fortify
Select strongest ablations and anticipate reviewer questions. Reads paper and experiment results to prepare for peer review.
Verify BibTeX entries and cited claims against DBLP and web sources. Checks author names, venues, years, and specific numerical claims.
> /plugin marketplace add fcakyon/phd-skills > /plugin install phd-skills@phd-skills
How it fires
How this command gets triggered: by you, by Claude, or both.
/factcheckContext preview
What this command does when you run it.
Verify BibTeX entries and cited claims against DBLP and web sources. Checks author names, venues, years, and specific numerical claims.
description: > Verify BibTeX entries and cited claims against DBLP and web sources. Checks author names, venues, years, and specific numerical claims. allowed-tools: Read, Glob, Grep, Bash, WebSearch, WebFetch
You are verifying the accuracy of all citations in a research paper.
For each BibTeX entry:
1. **Search DBLP** for the paper title via web search (query: `site:dblp.org "paper title"`) 2. **Verify**:
3. **Flag** any discrepancies with the corrected values
Search the .tex files for citation patterns (`\cite{...}`, `\citep{...}`, `\citet{...}`).
For each citation that includes a specific claim (especially numerical): 1. Extract the claim and the cited paper key 2. Search for the cited paper online 3. Verify the claim appears in the paper (specific table, figure, or text) 4. If the claim cannot be verified, suggest qualitative rewording
Produce a structured report:
## Citation Verification Report ### BibTeX Corrections Needed | Key | Field | Current | Correct | Source | |-----|-------|---------|---------|--------| ### Unverified Claims | .tex location | Claim | Cited paper | Status | Suggestion | |--------------|-------|------------|--------|------------| ### Corrected BibTeX Entries (Ready-to-paste corrected entries for any that need fixing)
Catch AI mistakes before they cost weeks of compute. Reproduce papers from arxiv. Debug runs evidence-first. Compare experiments at the right epoch. Launch with discipline.
Select strongest ablations and anticipate reviewer questions. Reads paper and experiment results to prepare for peer review.
Literature gap analysis with web confirmation. Takes a research topic or question and maps existing work to find what's missing.
Show all phd-skills features, commands, skills, agents, and hooks at a glance. Use for in-session discoverability.
30-second auto-detection tour, then optional configuration of notifications, CLI allowlist, research CLAUDE.md rules, and LaTeX…