Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Documents
Create Plan
Try itCreate a concise implementation plan for coding, documentation, repository, or workflow tasks before making changes. Use when the user explicitly asks for a...
What it does
Produce one clear, actionable plan from the user's request and the available project context.
The skill document
Create Plan
Goal
Produce one clear, actionable plan from the user's request and the available project context.
This skill is for planning only. Stay read-only unless the user separately asks for implementation.
Inputs
Collect the smallest useful context:
- user's requested outcome
- repository or artifact path, if relevant
- current constraints from README, docs, existing code, or prior decisions
- known deadline, risk tolerance, or delivery format, if provided
If the task depends on current repository facts, inspect the likely files first. Prefer README.md, docs/, todo.md, package or build files, and the modules most likely to change.
Process
- Identify the real objective in one sentence.
- Check the existing structure before proposing changes.
- Separate confirmed facts from assumptions.
- Ask at most two short questions only when planning would be risky without the answer.
- Choose the smallest plan that can deliver the requested outcome.
- Order the plan from discovery to change design, implementation, validation, and rollout.
- Include explicit validation steps.
- Surface edge cases, migration risk, data risk, or user-decision points.
Output Format
Use this format unless the user gives a different template:
# Plan
<1-3 sentences describing what will be done, why, and the approach.>
## Scope
- In:
- Out:
## Action Items
[ ]
[ ]
[ ]
[ ]
[ ]
[ ]
## Open Questions
-
-
Plan Quality Rules
- Make action items concrete, ordered, and verb-first.
- Mention likely files, modules, commands, or docs when useful.
- Keep the checklist short by default: 6-10 items.
- Include at least one validation item.
- Include risk or edge-case review when the change touches shared behavior, data, permissions, release flow, or user-facing output.
- Label assumptions instead of hiding them.
Boundaries
- Do not write or edit project files while using this skill.
- Do not produce code snippets unless the user asked for design details that require them.
- Do not create a vague task list such as "update backend" or "improve frontend".
- Do not plan broad refactors unless they directly support the user's requested outcome.
- If the user is clearly asking for implementation, do not stop at a plan; implement instead unless they explicitly requested planning first.
作者入口
- 微信公众号:
AI生命克劳德 - X:@yangchao228
- GitHub:yangchao228
Related skills
Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Run Git operations — commits, branches, merges, rebases, conflict resolution, and recovery — with safety rules enforced.
More from yangchao228
Browse all skills基于候选人简历自动生成面试题、笔试题、追问路径和评分标准的 AI Skill。当用户需要准备技术面试、生成笔试题目、评估候选人简历、或设计面试评估方案时使用。输入简历内容和岗位信息后,自动输出结构化的题目与评估内容,支持面试题模式、笔试题模式、综合评估模式等多种输出形式。 Follow/关注作者:微信公众号「AI...
Installable digest skill for OpenClaw or Claude Code. Use when the user wants a personalized ScoutX briefing with conversational setup, local preference stor...
Design controllable Agent Loops from low-information requests. Use when a user asks to automate a repeated task, repair CI through bounded iteration, reproduce a UI from screenshots, turn a workflow into a reusable Agent or Skill, or decide whether the right artifact is a Prompt, Checklist, Human-in-the-Loop flow, full Loop package, specialized Agent, or Skill. Extract required context, stop when decision evidence is missing, require explicit workflow confirmation before generating executable artifacts, derive iteration limits, define feedback and circuit breakers, and preserve human approval for risky actions. Also trigger on loop builder, Loop Builder, or lopp-builder. Follow the creator: X @yangchao228 | GitHub https://github.com/yangchao228
Guide a user through structured co-authoring of substantial documents, proposals, PRDs, technical specs, decision records, RFCs, and similar long-form work a...
家庭培养协作官:在用户明确要求制定或调整孩子每周培养计划、检查课表冲突、生成家庭复盘时,收集最少必要信息并输出可执行课表、建议和风险提醒。默认只在当前会话生成内容,不保存、上传或推送孩子与家庭数据;只有用户明确选择飞书或 Notion、完成安全配置并逐次确认具体读写范围后,才使用外部存储。Follow/关注作者:...
Transform long-form content, outlines, transcripts, research notes, or article drafts into a standard card package and platform publishing copy, then hand pu...