agentleFS
zhouey314-cloudzhouey314-cloud/ai-agent-skills/skills/research-synthesizer/SKILL.md

research-synthesizer

Skill0 starsChanged 51 days agoMITView on GitHub

Compare provided sources, distinguish fact from inference, and surface dated conflicts in a research answer.

5 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use content-repurposer.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when multiple documents or links disagree or when freshness matters.

    line 14
  2. Very specific:

    Run python3 tests/validate.py from the repository root to check this skill's contract and example provenance.

    line 42
  3. Distinctive:

    No live browsing is implied by this skill.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 5 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 Synthesizer

Purpose

Produce a synthesis with traceable citations and explicit disagreement.

When to Use

Use when multiple documents or links disagree or when freshness matters.

Inputs

question, sources: [{id,title,url,date,excerpt}], as_of_date.

Outputs

findings: [{claim,citations,confidence}], conflicts[], gaps[], inferences[].

Workflow

  1. Inventory source dates and whether each is primary or secondary.
  2. Extract relevant claims and quote only short supporting spans.
  3. Group agreement, disagreement and missing evidence separately.
  4. Label inferences as inferences and avoid resolving conflicts without evidence.
  5. Return a concise synthesis with citations and a freshness caveat.

Failure Handling

A broken citation or stale source blocks a current-fact claim. If sources conflict, report the conflict instead of selecting a convenient answer.

Example

synthetic_unverified: two fictional guides disagree on a deadline; the output reports the conflict.

Tests

Run python3 tests/validate.py from the repository root to check this skill's contract and example provenance. This is a structural test, not model-quality evidence.

Limitations

No live browsing is implied by this skill; it can only analyze sources actually supplied or retrieved with authorized tools.

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.