Other documented method
Last commit on March 24, 2026·Created on November 3, 2025
Orchestra-Research/AI-Research-SKILLs
“Turns research workflows into instructions an agent can follow.”
Combined rank
#35
across all skills
In Research
#3
category rank
Stars
11.4k
+1.8% in last 7d
Forks
835
+1.6% in last 7d
Watchers
51
-1.9% in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
Description
These skill files turn an agent into a research assistant that can design experiments, train models, interpret internals, audit safety, and deploy inference. They are built for AI research scientists, LLM fine-tuning engineers, distributed training engineers, and MLOps teams who need reproducible, agent-guided workflows across the full model lifecycle.
WHO IT'S FOR
AI Research Scientists
orchestrating autonomous research experiments
LLM Fine-Tuning Engineers
fine-tuning models with RL and preference optimization
Distributed Training Engineers
scaling LLM training across GPU clusters
MLOps and Infrastructure Teams
managing experiment tracking and GPU infrastructure
30 Days of GitHub Stars
+955 stars↑ 9.5% monthly change
Jul 7Jul 14Jul 21Jul 28Aug 5
Compatibility & Install98 Skills · 5 Compatible agents · 3 categories · 1 install path
Compatible agents
❯Claude Code❯Codex❯Gemini CLI❯OpenClaw❯DeepSeek
Categories
ResearchAutomationSoftware Engineering
Install via
Repository instructions
Also in this category4 of 29