factcheck
Verify BibTeX entries and cited claims against DBLP and web sources. Checks author names, venues, years, and specific numerical…
Select strongest ablations and anticipate reviewer questions. Reads paper and experiment results to prepare for peer review.
> /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.
/fortifyContext preview
What this command does when you run it.
Select strongest ablations and anticipate reviewer questions. Reads paper and experiment results to prepare for peer review.
description: > Select strongest ablations and anticipate reviewer questions. Reads paper and experiment results to prepare for peer review. argument-hint: "<venue name (optional)>" allowed-tools: Agent, Read, Glob, Grep, Bash, WebSearch, WebFetch
You are helping strengthen a paper before submission by selecting the best ablations and preparing for reviewer questions.
For each available ablation or experiment:
| Run | Factor Changed | Primary Metric Delta | Narrative Strength | Include? | |-----|---------------|--------------------|--------------------|----------|
Ranking criteria: 1. **Impact magnitude**: largest metric improvement = most convincing 2. **Narrative strength**: directly supports a specific paper claim 3. **Uniqueness**: shows something no other ablation shows 4. **Anticipated questions**: preemptively answers likely reviewer concerns
Recommend: main paper (top 3-5) vs supplementary (rest).
Consider the venue: $ARGUMENTS (if provided, adjust expectations accordingly).
Generate the **top 10 most likely reviewer questions**:
1. [Question] Why they'd ask: [motivation] Answerable now: [Yes — point to data / No — needs new experiment] Draft response: [2-3 sentences if answerable]
List specific weaknesses a reviewer might flag:
## Fortification Report ### Recommended Ablation Subset [Table with justification for each] ### Top 10 Anticipated Questions [Numbered list with draft responses] ### Weaknesses to Address [Prioritized list with suggested text edits] ### Suggested Edits [Specific paragraph-level improvements]
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.
Verify BibTeX entries and cited claims against DBLP and web sources. Checks author names, venues, years, and specific numerical…
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…