agentsclimarketplace
Sign in

Research plan implement

Skill wchen02/cursor-agent-learning/.cursor/skills/research-plan-implement

Research codebase first, then plan, then implement. Use when the user has an unclear or large task and wants research before planning and implementation.From its SKILL.md

Install
npx -y skills add wchen02/cursor-agent-learning --skill research-plan-implement

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.7 KB, 351 tokens by cl100k_base, as published. Nobody here has run it

Research → Plan → Implement

This skill runs a research-first workflow for unclear or large tasks: research the codebase and docs, then plan, then implement.

Steps

  1. Research

    • Use the explore subagent (or main agent) to search the codebase and docs for the user’s goal.
    • Summarize: what exists, current patterns, what’s missing. Answer what the codebase already does and what would need to change.

  2. Plan

    • Invoke the planner subagent with the research summary and the user’s goal.
    • Capture scope, numbered steps, dependencies, and notes. Do not write code yet.

  3. Implement

    • Execute the plan step by step. Follow project rules (e.g. @general-conventions, @api-conventions when relevant).
    • If the user asked for “first N steps only,” implement only those and say what’s left for later.

  4. Verify (optional)

    • Optionally invoke the verifier subagent to confirm the implementation matches the plan, tests pass, and nothing obvious is broken.
    • If the user did not ask for verification, you may skip this step and report completion.

Notes

  • If the user only asked for research, stop after step 1 and present the research summary.
  • If the user only asked for research and plan, stop after step 2 and present the plan.
  • Subagents used: explore (built-in), planner, verifier (optional). Written workflow: examples/agent-frameworks/research-plan-implement.md.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,834. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.