跳到正文
cccskills
免费在 GitHub 公开

spread

Before improving anything, show the spread of what can concretely be done on this specific input — a short menu of 3-5 interventions from lightest to heaviest touch, then wait for the user to pick. Domain-agnostic; works on any material the user hands over. Trigger when the user says "spread", "show me my options", "what can you do with this", or asks to improve or fix something without specifying how. Do NOT trigger when the user has already named a specific fix — then just do the fix.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md1.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Spread

Show the capability spread on one concrete input before doing any work. Do not pick one interpretation of "fix this" and run with it. Enumerate the real options on this exact material, scope each honestly, and let the user choose the level.

Hard rule: no input, no run

This skill operates on a specific thing the user provides. If triggered without one, ask what the thing is and wait. Never produce a generic capabilities list.

Procedure

  1. Read the input fully.
  2. List 3-5 interventions you can concretely perform on it — actual operations against actual parts of the material, not categories or generic advice.
  3. Order them lightest to heaviest touch.
  4. Give one line per item on scope and risk.
  5. Stop. Ask which level the user wants. Do zero work until they pick.

Constraints

  • Only list what you can actually complete with what's available. If an option needs something missing, mark it "needs: X" inline.
  • If the honest spread is thin, say so. Fewer real options beat padded ones.
  • Keep the whole output under one screen. No emojis, no headers inside the output.

After the pick

Execute only the chosen option at its stated scope. If mid-work that scope can't achieve the goal, stop and say so — offer to move up one level, don't just do it.

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

Use when creating a new project folder, starter pack, app scaffold, or agent-ready workspace — AGENTS.md, README, TASKS, DECISIONS, PROMPTS, an idempotent bootstrap script, and starter-pack modes.

中文简介正在准备中。当前显示原文说明。

aka-kika/akakika-skills112026年9月12日 更新

Use when designing or implementing states for AI agent tasks, background jobs, local model runs, queues, and notifications — one shared set of states, only legal transitions, and a recovery path out of every failure.

中文简介正在准备中。当前显示原文说明。

aka-kika/akakika-skills112026年9月12日 更新

Use when exposing app features to App Intents, Shortcuts, Siri, Spotlight, widgets, controls, or system actions — small safe AppIntents, AppShortcutsProvider, AppEnum/AppEntity, parameters, and open-vs-background behavior.

中文简介正在准备中。当前显示原文说明。

aka-kika/akakika-skills112026年9月12日 更新

Use when designing, reviewing, or implementing a command-palette / ⌘K layer for an Apple-platform app — keyboard-first global search, ranked and grouped results, native floating panel, and protected destructive commands.

中文简介正在准备中。当前显示原文说明。

aka-kika/akakika-skills112026年9月12日 更新

Use when designing or implementing empty, first-run, no-result, offline, error, or waiting states in Apple-platform apps — every empty state explains what is missing, why it matters, and what to do next.

中文简介正在准备中。当前显示原文说明。

aka-kika/akakika-skills112026年9月12日 更新

Use when designing or implementing feedback, status, progress, alerts, errors, success states, and live activity indicators in Apple-platform apps — inline status, banners, alerts, notifications, and loading states.

中文简介正在准备中。当前显示原文说明。

aka-kika/akakika-skills112026年9月12日 更新

查看 aka-kika 的全部技能

报告此技能的问题