跳到正文
cccskills
免费在 GitHub 公开

plan

Structured design intake for non-trivial tasks. Asks clarifying questions and produces a design proposal.

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.md2.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Plan

Structured intake for complex tasks. The plan lives in a file, not in conversation output. Stay at the architecture level — define boundaries, interfaces, and data flow. Leave implementation details to the implementer.

  1. Understand: ask clarifying questions using AskUserQuestion — this is mandatory, never skip it. Use batches of ~4 questions, multiple-choice with 2-4 options + "Other / Not sure" when possible. Iterate until the reasoning framework is filled in — Problem, Goal, Background, Constraints. Do not write code or produce a plan until the user has answered at least one round of questions.
  2. Propose: write the proposal to a temp file (/tmp/plan-<timestamp>.md). Print a markdown link to the file (e.g., [plan-name.md](/tmp/plan-name.md)) so the user can click to open it — do not dump the plan into conversation output. Use the reasoning framework from workflow.md, structured top-down:
    • Problem(s): what's wrong or missing — the motivation for this work
    • Goal(s): what success looks like (optional if obvious from the problem)
    • Background: relevant context to understand the problem/solution — existing architecture, constraints, prior art. Use diagrams (ASCII or Mermaid) for data flow and component relationships when helpful.
    • Solution: what we're doing about it and how it integrates with what already exists. Structure as versioned milestones when the work has natural increments (v0 = minimal viable, v1 = full feature, etc.). Each version should be independently shippable. Within a version, group tasks by dependency — independent tasks are parallelizable. Define interfaces (API contracts, data shapes, protocols) at boundaries where parallel work can happen. Use diagrams (ASCII or Mermaid) for architecture and data flow when helpful.
    • Alternative(s) considered: other approaches evaluated and why not (optional, include when non-obvious)
    • Implementation details: specific file paths, configs, schemas, code snippets that clarify the solution. Optional — the plan should be understandable without it.
  3. Iterate: when the user requests changes, update the file in place. Never reprint the full plan — just summarize what changed.
  4. Confirm: wait for user confirmation before implementing.

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

amend

免费

Amend the last commit with current changes and/or an updated message.

中文简介正在准备中。当前显示原文说明。

simonepri/ifttt-lint292026年9月29日 更新

commit

免费

Stage changes and create a commit with a conventional commit message.

中文简介正在准备中。当前显示原文说明。

simonepri/ifttt-lint292026年9月29日 更新

cook

免费

Full autopilot — plan, implement, and polish a task end-to-end.

中文简介正在准备中。当前显示原文说明。

simonepri/ifttt-lint292026年9月29日 更新

diff

免费

Fetch and display diffs for various scopes (PR, commit, branch, staged, working tree). Used by other skills that need to analyze changes.

中文简介正在准备中。当前显示原文说明。

simonepri/ifttt-lint292026年9月29日 更新

execute

免费

Execute a plan file — parse phases, spawn parallel subagents, handle failures.

中文简介正在准备中。当前显示原文说明。

simonepri/ifttt-lint292026年9月29日 更新

fork

免费

Start or end a forked session for exploring rabbit holes without losing the main conversation's context.

中文简介正在准备中。当前显示原文说明。

simonepri/ifttt-lint292026年9月29日 更新

查看 simonepri 的全部技能

报告此技能的问题