yiming-qing/research-agent---1st-place-in-alibaba-cloud-data-ai-competition/create-plan
Claude Code and agent skill by yiming-qing/research-agent---1st-place-in-alibaba-cloud-data-ai-competition
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Create a concise, actionable plan. Use when a user explicitly asks for a plan or next steps.
Install
npx vskill@latest install yiming-qing/research-agent---1st-place-in-alibaba-cloud-data-ai-competition/create-planSKILL.md
Create Plan
Goal
Turn a user request into one clear, actionable plan that an agent (chat, websearch, or tool-using) can directly follow.
The plan should be concise, structured, and focused on what to do next, not how to implement details.
Operating principles
- Operate in read-only / planning mode (no execution).
- Prefer clarity over completeness.
- Optimize for agent executability: each step should be something an agent can actually do.
- Assume the agent may have access to tools such as search, browsing, or analysis, but do not depend on any specific tool unless required.
Minimal workflow
- Understand the request and context
- Identify the user’s goal, success criteria, and constraints.
- Use available context (conversation, provided links, known domain knowledge).
- If relevant, note assumptions about audience, timeframe, or format.
- Ask follow-ups only if blocking
- Ask at most 1–2 questions.
- Only ask if the plan would be meaningfully wrong without the answer.
- Prefer assumptions over questions when safe; make assumptions explicit if needed.
- Create the plan using the template below
- Start with 1–3 sentences describing intent and overall approach.
- Clearly define what is in scope and out of scope.
- Provide a short, ordered checklist of concrete actions (default 6–10).
- Steps should be atomic, verb-first, and outcome-oriented.
- Typical flow: understanding → gathering info → analysis → synthesis → validation → delivery.
- Include:
- At least one validation / quality check step.
- At least one risk, edge case, or uncertainty step when applicable.
- If important unknowns remain, add a small Open questions section (max 3).
- Output only the plan
- Do not include meta commentary, explanations, or alternatives.
- Do not include implementation details beyond what’s necessary for planning.
Plan template (follow exactly)
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/create-plan/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/yiming-qing/research-agent---1st-place-in-alibaba-cloud-data-ai-competition/create-plan)