agentleFS
Sign inStart free
cobusgreylingcobusgreyling/grok-bot-templates/skills/cited-research/SKILL.md

cited-research

Skill14 starsChanged 3 months agoMITView on GitHub

Paste this into Grok Bot after a successful run: Save the process we just used as a skill called “Cited Research”. A useful skill states the six fields from Skills and routines. A question needs a brief that a skeptic could audit: claims, sources, disagreements, and what was not found. Every non-trivial claim has a URL. No unsourced statistics. Disagreements are represented, not averaged away. A brief with Claims, Evidence, Disagreements, Not found, and Recommended next read. Do not contact…

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Search for primary sources.

    line 23
  2. Distinctive:

    Every non-trivial claim has a URL.

    line 30
  3. Distinctive:

    Do not contact people for interviews.

    line 40

≈ “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

Cited Research

Paste this into Grok Bot after a successful run:

Save the process we just used as a skill called “Cited Research”.

A useful skill states the six fields from Skills and routines.

1. When to use it

A question needs a brief that a skeptic could audit: claims, sources, disagreements, and what was not found.

2. Required inputs and access

  • The question
  • Scope limits (dates, domains, what not to use)
  • Preferred primary sources when the owner named them

3. Sequence of work

  1. Restate the question and the scope. Confirm before a long run if ambiguous.
  2. Search for primary sources. Prefer docs, papers, official pages, and filings over recaps.
  3. For contested claims, find at least two independent sources or label the claim unverified.
  4. Separate facts, inferences, and open questions.
  5. List what you could not find. That list is part of the deliverable.

4. How to validate the result

Every non-trivial claim has a URL. No unsourced statistics. Disagreements are represented, not averaged away.

5. What to return

A brief with Claims, Evidence, Disagreements, Not found, and Recommended next read.

6. What requires approval

Do not contact people for interviews. Do not pay for papers or datasets. Do not publish the brief.

Type / in the composer to reference a saved skill. If it does not appear, open Settings → Plugins → Yours and enable it for this Bot.

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