigger phrases from the user — read the digest first:
- "what did I work on yesterday / today / this week"
- "what changed across {GitHub, Linear, Notion, Slack, ...} {yesterday, since Friday, etc.}"
- "summarize my activity"
- "give me a standup update"
- "what did $team_member ship recently"
If the user's question is not windowed by time (e.g. "find the Notion page about onboarding"), the digest is not the right entry point — use or indexes instead. See the skill.
by-title/by-id/workspace-layout用户触发短语 — 优先读取摘要:
- “我昨天/今天/本周做了什么”
- “{GitHub、Linear、Notion、Slack等}在{昨天、自周五以来等}有哪些变化”
- “总结我的活动”
- “给我一份站会更新内容”
- “$team_member最近完成了什么”
如果用户的问题未按时间窗口限定(例如“找到关于入职的Notion页面”),则摘要不是合适的入口点 — 请改用或索引。详见技能。
by-title/by-id/workspace-layoutWhat digests look like
摘要的格式
bash
$ ls $MOUNT/digests/
yesterday.md # rolling — generated at 00:00 local for the prior calendar day
today.md # rolling — updated continuously as the day progresses
2026-05-12.md # date-stamped, immutable once the day closes
2026-05-11.md
...
this-week.md # rolling — Mon→now of the current ISO week
last-week.md # immutable, prior ISO weekThe body is plain Markdown with one section per provider:
markdown
undefinedbash
$ ls $MOUNT/digests/
yesterday.md # 滚动更新 — 本地时间00:00生成前一自然日的摘要
today.md # 滚动更新 — 当日持续更新
2026-05-12.md # 带日期戳,当日结束后不可修改
2026-05-11.md
...
this-week.md # 滚动更新 — 当前ISO周从周一至今的内容
last-week.md # 不可修改,上一个ISO周的内容摘要主体为纯Markdown格式,每个供应商对应一个章节:
markdown
undefinedActivity for 2026-05-12
2026-05-12的活动
linear
linear
- AGE-16 moved to Blocked (waiting on design) — [/linear/issues/AGE-16__87389837-...]
- AGE-9 closed — [/linear/issues/AGE-9__2bb2c00f-...]
- AGE-16 状态变更为Blocked(等待设计) — [/linear/issues/AGE-16__87389837-...]
- AGE-9 已关闭 — [/linear/issues/AGE-9__2bb2c00f-...]
github
github
- relayfile-adapters#412 merged to main — [/github/repos/.../pulls/412.json]
- relayfile#287 opened — [/github/repos/.../pulls/287.json]
- relayfile-adapters#412 已合并至main分支 — [/github/repos/.../pulls/412.json]
- relayfile#287 已创建 — [/github/repos/.../pulls/287.json]
notion
notion
- "Khaliq's To Dos" edited — [/notion/pages/3566800c-.../content.md]
- “Khaliq的待办事项”已编辑 — [/notion/pages/3566800c-.../content.md]
slack
slack
- 7 messages in #gtm-prospects mentioning "ACME"
Each bullet links to the canonical file in the mount, so a follow-up question ("what changed about AGE-16?") is one `cat` away.- #gtm-prospects频道中有7条提及“ACME”的消息
每个项目符号都链接到挂载中的标准文件,因此后续问题(例如“AGE-16有哪些变化?”)只需一次`cat`命令即可解决。How to use it
使用方法
bash
undefinedbash
undefined1. Check the digest covers the date the user asked about.
1. 检查摘要是否覆盖用户询问的日期。
ls $MOUNT/digests/
cat $MOUNT/digests/yesterday.md
ls $MOUNT/digests/
cat $MOUNT/digests/yesterday.md
2. If the user asked about a specific date, prefer the date-stamped file.
2. 如果用户询问特定日期,优先使用带日期戳的文件。
cat $MOUNT/digests/2026-05-12.md
cat $MOUNT/digests/2026-05-12.md
3. Confirm coverage before answering. The digest header includes the window
3. 回答前确认覆盖范围。摘要头部包含其涵盖的时间窗口;如果用户的时间窗口更宽,请读取多个摘要文件,而非从原始供应商数据重新生成。
it spans; if the user's window is wider, read multiple digest files
—
rather than re-deriving from raw provider data.
—
head -5 $MOUNT/digests/this-week.md
That is usually the entire workflow: read → quote → done. Four tool calls or fewer.head -5 $MOUNT/digests/this-week.md
这通常就是完整的工作流程:读取 → 引用 → 完成。仅需4次以内的工具调用。When to fall back to exploration
何时退回到直接探索
The digest is the right answer when:
- The window matches a digest file (yesterday, today, a specific past date, this/last week).
- The user wants everything in the window, not a filtered slice.
Fall back to direct exploration via index subtrees when:
by-edited/<date>/- The window is unusual (e.g. "the last 36 hours"). Use indexes; see
by-edited/.workspace-layout - The user wants a filter the digest doesn't pre-compute (e.g. "only Linear issues assigned to me").
- The digest file is missing or its header indicates incomplete provider coverage.
在以下情况下,摘要是合适的解决方案:
- 时间窗口与某个摘要文件匹配(昨天、今天、特定过去日期、本周/上周)。
- 用户需要时间窗口内的全部内容,而非筛选后的部分。
在以下情况下,请退回到通过索引子树进行直接探索:
by-edited/<date>/- 时间窗口特殊(例如“过去36小时”)。请使用索引;详见
by-edited/技能。workspace-layout - 用户需要摘要未预先计算的筛选条件(例如“仅分配给我的Linear问题”)。
- 摘要文件缺失或其头部显示供应商覆盖不完整。
Why this matters
为什么这很重要
In our published benchmarks, the activity-summary question dropped from ~20 turns and $0.30+ to 4 turns and ~$0.07 once the digest existed and the agent read it first. The digest is one file read that replaces ~25 individual provider queries.
If you find yourself listing more than 2-3 directories to answer an activity question, stop and check — you're almost certainly working harder than you need to.
digests/在我们发布的基准测试中,活动总结类问题的处理从约20轮调用、花费0.30美元以上,降至4轮调用、花费约0.07美元,这一切都源于摘要的存在以及Agent优先读取摘要的操作。一次文件读取的摘要可以替代约25次单独的供应商查询。
如果您发现自己为了回答活动类问题而列出2-3个以上的目录,请停下来检查目录 — 您几乎肯定在做不必要的额外工作。
digests/