跳到正文
cccskills
免费在 GitHub 公开

widen

Assemble cases from context, induce the widest sound rule. Use when a real case shows a class no rule yet decides, or a rule decides only the cases it came from.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md1.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Assemble

This runs inside one turn — nothing waits on the user.

Pull every real case the context holds — what the input shows, what the named files record, what memory and your own judgment place in the same class. State each case with the wrong answer it exhibits and the right answer it demands.

Induce

Do not summarize the cases. Induce the widest rule that gets every case in the set exactly right, and forbids the wrong answer each case exhibits.

Where a rule already existed, the new one still comes from the case set alone; if the cases or the objective moved, the old rule is void and what you hand back is a fresh derivation. Between candidate rules, prefer the one that decides more situations, even if it takes longer to state.

Probe

  1. List 10 situations not in the case set where the rule gives a definite answer, and state the answer it forces in each.
  2. Hunt for one situation where the rule forces a wrong answer.
    • Found one → narrow the rule by the smallest amount that fixes it. A narrowing that loses a case from the set went past the smallest — find one that keeps the whole set. Then list and hunt again on the narrowed rule.
    • Found none → the loop ends; the rule stands.

If narrowing has left the rule unable to give a definite answer in 10 situations outside the set, stop there and carry the shortfall into the record — the widest sound rule found barely outreaches its cases.

Hand back

The rule, then one line per case and per listed situation, each with the answer the rule forces.

Nothing unseen will ever meet the rule — something already written should get shorter and nothing it covers can be lost → use reduce skill.

评价

还没有评价。欢迎分享你的使用感受。

评论

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。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

anchor

免费

Rewrite a rule so anyone applies it the same way. Use when a stated rule or claim takes the reader's judgment to apply.

中文简介正在准备中。当前显示原文说明。

saadshahd/moo.md382026年10月17日 更新

clarify

免费

Turn words with two readings into one confirmed ask. Use when the user's words admit two readings that would build different things.

中文简介正在准备中。当前显示原文说明。

saadshahd/moo.md382026年10月17日 更新

compose

免费

Plan the skills an ask needs, invoke each as its condition arrives. Use when the ask has multiple aspects that different skills carry, or the user named multiple skills.

中文简介正在准备中。当前显示原文说明。

saadshahd/moo.md382026年10月17日 更新

consult

免费

Bring how named experts would think about the question. Use when the user wants expert thinking on a tradeoff, choice, or stuck problem — not a verdict.

中文简介正在准备中。当前显示原文说明。

saadshahd/moo.md382026年10月17日 更新

deepen

免费

Hold an ask to the bar a top professional in its field would set — a deeper ask, never a bigger one. Use when an ask is clear but nothing yet names the sources, methods, target, or outside check the work will meet.

中文简介正在准备中。当前显示原文说明。

saadshahd/moo.md382026年10月17日 更新

draft

免费

Build the thing the user can't specify, choices surfaced. Use when the user needs something to react to before they can choose.

中文简介正在准备中。当前显示原文说明。

saadshahd/moo.md382026年10月17日 更新

查看 saadshahd 的全部技能

报告此技能的问题