Packs
4 packscurated
Email Productivity Toolkit
For professionals who want to manage their inbox, draft replies, and send emails with delivery confirmation.
12 skills · pack
@klotzkette
Kanzlei Allgemein
Kanzlei-Allgemein-Plugin (fusioniert mit Cowork): edles Kommandocenter Mandatsannahme/GwG Klage/Replik Vertrag Rechtsprechung Handelsregister beA-Journal Rechnung UStVA Fristenbuch Timesheet RVG Versand-Vor-Check Posteingang Mandantenakte Mahnwesen Tagesbrief Geburtstage Weihnachtskarten.
4 skills · pack
@samyakjhaveri
Sam Superpowers
Fork of obra/superpowers 5.0.7: the 14 core skills (TDD, debugging, collaboration patterns) with the mandatory-gate SessionStart injection replaced by a short judgment-based router. Skills are tools, not gates.
14 skills · pack
@sbroggioadv
Civel Adv Os
Plugin full-stack de contencioso civel brasileiro (Civil Litigation Master) — 64 skills em 9 camadas: procedimento comum (inicial, contestacao, replica, saneamento, instrucao, sentenca), tutelas de urgencia/evidencia, a gama de acoes civeis (indenizatoria, obrigacao de fazer/nao fazer, resolucao/revisional contratual, cobranca/monitoria, consignacao, declaratoria, anulatoria, possessorias, usucapi
64 skills · pack
Results for “repl”
6 skills
More results
smith6jt-cop pytorch-common-pitfalls
Fixes common PyTorch bugs including percentile calculations, LayerNorm for Conv1d, and buffer edge cases in reinforcement learning and neural network code.
3
orchestra-research fine-tuning-with-trl
Fine-tune and align language models using reinforcement learning with TRL, including SFT, DPO, PPO, GRPO, and reward model training.
10.4k · bundle
orchestra-research grpo-rl-training
Expert guidance for implementing GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.
10.4k · bundle
orchestra-research verl-rl-training
Train LLMs with reinforcement learning using verl (Volcano Engine RL), supporting RLHF, GRPO, PPO, and other algorithms for scalable post-training with flexible infrastructure backends.
10.4k · bundle
ecnu-icalk ciou-giou
Replaces GIoU with Complete IoU (CIoU) loss in PyTorch object tracking or detection tasks, combining overlap area, center-point distance, and aspect-ratio similarity for improved bounding-box regression.
559