compare
Same-epoch comparison of training runs across wandb, neptune, tensorboard, or mlflow. Aligns runs at the student's current step…
Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation. Triggers on phrases like "setup latex", "biber vs bibtex", "latex compilation error", "install latex
$ npx -y skills add fcakyon/phd-skills --skill latex-setup --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/latex-setupContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation. Triggers on phrases like "setup latex", "biber vs bibtex", "latex compilation error", "install latex
name: latex-setup description: > Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation. Triggers on phrases like "setup latex", "biber vs bibtex", "latex compilation error", "install latex packages", "venue template", or "texlive setup".
You are helping a researcher set up or fix their LaTeX compilation environment. Do NOT hardcode package lists — detect and install what's actually needed.
Before installing anything:
1. **Check installed TeX distribution**:
which pdflatex && pdflatex --version which xelatex && xelatex --version which lualatex && lualatex --version
2. **Check bibliography processor**:
which biber && biber --version which bibtex && bibtex --version
3. **Check package manager**:
which tlmgr && tlmgr --version
Read the main .tex file to determine requirements:
1. **Document class**: `\documentclass{article}`, `\documentclass{IEEEtran}`, etc. 2. **Bibliography system**:
3. **Required packages**: extract from all `\usepackage{...}` declarations 4. **Special requirements**: TikZ, minted (needs pygments), algorithm2e, etc.
If the user mentions a venue, search for the official template:
Common venues and their requirements: | Venue | Class | Bib system | Notes | |-------|-------|-----------|-------| | CVPR/ECCV | Custom class file | bibtex | Usually provided in template | | NeurIPS | neurips_20XX.sty | natbib + bibtex | Style file changes yearly | | ICLR | iclr20XX_conference.sty | natbib + bibtex | OpenReview format | | ACL/EMNLP | acl.cls | bibtex | ACL Anthology format | | IEEE | IEEEtran.cls | bibtex | Column formatting specific | | Springer | llncs.cls | bibtex or biblatex | Depends on series |
Based on analysis, install only what's missing:
# Base installation (if nothing installed) sudo apt install texlive-base texlive-latex-recommended # Common extras sudo apt install texlive-latex-extra # most \usepackage needs sudo apt install texlive-fonts-recommended texlive-fonts-extra sudo apt install texlive-bibtex-extra biber # if biblatex used sudo apt install texlive-science # algorithm2e, etc.
# Full installation (recommended) brew install --cask mactex # Minimal brew install --cask basictex sudo tlmgr update --self sudo tlmgr install <package-name>
# If specific packages are missing sudo tlmgr install <package-name>
Set up the correct compilation pipeline:
pdflatex main.tex bibtex main pdflatex main.tex pdflatex main.tex
pdflatex main.tex biber main pdflatex main.tex pdflatex main.tex
After configuration:
1. Run the full compilation pipeline 2. Check the PDF opens correctly 3. Verify bibliography entries appear 4. Check for any remaining warnings in the .log file
Produce: 1. **Current state**: what's installed, what's missing 2. **Project requirements**: detected from .tex files 3. **Installation commands**: only what's needed, OS-specific 4. **Compilation command**: the exact pipeline for this project 5. **Verification**: confirm successful compilation
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.
Same-epoch comparison of training runs across wandb, neptune, tensorboard, or mlflow. Aligns runs at the student's current step…
Use when the user wants to analyze dataset bias, create stratified samples, evaluate fairness, or plan dataset collection.…
Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU…
Use when the user wants to design experiments, plan ablation studies, structure baselines, or create incremental evaluation…
Pre-flight checklist for long-running ML training jobs covering config diff, run naming, path verification, monitoring setup, and…
Use when the user wants to find related work, survey a research area, identify literature gaps, or discover open-source…