agentleFS
QuixiAIQuixiAI/agi-memory/skills/installed/research/SKILL.md

research

Skill617 starsChanged 10 months agoMITView on GitHub

How to research topics using web tools

We split this skill into the rules it gives an agent

9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 163 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When investigating a topic that requires current or external information:

    line 14
  2. Very specific:

    Use web_search for broad queries to find relevant sources

    line 16
  3. Very specific:

    Use web_fetch to read the most promising results in full

    line 17
  4. Distinctive:

    When a goal requires information you don't have in memory

    line 23
  5. Distinctive:

    When existing memories have low confidence or are outdated

    line 24
  6. Distinctive:

    When the user asks about recent events or facts

    line 25
  7. Distinctive:

    When you need to verify something before acting on it

    line 26
  8. Distinctive:

    Use specific, targeted search queries rather than broad ones

    line 30
  9. Distinctive:

    Prefer authoritative sources (official docs, academic, established media)

    line 33

“Common” is measured: kept by at least 6 in 10 of the 163 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

Research Methodology

When investigating a topic that requires current or external information:

  1. Use web_search for broad queries to find relevant sources
  2. Use web_fetch to read the most promising results in full
  3. Cross-reference findings with existing memories via recall
  4. Store important findings with remember for future reference

When to Research

  • When a goal requires information you don't have in memory
  • When existing memories have low confidence or are outdated
  • When the user asks about recent events or facts
  • When you need to verify something before acting on it

Research Quality

  • Use specific, targeted search queries rather than broad ones
  • Cross-reference multiple sources before accepting a claim
  • Note the source URL when storing findings as memories
  • Prefer authoritative sources (official docs, academic, established media)

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.

Reviews can't be read right now.

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.