agentleFS
Sign inStart free
AlessandroCaforioAlessandroCaforio/Academic-Writing/.claude/skills/verify-claims/SKILL.md

verify-claims

Skill17 starsChanged 9 months agoMITView on GitHub

Verify thesis claims against the 105-paper literature corpus using RAG

12 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

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

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify claims made in the thesis against the indexed literature corpus (105 papers in ChromaDB).

    line 10
  2. Very specific:

    If the argument is a chapter name (e.g., 04_methodology):

    line 14
  3. Very specific:

    Read the chapter at thesis/chapters/$ARGUMENTS.tex

    line 15
  4. Very specific:

    If the argument is a specific claim (e.g., "Mutz (2018) finds that status threat explains the 2016 vote"):

    line 19

“Common” is measured: kept by at least 6 in 10 of the 12 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

Verify Claims

Verify claims made in the thesis against the indexed literature corpus (105 papers in ChromaDB). The argument can be a chapter name or a specific claim to verify.

Instructions

  1. If the argument is a chapter name (e.g., 04_methodology):
    • Read the chapter at thesis/chapters/$ARGUMENTS.tex
    • Extract all factual claims that cite literature
    • Query the RAG system for each claim
  2. If the argument is a specific claim (e.g., "Mutz (2018) finds that status threat explains the 2016 vote"):
    • Query the RAG system directly for the claim
    • Assess whether it is supported by retrieved evidence

RAG Query Command

cd /Users/alessandro/Projects/Tesi/thesis/references/RAG && source venv/bin/activate && python /Users/alessandro/Projects/Tesi/.claude/skills/verify-claims/scripts/query_rag.py "query" --top-k 5

Additional Resources

  • Concept graph: thesis/references/literature_analysis/concept_graph.json
  • Paper extractions: thesis/references/literature_analysis/paper_extractions/*.json

Output

Return a claim verification report with status (SUPPORTED / PARTIALLY SUPPORTED / UNSUPPORTED / CONTRADICTED) for each claim.

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