phd-skills
PluginResearch guardrails for PhD students: reproduce arXiv papers, debug training anomalies with evidence, compare runs at matched epochs, check paper-code consistency, verify BibTeX, find literature gaps and predict reviewer comments. No MCP or extra dependencies; mostly for ML research.
phd-skills
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 (2000+ citations, 5 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.
Paper search and acquisition use Paper Search CLI, installed with uv and Python 3.10+. See paper search setup. Other skills do not require it.
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-skills
The 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] | 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 | Paper Search CLI for paper workflows | 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
関連リソース
Oh My Paper
PluginA research plugin for Claude Code: commands like /omp:survey, /omp:experiment and /omp:write chain literature review, topic selection, experiments, writing and self-review, with 5 specialized agents and 34 research skills that remember project progress across sessions. Experiments lean toward ML.
LigphiDonk/Oh-my--paper743
ARIS (Auto-claude-code-research-in-sleep)
SkillLets Claude Code push ML research forward unattended: literature review, topic selection, experiment deployment, cross-model review loops and paper writing through rebuttal, in 80+ skills. Codex acts as the independent reviewer by default; other model pairings work too.
wanshuiyin/Auto-claude-code-research-in-sleep17.6k
Feynman
CLIOpen-source research agent: one command runs literature reviews, deep research, paper reviews, paper-code consistency checks and replication plans, searching arXiv, PubMed and more with sources recorded. Good for grad students writing reviews. Run feynman setup to sign in to a model provider.
Companion-Inc/feynman10k
arXiv MCP Server
MCPSearch and download arXiv papers and read the authors' LaTeX source section by section, export BibTeX and follow topic updates, with papers cached locally. No API key needed.
blazickjp/arxiv-mcp-server3.2k
Academic Research Skills
PluginEnd-to-end academic paper plugin: deep research and literature review, writing, multi-perspective simulated peer review, revision and finalization, pausing for your approval at each stage, with built-in citation verification and integrity checks. Licensed CC BY-NC.
Imbad0202/academic-research-skills52.4k
AI Research Skills
PluginPlugin marketplace for AI research with nearly 100 skills in 23 categories, from ideation, fine-tuning and post-training to distributed training, inference serving, evaluation and paper writing, coordinated end to end by the autoresearch skill.
Orchestra-Research/AI-Research-SKILLs13.6k