agentleFS
Sign inStart free
cellrishi-codecellrishi-code/claude-skills-atlas/skills/research/source-verification/SKILL.md

source-verification

Skill6 starsChanged 40 days agoMITView on GitHub

Verify important factual claims before they are repeated in research, technical writing, or documentation. Use when sources may be outdated, secondary, conflicting, or difficult to interpret.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 6

    Distinctive

    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:

    Verify the support behind a claim rather than merely collecting links.

    line 8
  2. Distinctive:

    Write the exact claim being checked.

    line 12
  3. Distinctive:

    Check whether the source actually supports the claim.

    line 15
  4. Distinctive:

    Check scope, population, version, and date.

    line 16
  5. Distinctive:

    Look for credible contradictory evidence when consequential.

    line 17
  6. Distinctive:

    Search-result snippets used as evidence

    line 22

“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

Source Verification

Verify the support behind a claim rather than merely collecting links.

Process

  1. Write the exact claim being checked.
  2. Identify the source type and publication date.
  3. Locate the original or highest-authority source available.
  4. Check whether the source actually supports the claim.
  5. Check scope, population, version, and date.
  6. Look for credible contradictory evidence when consequential.
  7. Record limitations without pretending to have certainty.

Red flags

  • Search-result snippets used as evidence
  • Secondary summaries that overstate the original source
  • Outdated documentation for changing software
  • Claims detached from their original context
  • Unclear authorship or provenance
  • Statistics without a defined population or time period

Output

For each claim:

  • Claim
  • Best source
  • Source type and date
  • Supporting evidence
  • Scope and caveats
  • Contradictory evidence
  • Verification status

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