agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/cat-agent-skills/submissions/consumer-market-insight-synthesis/skills/research-retrieve/SKILL.md

research-retrieve

Skill95 starsChanged 6 days agoMITView on GitHub

Retrieves and ranks prior research, panel extracts and campaign results relevant to the question. Use when the user says "what do we already know about <topic>", "find prior research on", "have we studied this before", or an insight request begins.

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:

    Start of every insight run.

    line 11
  2. Distinctive:

    Every study carries its repository identity.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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 Retrieve

Purpose

Rank the repository against the question (market + topics + recency, #1.1) so decades of research get reused, not re-commissioned.

When to use

Start of every insight run.

Inputs

Question (market, topics, use_case DECLARED UP FRONT - internal vs external gates everything downstream, #4.2); research index. Emits the entry hop (schema in contracts/).

Steps

  1. Structure question.json: market, topics, recency floor, use_case, as_of_date.
  2. Retrieval + ranking happen in trend_compare's first pass; this skill assembles the question and index.

Output

question.json - the entry hop.

Grounding requirements

Every study carries its repository identity; nothing cited that was not retrieved (#1.1).

Constraints

  • Scope #5.1: retrieval and citation - no analysis over large tabular files (known boundary), no forecasting.

Escalation / uncertainty

Undeclared use_case: ask - the rights gate cannot run without it (#4.2).

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.

Check your setup, free