Borrowing it
Nothing to install: this file belongs to AlessandroCaforio/Academic-Writing. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AlessandroCaforio/Academic-Writing/main/.claude/skills/verify-claims/SKILL.mdgit clone --depth 1 https://github.com/AlessandroCaforio/Academic-WritingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alessandrocaforio/academic-writing/verify-claims)<a href="https://agentmods.dev/skills/alessandrocaforio/academic-writing/verify-claims"><img src="https://agentmods.dev/badge/skills/alessandrocaforio/academic-writing/verify-claims/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alessandrocaforio/academic-writing/verify-claims"><img src="https://agentmods.dev/badge/skills/alessandrocaforio/academic-writing/verify-claims.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00017 | $0.00333 |
| Opus 5.5 | $0.00007 | $0.00133 |
| Sonnet 5.5 | $0.00003 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
verify-claims scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Verify Claims
Verify claims made in the thesis against the indexed literature corpus (105 papers in ChromaDB). The argument can be a chapter name or a specific claim to verify.
Instructions
-
If the argument is a chapter name (e.g.,
04_methodology):- Read the chapter at
thesis/chapters/$ARGUMENTS.tex - Extract all factual claims that cite literature
- Query the RAG system for each claim
- Read the chapter at
-
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.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 37 lines · 17 tokens per session scan A 3818418279ec
verify-claims is a skill published in the GitHub repository AlessandroCaforio/Academic-Writing (23 stars, last pushed 7mo ago), licensed MIT. It adds 17 tokens to every session and 333 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
oracle
Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.
seek
Designing search engines and vector DBs for full-text, vector, and hybrid retrieval, including permission-aware retrieval for multi-tenant or per-role corpora. Use for search design, index optimization, the RAG retrieval layer, or deciding where ACL filtering belongs in the query path.
corpus-grounding-expander
Fetches and normalizes multi-version public-domain corpora into a single verified-axiom store for verbatim-relay grounding, recording per-version license and provenance.
rag-vs-finetune-decision
The model-capability decision tree — prompt-engineering first, then RAG for missing knowledge, then fine-tuning for missing behavior/format or cost/latency, climbing only as far as needed. Covers the cost/latency/maintenance tradeoffs of each rung and when each is the wrong choice (especially the premature-fine-tune…
cite-or-refuse
Ground answers in retrieved user-corpus spans; cite every claim or refuse when retrieval is empty.
ai-use-case-scoping
The should-this-even-be-AI gate — decide where an LLM belongs versus deterministic rules, frame error tolerance as a product decision, and climb the capability ladder (rules → prompt → RAG → fine-tune) only as far as the problem demands. Stops the "AI everywhere" anti-pattern before it reaches the spec. Hosted by…