文档Docs

技能健康度和「存成技能」Skill health and saving repeated work as a skill

技能页显示每个技能最近一次用是什么时候、用了几次，很久没用的可以归档；同一件事让 Agent 做满 3 次，它会主动问你要不要存成技能。The Skills page shows when each skill was last used and how often, long-unused ones can be archived, and after the same task three times the Agent offers to save it as a skill.

技能装多了，哪些常用、哪些早就不用了，一眼很难看出来。Agent J 帮你记两件事：每个技能用了几次、最近一次是哪天；还有你反复让 Agent 做的同一件事。

技能页上看什么

打开手机左上角 logo 菜单里的「技能」页，每个技能下面多了一行：

最近使用：3 天前 · 5 次 —— 电脑上的 Agent J 亲眼看到的次数。
最近使用：— —— 还没看到它被用过。Agent J 拿不到准确数字时就显示「—」，不会估一个数给你。
很久没用了（超过 30 天） —— 装了满 30 天、30 天里一次也没用过。下面有个「归档」按钮。

怎么才算用了一次：

你在手机上发 /技能名，任何 AI 编程工具都算。
用 Claude Code 时，Claude 自己调用技能、或者你在电脑上敲 /技能名，也算。
Codex、OpenCode 等工具不告诉 Agent J 它们用了哪个技能，所以这些工具下只统计你从手机发的 / 命令，也不会标「很久没用了」——那样就是在猜了。

归档和恢复

点「归档」，这个技能的文件夹会挪到旁边的归档文件夹里（比如 ~/.claude/skills-archive/），AI 编程工具就不会再加载它。不会删除任何文件。

想再用：在技能页最下面的「已归档」里点「恢复」，它回到原来的位置。
Agent J 自带的技能（agentj- 开头的）不建议归档，也没有归档按钮。
工作流项目自己带的技能请在那个项目里管理，这里不提供归档。
指向别处的链接（符号链接）技能，比如从别的文件夹链进来的，为了安全不能在这里归档，也没有归档按钮；详情里会写明原因。要停用它，到它真正所在的文件夹里处理。
Agent J 从不自己归档，只有你在手机上点了才会动。

在电脑上也能做同样的事：

agentj skills health            # 每个技能最近一次使用、次数、是否很久没用
agentj skills archive 技能名     # 归档（不删除）
agentj skills restore 技能名     # 放回原处

多少天算很久没用，可以自己定，默认 30 天，范围 7 到 365：在电脑上对 Agent 说「把技能很久没用的天数改成 60」，或者改配置里的 skills.stale_days。

同一件事做了 3 次：存成技能

如果 14 天里你让 Agent 做了 3 次差不多的事——比如「把下载文件夹里的发票整理成表格发我邮箱」，只是日期不同——Agent 会在办完第 3 次之后问你一句：「这件事你已经让我做了 3 次，要不要存成技能？」

你说要：Agent 按做命令的老办法帮你写一个技能，起个名字，以后一句 /名字 就行。每个这样存下的技能都带一个自检（技能文件夹里的 tests/check.sh 或 check.py），Agent 会先跑一遍给你看结果。
你说不用：这件事以后不会再问。
每件事只问一次，一天最多问一次。

怎么判断是不是差不多的事：电脑上的 Agent J 把你的话去掉日期、数字、路径、引号里的内容后比对，完全一样才算同一件；Agent 反复跑的同一个脚本或同一串命令也算。这一步不调用任何大模型。

隐私：记下来的只是去掉了细节的一小段文字（不超过 60 个字）和时间，不存你的原话；密钥、令牌这类内容会先被抹掉，存在你自己的电脑上，不上传。

不想被问：对 Agent 说「关掉存成技能的建议」，或者把配置里的 skills.suggest 改成 false。

在电脑上看当前的建议：

agentj skills suggest           # 当前的建议
agentj skills suggest --all     # 也列出已经回答过的

Once you have many skills, it is hard to see which ones you use and which you forgot long ago. Agent J keeps track of two things for you: how often each skill is used and when it was last used, and the tasks you keep asking the Agent to repeat.

What the Skills page shows

Open the Skills page from the logo menu on your phone. Each skill now has one more line:

Last used: 3 days ago · 5 times — the uses Agent J on your computer actually saw.
Last used: — — no use seen yet. When Agent J has no exact number it shows "—"; it never shows a guess.
Not used for a long time (over 30 days) — installed for 30 days and not used once in that time. An "Archive" button sits underneath.

What counts as one use:

You send /skill-name from your phone, with any AI coding tool.
With Claude Code, Claude running a skill by itself, or you typing /skill-name on the computer, also counts.
Codex, OpenCode and the other tools do not tell Agent J which skills they run, so with them only the / commands you send from the phone are counted, and no skill is marked as long unused — that would be a guess.

Archive and restore

Tap "Archive" and the skill's folder is moved to an archive folder next to it (for example ~/.claude/skills-archive/), so your AI coding tool no longer loads it. No file is deleted.

To use it again, tap "Restore" under "Archived" at the bottom of the Skills page; it goes back where it was.
Skills that come with Agent J (names starting with agentj-) are not archived and have no Archive button.
Skills that belong to a workflow project are managed in that project; they are not archived here.
A skill that is a link to a folder elsewhere (a symbolic link) can't be archived here, for safety, so it has no archive button; its details say why. To retire it, deal with it in the folder it points to.
Agent J never archives anything by itself: only your tap on the phone does.

You can do the same on the computer:

agentj skills health            # each skill's last use, count, and whether it is long unused
agentj skills archive skill-name    # archive (nothing deleted)
agentj skills restore skill-name    # put it back

How many days count as "a long time" is up to you: 30 by default, anything from 7 to 365. Tell the Agent "set the skill long-unused days to 60", or change skills.stale_days in the configuration.

The same task three times: save it as a skill

If within 14 days you ask the Agent three times for much the same thing — say "put the invoices in my Downloads folder into a spreadsheet and email it to me", only with a different date — the Agent finishes the third one and then asks: "You've asked me for this three times — save it as a skill?"

Yes: the Agent writes the skill the usual way for commands and gives it a name, so next time it is just /name. Every skill saved this way comes with a self-check (tests/check.sh or check.py in the skill's folder), and the Agent runs it once and shows you the result.
No: it never asks about that task again.
It asks about each task once, and at most once a day.

How "the same task" is decided: Agent J on your computer removes dates, numbers, paths and quoted text from your words and compares what is left; only an exact match counts. The same script or chain of commands the Agent keeps running counts too. No AI model is used for this.

Privacy: only that short, detail-free text (at most 60 characters) and the times are kept, never your original words; keys and tokens are removed first. It stays on your own computer.

To stop the offers, tell the Agent "turn off the save-as-skill offers", or set skills.suggest to false in the configuration.

To see the current offers on the computer:

agentj skills suggest           # current offers
agentj skills suggest --all     # also the ones already answered

这一页的 Markdown 原文This page as Markdown: zh.md · en.md