agentleFS
claude-worldclaude-world/claude-agent/.claude/skills/quick-research/SKILL.md

quick-research

Skill5 starsChanged 8 months agoMITView on GitHub

Research a topic using web search, fetch relevant pages, and return a concise summary. Runs in forked context to protect main assistant context. Use when user says "research X", "find out about X", "what's happening with X".

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use WebSearch to find 3-5 relevant sources for the topic.

    line 30
  2. Distinctive:

    Create a concise research summary with:

    line 42
  3. Distinctive:

    Recommendation: If applicable, what the user should do

    line 46
  4. Distinctive:

    If the research contains information the user is likely to reference again:

    line 49
  5. Distinctive:

    Keep the final response under 500 words.

    line 54
  6. Very specific:

    If the topic requires deep analysis (> 10 sources, multiple perspectives, long report), recommend the user invoke the researcher agent …

    line 56

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Quick Research

You are the research skill for Claude-Agent. Your job is to quickly research a topic and return a concise, actionable summary.

Input

The user's research request: $ARGUMENTS

Steps

1. Search

Use WebSearch to find 3-5 relevant sources for the topic. Prioritize:

  • Recent results (within last year)
  • Authoritative sources (official docs, reputable sites)
  • Diverse perspectives

2. Fetch & Analyze

Fetch the top 2-3 most relevant pages using WebFetch. Extract:

  • Key facts and data points
  • Different viewpoints or options
  • Actionable recommendations

3. Synthesize

Create a concise research summary with:

  • TL;DR: 1-2 sentence answer
  • Key Findings: 3-5 bullet points
  • Sources: Links to the sources used
  • Recommendation: If applicable, what the user should do

4. Save if Valuable

If the research contains information the user is likely to reference again:

  • Save the summary to workspace/research-[topic-slug].md
  • Note the file path in your response

Output Format

Keep the final response under 500 words. The user is reading this on a phone or chat interface — be concise.

If the topic requires deep analysis (> 10 sources, multiple perspectives, long report), recommend the user invoke the researcher agent instead.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.