All authors
Claude Skills by MustafaKemal0146
github.com/MustafaKemal0146961 skills11 installs1,632 views
- PlanPlan mode: write markdown plan to .fetih/plans/, no exec.Votes: 0GitHub stars: 4
- Python DebugpyDebug Python: pdb REPL + debugpy remote (DAP).Votes: 0GitHub stars: 4
- Requesting Code ReviewPre-commit review: security scan, quality gates, auto-fix.Votes: 0GitHub stars: 4
- SpikeThrowaway experiments to validate an idea before build.Votes: 0GitHub stars: 4
- Subagent Driven DevelopmentExecute plans via delegate_task subagents (2-stage review).Votes: 0GitHub stars: 4
- Systematic Debugging4-phase root cause debugging: understand bugs before fixing.Votes: 0GitHub stars: 4
- Test Driven DevelopmentTDD: enforce RED-GREEN-REFACTOR, tests before code.Votes: 0GitHub stars: 4
- Writing PlansWrite implementation plans: bite-sized tasks, paths, code.Votes: 0GitHub stars: 4
- YuanbaoYuanbao (元宝) groups: @mention users, query info/members.Votes: 0GitHub stars: 4
- Tensorrt LlmOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.Votes: 0GitHub stars: 4
- TorchtitanProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.Votes: 0GitHub stars: 4