sundial-org verified
Building open-source Claude skills. 20 skills with 5,882 total stars.
Contributed
20
Total Stars
5.9k
Total Forks
586
Avg Stars
294
Paper reviewer that evaluates machine learning research projects following official ICML reviewer guidelines. Provides c...
Calculate training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens...
Neuro-symbolic AI combining LLMs with symbolic solvers. Use when implementing NL-to-logic translation, integrating Z3/Pr...
Critiques ML conference papers with reviewer-style feedback. Use when users want to anticipate reviewer concerns, identi...
Calculate training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens...
Run OpenAI's Codex CLI agent in non-interactive mode using `codex exec`. Use when delegating coding tasks to Codex, runn...
Guidelines for creating high-quality datasets for LLM post-training (SFT/DPO/RLHF). Use when preparing data for fine-tun...
Fine-tune LLMs using the Tinker API. Covers supervised fine-tuning, reinforcement learning, LoRA training, vision-langua...