Claude Researcher banner
maher-naija-pro maher-naija-pro

Claude Researcher

Testing community

Description

Structured research skill for Claude — parallel web search, test solutions, weighted scoring decisions

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Claude Researcher Skill

Claude Researcher

Give Claude a research question. Get a structured report with tested solutions and a scored decision.

Demo

Install in 30s · See example output · ⭐ Star if useful


This skill gives Claude a structured research workflow: search the web in parallel, organize findings into folders, optionally test each solution, and produce a weighted scoring decision.

What This Skill Does

  • Creates a dedicated _problem/ workspace.
  • Searches for candidate solutions from multiple source types (community, articles, code repos, academic, reference docs, videos).
  • Organizes each solution into its own directory with documentation notes.
  • Produces a per-solution README.md with summary, sources, pros, and cons.
  • Optionally tests each solution and records reproducible outcomes.
  • Generates a final decision/DECISION.md with weighted scoring and a recommended choice.

Install

mkdir -p ~/.claude/skills/researcher
curl -o ~/.claude/skills/researcher/SKILL.md \
  https://raw.githubusercontent.com/maher-naija-pro/claude-researcher/main/researcher/SKILL.md

Then restart your Claude CLI session so the skill is reloaded.

How To Use

Ask for research tasks with prompts like:

  • "Research solutions for fixing slow API response times."
  • "Compare approaches for background jobs in Node.js."
  • "Investigate options for vector databases for RAG."

The skill follows this flow:

  1. Create problem directory.
  2. Search for candidate solutions in parallel.
  3. Create one directory per solution.
  4. Gather source documentation into markdown files.
  5. Write per-solution summary (README.md).
  6. Optionally test each solution and write `test_results_<s