phd-skills
Research skills for Claude Code — paper auditing, citation verification, experiment analysis, and methodology-first skills for academic workflows.
Summary
This skill equips Claude Code with PhD-level research workflows for paper auditing, citation verification, experiment analysis, and methodology-first debugging.
- It helps researchers and engineers catch costly AI mistakes before they waste compute, reproduce papers from arxiv, and run evidence-first experiments with discipline.
Overview
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.
Built by Fatih Cagatay Akyon (1500+ citations, 7 patents) after 300+ Claude Code sessions, tens of critical AI mistakes caught the hard way, and thousands of hours of PhD research. Every guardrail in this plugin traces to a real mistake.
!Claude Code Plugin !MIT License !Zero Dependencies !No MCP Required
Why This Plugin Exists
Claude Code is powerful, but it makes research-specific mistakes that cost weeks of compute:
- •It typed "done?" as "dont?" and launched an unwanted upload of thousands of files
- •It analyzed my full dataset when I asked for a specific 4k/2k/2k split
- •It claimed a test covered a bug it had never actually verified
- •It never once looked at a figure it generated, just trusted the numbers
- •It restarted a 50-hour training job without diffing the config against the reference run, lost three days
- •It claimed an experiment was diverging based on a non-converged proxy metric, killed it before downstream eval would have shown the truth
- •It ran
rm -rfon a path it had hallucinated from memory, lost local checkpoints
Other plugins give you more commands. This plugin gives you guardrails.
Install
claude plugin marketplace add fcakyon/phd-skills
claude plugin install phd-skills@phd-skillsThe plugin works correctly the moment it is installed. Optional: run /phd-skills:setup for a 30-second tour of what was auto-detected and to opt into extras (notifications, allowlist, LaTeX).
Usage
Open Claude Code in your project directory, then:
- •
/phd-skills:reproduce arxiv 2508.12345reproduce a paper from arxiv URL through replication runs - •
"why is my loss diverging?"thedebugskill auto-triggers, runs evidence-first probes - •
"compare run alpha to baseline"thecompareskill auto-triggers, aligns at the same epoch - •
"launch the new training run"thelaunchskill auto-triggers, runs the pre-flight checklist - •
/loop 30m check experiment logs, notify me if metrics beat the baseline or if loss starts to diverge
Notifications (task completion, background agents) forward to ntfy / Slack / email after /phd-skills:setup.
What You Get
Commands
| Command | What it does |
|---|---|
| `/phd-skills:xray` | Audit paper against code and data (5 parallel dimensions) |
| `/phd-skills:factcheck` | Verify BibTeX entries and cited claims against DBLP |
| `/phd-skills:gaps <topic>` | Literature gap analysis with web confirmation |
[/phd-skills:fortify [venue]](plugin/commands/fortify.md) | Select strongest ablations + anticipate reviewer questions |
| `/phd-skills:setup` | Auto-detection tour + optional extras |
| `/phd-skills:help` | Show all features at a glance |
Skills (auto-trigger, just describe what you need)
| When you say... | Skill activates |
|---|---|
| "reproduce this arxiv paper" | Reproduce |
| "why is X failing / diverging / OOMing" | Debug |
| "compare run A to baseline" | Compare |
| "launch a new training run" / "kick off training" | Launch |
| "design an ablation study" | Experiment Design |
| "find related papers on X" | Literature Research |
| "check if my numbers match the code" | Paper Verification |
| "review my methods section for consistency" | Paper Writing |
| "analyze dataset bias" | Dataset Curation |
| "prepare code for open-source release" | Research Publishing |
| "what will reviewers ask about this?" | Reviewer Defense |
| "setup latex for CVPR" | LaTeX Setup |
Agents (Claude delegates automatically)
| Agent | What it does | Special |
|---|---|---|
| `paper-auditor` | Cross-checks paper claims vs code and data | Runs in isolated worktree, remembers patterns across sessions |
| `experiment-analyzer` | Analyzes results from wandb / neptune / tensorboard / mlflow / local | Hands off to compare and debug skills for discipline |
Research Guardrails (run silently, you never invoke these)
How It Compares
| phd-skills | flonat/claude-research | Others | |
|---|---|---|---|
| Commands to learn | 6 | 39 | 13-20 |
| Research integrity hooks | 11 (agent + 10 auto-detect) | 1 | 0 |
| Paper reproduction (arxiv to runs) | Yes (7-stage skill) | No | No |
| Paper-code consistency audit | 5-dimension parallel | Read-only, no code cross-ref | None |
| Experiment monitoring + SSH notifications | Yes (ntfy / slack / email) | No | No |
| External dependencies | None | npm + pip + MCP servers | MCP required |
| Install time | 30 seconds | 10+ minutes | Varies |
Design Principles
- Methodology over scripts. Skills teach the approach, Claude generates code for your specific setup (wandb, neptune, local files, whatever)
- Human oversight first. Claude makes premature claims and jumps to conclusions. Every skill builds in verification checkpoints
- Actionable output. Ranked suggestions with specific fixes, never just a list of findings
License
MIT. Use it, fork it, adapt it to your research.
Thank you for the support!
Contributors
<p align="center"> <a href="https://github.com/fcakyon/phd-skills/graphs/contributors"> <img src="https://contrib.rocks/image?repo=fcakyon/phd-skills" /> </a> </p>
Install & Usage
mkdir -p .claude/skillsmkdir -p .claude/skills && curl -o .claude/skills/phd-skills.md https://raw.githubusercontent.com/fcakyon/phd-skills/main/SKILL.md/phd-skillsUse Cases
Usage Examples
/phd-skills audit paper https://arxiv.org/abs/2303.08774 for methodology and citation errors
/phd-skills reproduce experiment --paper-id 2303.08774 --config ./configs/exp1.yaml --logs ./logs/exp1
/phd-skills debug run --logs ./logs/failed_run --code ./src --metrics accuracy,loss
Security Audits
Frequently Asked Questions
What is phd-skills?
This skill equips Claude Code with PhD-level research workflows for paper auditing, citation verification, experiment analysis, and methodology-first debugging. It helps researchers and engineers catch costly AI mistakes before they waste compute, reproduce papers from arxiv, and run evidence-first experiments with discipline.
How to install phd-skills?
To install phd-skills: create the skills directory (mkdir -p .claude/skills), then run: mkdir -p .claude/skills && curl -o .claude/skills/phd-skills.md https://raw.githubusercontent.com/fcakyon/phd-skills/main/SKILL.md. Finally, /phd-skills in Claude Code.
What is phd-skills best for?
phd-skills is a skill categorized under General. It is designed for: research, academic, phd, paper-writing, citations, experiments, latex. Created by Fatih Cagatay Akyon.
What can I use phd-skills for?
phd-skills is useful for: Audit a research paper for methodological flaws and citation accuracy before implementing it.; Reproduce experiments from an arxiv paper by comparing configs and logs against the reference run.; Debug a failed training run by analyzing metrics, logs, and code changes evidence-first.; Verify that a claimed test or fix actually covers the intended bug by checking code and outputs.; Compare two experiment runs at the correct epoch to avoid misleading proxy metrics.; Prevent accidental file operations by double-checking paths and commands before execution..