agentleFS
Sign inStart free
Shugar86Shugar86/my-agent/skills/deep_research/SKILL.md

deep_research

Skill0 starsChanged 6 months agoMITView on GitHub

Comprehensive deep research with multi-query search, academic sources, structured analysis, and citations.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If critical info is missing, ask 3-5 clarifying questions

    line 26
  2. Distinctive:

    Use deep_search for general web research (3-5 queries minimum)

    line 30
  3. Distinctive:

    Use scholar_search for academic papers (call ONCE to save API costs)

    line 31
  4. Distinctive:

    Use web_scrape to extract details from important URLs

    line 32
  5. Distinctive:

    Document conflicting perspectives with credibility analysis

    line 35
  6. Distinctive:

    Always include source links for verifiable claims

    line 46
  7. Distinctive:

    No unsourced assertions as facts

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Deep Research Skill (from OpenSwarm)

Process

Before Starting

  1. Review the research request carefully
  2. If critical info is missing, ask 3-5 clarifying questions
  3. Once clear, begin research without delay

Conducting Research

  1. Use deep_search for general web research (3-5 queries minimum)
  2. Use scholar_search for academic papers (call ONCE to save API costs)
  3. Use web_scrape to extract details from important URLs
  4. Prioritize sources: official docs > government > academic > news > industry
  5. Record source links for every important claim
  6. Document conflicting perspectives with credibility analysis

Output Format

  1. Executive Summary — 5-10 actionable bullet points
  2. Key Findings — grouped by theme with context
  3. Evidence and Details — with inline citations [Source: URL]
  4. Options — 2-4 paths with pros/cons
  5. Recommendation — clear choice with rationale
  6. Risks, Unknowns, Open Questions — gaps and follow-ups

Notes

  • Always include source links for verifiable claims
  • No unsourced assertions as facts
  • Be transparent about confidence levels
  • Maintain objectivity — evidence over opinions

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.

Check your setup, free