agentleFS
sherificansherifican/Agent-FleetOps/skills/research-dispatch/SKILL.md

research-dispatch

Skill34 starsChanged 37 days agoMITView on GitHub

Dispatch external research to independent workers and reconcile claims with source-backed confidence labels.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Use multiple independent research legs when current or external facts materially affect a decision.

    line 9
  2. Distinctive:

    Read current feedback and constraints before dispatching.

    line 13

≈ “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

Research Dispatch

Overview

Use multiple independent research legs when current or external facts materially affect a decision. A single worker can miss sources, misread a page, or produce plausible unsupported specifics.

Procedure

  1. Frame one precise question, the deliverable structure, and what evidence would answer it.
  2. Read current feedback and constraints before dispatching.
  3. Send equivalent briefs to at least two suitable research workers. Require each to retrieve the live primary pages it cites.
  4. Store each leg as a separately named artifact under the project's documented convention.
  5. Reconcile into a final brief: compare each critical claim, record confidence, and list unresolved points.

Reconciliation rules

  • Agreement between independently sourced legs raises confidence but does not replace source inspection where stakes require it.
  • A claim found in only one leg remains flagged until directly verified.
  • A leg without successful retrieval is not evidence for its specific quotations, dates, or figures.

Pitfalls

  • Treating recalled information as a current fetch.
  • Averaging contradictory reports without checking the cited primary source.
  • Hiding which claims remain unverified.

Verification checklist

  • Two or more independent legs were used when appropriate.
  • Each factual claim has a source or an explicit gap label.
  • The reconcile identifies disagreements and unresolved claims.

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.