AI Research Skills
Open library of AI research and engineering skills (training, fine-tuning, evaluation and more) for Claude Code, Codex and Gemini agents.
Test results
Run with our skill harness: the skill alone in a throwaway project, invoked by name, and the real output file checked. Skills are tested in Claude Code and Cursor only so far.
| Client | Result | Last passed | What we checked |
|---|---|---|---|
| Claude Code 2.1.296 (Claude Code) | Passed Tested 2026-10-26 | 2026-10-26 | figure: {'valid 1-page PDF': True, 'legend Baseline': True, 'legend Ours': True, 'x label with token': True, 'plotting script saved (reproducible)': True}; scripts=['plot.py']; pdf text='1.0 0.8 0.6 Accuracy 0.4 0.2 Base |
| Cursor 2026.10.22-27dcf5f | Passed Tested 2026-10-26 | 2026-10-26 | figure: {'valid 1-page PDF': True, 'legend Baseline': True, 'legend Ours': True, 'x label with token': True, 'plotting script saved (reproducible)': True}; scripts=['plot.py']; pdf text='0.8 0.7 0.6 Accuracy 0.5 0.4 0.3 |
Skill version: github.com/Orchestra-Research/AI-Research-SKILLs @ 773a5294 (2026-06-15).
Get it
The skill’s files and install instructions are in its repository: github.com/Orchestra-Research/AI-Research-SKILLs.