Loading...
Loading...
Found 36 Skills
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
Evidence-based memory optimization from real usage patterns. Analyzes recall performance, identifies bottlenecks, suggests consolidation/pruning/enrichment, and tracks improvement over time via checkpoint Q&A.
Optimize code performance through iterative improvements (max 2 rounds). Benchmark execution time and memory usage, compare against baseline implementations, and generate detailed optimization reports. Supports C++, Python, Java, Rust, and other languages.
Provides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvements for files such as CLAUDE.md. Use when user asks to check, audit, update, improve, fix, maintain, or validate project memory files. Also triggers for "project memory optimization", "CLAUDE.md quality check", "documentation review", or when a project memory file needs to be created from scratch. This skill scans memory files, evaluates quality against standardized criteria, outputs detailed quality reports with scores and recommendations, then makes targeted updates with user approval.
Refactor Pandas code to improve maintainability, readability, and performance. Identifies and fixes loops/.iterrows() that should be vectorized, overuse of .apply() where vectorized alternatives exist, chained indexing patterns, inplace=True usage, inefficient dtypes, missing method chaining opportunities, complex filters, merge operations without validation, and SettingWithCopyWarning patterns. Applies Pandas 2.0+ features including PyArrow backend, Copy-on-Write, vectorized operations, method chaining, .query()/.eval(), optimized dtypes, and pipeline patterns.
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"
Design memory hierarchy with progressive loading for optimal context management. Use when organizing CLAUDE.md imports, implementing just-in-time context loading, or designing priming hierarchies for agents.
Comprehensive Rust coding guidelines with 179 rules across 14 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, API design, memory optimization, performance, testing, and common anti-patterns. Invoke with /rust-skills.
セッション管理の総合窓口。初期化・記憶・状態を一手に引き受けます。Use when managing Claude Code sessions, /session command. Do NOT load for: app user sessions, login state, authentication features.
Fast ASR CLI tool for transcribing audio/video files. Use when user wants to transcribe audio/video, generate subtitles (VTT), convert speech to text with timestamps (JSON), or optimize transcription for low memory.
RTK CLI performance analysis and optimization. Startup time (<10ms), binary size (<5MB), regex compilation, memory usage. Use when adding dependencies, changing initialization, or suspecting regressions.
Process large datasets efficiently using chunk(), chunkById(), lazy(), and cursor() to reduce memory consumption and improve performance