[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QF1KCV9B95CNE762ADFXE7":3,"skill-same:01M6QF1KCV9B95CNE762ADFXE7":87},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":14,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6QF1KCV9B95CNE762ADFXE7","llama-cpp",null,"Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1\u002FM2\u002FM3 Macs, AMD\u002FIntel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-llama-cpp\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"cpp","Llama","llama cpp","gguf quantization","serving","for","Intel GPUs","AMD GPUs","Non-NVIDIA","Edge Deployment","CPU","bit","python","embedded","use","llm inference","NVIDIA","edge","deployment","inference","2026-11-10 10:12:30",false,"---\nname: llama-cpp\ndescription: Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1\u002FM2\u002FM3 Macs, AMD\u002FIntel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  category: ml-inference-and-ops\n  maintainer: Kalaris Labs\n  tags: Inference Serving, Llama.cpp, CPU Inference, Apple Silicon, Edge Deployment, GGUF, Quantization, Non-NVIDIA, AMD GPUs, Intel GPUs, Embedded\n  dependencies: llama-cpp-python\n---\n\n# llama.cpp\n\nPure C\u002FC++ LLM inference with minimal dependencies, optimized for CPUs and non-NVIDIA hardware.\n\n## When to use llama.cpp\n\n**Use llama.cpp when:**\n- Running on CPU-only machines\n- Deploying on Apple Silicon (M1\u002FM2\u002FM3\u002FM4)\n- Using AMD or Intel GPUs (no CUDA)\n- Edge deployment (Raspberry Pi, embedded systems)\n- Need simple deployment without Docker\u002FPython\n\n**Use TensorRT-LLM instead when:**\n- Have NVIDIA GPUs (A100\u002FH100)\n- Need maximum throughput (100K+ tok\u002Fs)\n- Running in datacenter with CUDA\n\n**Use vLLM instead when:**\n- Have NVIDIA GPUs\n- Need Python-first API\n- Want PagedAttention\n\n## Quick start\n\n### Installation\n\n```bash\n# macOS\u002FLinux\nbrew install llama.cpp\n\n# Or build from source\ngit clone https:\u002F\u002Fgithub.com\u002Fggerganov\u002Fllama.cpp\ncd llama.cpp\nmake\n\n# With Metal (Apple Silicon)\nmake LLAMA_METAL=1\n\n# With CUDA (NVIDIA)\nmake LLAMA_CUDA=1\n\n# With ROCm (AMD)\nmake LLAMA_HIP=1\n```\n\n### Download model\n\n```bash\n# Download from HuggingFace (GGUF format)\nhuggingface-cli download \\\n    TheBloke\u002FLlama-2-7B-Chat-GGUF \\\n    llama-2-7b-chat.Q4_K_M.gguf \\\n    --local-dir models\u002F\n\n# Or convert from HuggingFace\npython convert_hf_to_gguf.py models\u002Fllama-2-7b-chat\u002F\n```\n\n### Run inference\n\n```bash\n# Simple chat\n.\u002Fllama-cli \\\n    -m models\u002Fllama-2-7b-chat.Q4_K_M.gguf \\\n    -p \"Explain quantum computing\" \\\n    -n 256  # Max tokens\n\n# Interactive chat\n.\u002Fllama-cli \\\n    -m models\u002Fllama-2-7b-chat.Q4_K_M.gguf \\\n    --interactive\n```\n\n### Server mode\n\n```bash\n# Start OpenAI-compatible server\n.\u002Fllama-server \\\n    -m models\u002Fllama-2-7b-chat.Q4_K_M.gguf \\\n    --host 0.0.0.0 \\\n    --port 8080 \\\n    -ngl 32  # Offload 32 layers to GPU\n\n# Client request\ncurl http:\u002F\u002Flocalhost:8080\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"llama-2-7b-chat\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n    \"temperature\": 0.7,\n    \"max_tokens\": 100\n  }'\n```\n\n## Quantization formats\n\n### GGUF format overview\n\n| Format | Bits | Size (7B) | Speed | Quality | Use Case |\n|--------|------|-----------|-------|---------|----------|\n| **Q4_K_M** | 4.5 | 4.1 GB | Fast | Good | **Recommended default** |\n| Q4_K_S | 4.3 | 3.9 GB | Faster | Lower | Speed critical |\n| Q5_K_M | 5.5 | 4.8 GB | Medium | Better | Quality critical |\n| Q6_K | 6.5 | 5.5 GB | Slower | Best | Maximum quality |\n| Q8_0 | 8.0 | 7.0 GB | Slow | Excellent | Minimal degradation |\n| Q2_K | 2.5 | 2.7 GB | Fastest | Poor | Testing only |\n\n### Choosing quantization\n\n```bash\n# General use (balanced)\nQ4_K_M  # 4-bit, medium quality\n\n# Maximum speed (more degradation)\nQ2_K or Q3_K_M\n\n# Maximum quality (slower)\nQ6_K or Q8_0\n\n# Very large models (70B, 405B)\nQ3_K_M or Q4_K_S  # Lower bits to fit in memory\n```\n\n## Hardware acceleration\n\n### Apple Silicon (Metal)\n\n```bash\n# Build with Metal\nmake LLAMA_METAL=1\n\n# Run with GPU acceleration (automatic)\n.\u002Fllama-cli -m model.gguf -ngl 999  # Offload all layers\n\n# Performance: M3 Max 40-60 tokens\u002Fsec (Llama 2-7B Q4_K_M)\n```\n\n### NVIDIA GPUs (CUDA)\n\n```bash\n# Build with CUDA\nmake LLAMA_CUDA=1\n\n# Offload layers to GPU\n.\u002Fllama-cli -m model.gguf -ngl 35  # Offload 35\u002F40 layers\n\n# Hybrid CPU+GPU for large models\n.\u002Fllama-cli -m llama-70b.Q4_K_M.gguf -ngl 20  # GPU: 20 layers, CPU: rest\n```\n\n### AMD GPUs (ROCm)\n\n```bash\n# Build with ROCm\nmake LLAMA_HIP=1\n\n# Run with AMD GPU\n.\u002Fllama-cli -m model.gguf -ngl 999\n```\n\n## Common patterns\n\n### Batch processing\n\n```bash\n# Process multiple prompts from file\ncat prompts.txt | .\u002Fllama-cli \\\n    -m model.gguf \\\n    --batch-size 512 \\\n    -n 100\n```\n\n### Constrained generation\n\n```bash\n# JSON output with grammar\n.\u002Fllama-cli \\\n    -m model.gguf \\\n    -p \"Generate a person: \" \\\n    --grammar-file grammars\u002Fjson.gbnf\n\n# Outputs valid JSON only\n```\n\n### Context size\n\n```bash\n# Increase context (default 512)\n.\u002Fllama-cli \\\n    -m model.gguf \\\n    -c 4096  # 4K context window\n\n# Very long context (if model supports)\n.\u002Fllama-cli -m model.gguf -c 32768  # 32K context\n```\n\n## Performance benchmarks\n\n### CPU performance (Llama 2-7B Q4_K_M)\n\n| CPU | Threads | Speed | Cost |\n|-----|---------|-------|------|\n| Apple M3 Max | 16 | 50 tok\u002Fs | $0 (local) |\n| AMD Ryzen 9 7950X | 32 | 35 tok\u002Fs | $0.50\u002Fhour |\n| Intel i9-13900K | 32 | 30 tok\u002Fs | $0.40\u002Fhour |\n| AWS c7i.16xlarge | 64 | 40 tok\u002Fs | $2.88\u002Fhour |\n\n### GPU acceleration (Llama 2-7B Q4_K_M)\n\n| GPU | Speed | vs CPU | Cost |\n|-----|-------|--------|------|\n| NVIDIA RTX 4090 | 120 tok\u002Fs | 3-4× | $0 (local) |\n| NVIDIA A10 | 80 tok\u002Fs | 2-3× | $1.00\u002Fhour |\n| AMD MI250 | 70 tok\u002Fs | 2× | $2.00\u002Fhour |\n| Apple M3 Max (Metal) | 50 tok\u002Fs | ~Same | $0 (local) |\n\n## Supported models\n\n**LLaMA family**:\n- Llama 2 (7B, 13B, 70B)\n- Llama 3 (8B, 70B, 405B)\n- Code Llama\n\n**Mistral family**:\n- Mistral 7B\n- Mixtral 8x7B, 8x22B\n\n**Other**:\n- Falcon, BLOOM, GPT-J\n- Phi-3, Gemma, Qwen\n- LLaVA (vision), Whisper (audio)\n\n**Find models**: https:\u002F\u002Fhuggingface.co\u002Fmodels?library=gguf\n\n## References\n\n- **[Quantization Guide](references\u002Fquantization.md)** - GGUF formats, conversion, quality comparison\n- **[Server Deployment](references\u002Fserver.md)** - API endpoints, Docker, monitoring\n- **[Optimization](references\u002Foptimization.md)** - Performance tuning, hybrid CPU+GPU\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fggerganov\u002Fllama.cpp\n- **Models**: https:\u002F\u002Fhuggingface.co\u002Fmodels?library=gguf\n- **Discord**: https:\u002F\u002Fdiscord.gg\u002Fllama-cpp\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm hardware, framework and server versions, model format, and expected load.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Serve or log a single request or run end to end before scaling.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Measure latency, throughput and output correctness against a reference; check resource usage and costs.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| The server fails to start or OOMs | Check model size versus memory, quantization and parallelism settings. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Do not expose services or credentials publicly; confirm cloud costs before provisioning.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `gguf-quantization`: GGUF format and llama.cpp quantization for efficient CPU\u002FGPU inference.\n- `tensorrt-llm`: Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency.\n- `gptq`: Quantizes LLMs to 4-bit (also 3-bit) with GPTQ using group-wise quantization (group size 128 by default), via AutoGPTQ and transformers.\n","# llama.cpp\n\nPure C\u002FC++ LLM inference with minimal dependencies, optimized for CPUs and non-NVIDIA hardware.\n\n## When to use llama.cpp\n\n**Use llama.cpp when:**\n- Running on CPU-only machines\n- Deploying on Apple Silicon (M1\u002FM2\u002FM3\u002FM4)\n- Using AMD or Intel GPUs (no CUDA)\n- Edge deployment (Raspberry Pi, embedded systems)\n- Need simple deployment without Docker\u002FPython\n\n**Use TensorRT-LLM instead when:**\n- Have NVIDIA GPUs (A100\u002FH100)\n- Need maximum throughput (100K+ tok\u002Fs)\n- Running in datacenter with CUDA\n\n**Use vLLM instead when:**\n- Have NVIDIA GPUs\n- Need Python-first API\n- Want PagedAttention\n\n## Quick start\n\n### Installation\n\n```bash\n# macOS\u002FLinux\nbrew install llama.cpp\n\n# Or build from source\ngit clone https:\u002F\u002Fgithub.com\u002Fggerganov\u002Fllama.cpp\ncd llama.cpp\nmake\n\n# With Metal (Apple Silicon)\nmake LLAMA_METAL=1\n\n# With CUDA (NVIDIA)\nmake LLAMA_CUDA=1\n\n# With ROCm (AMD)\nmake LLAMA_HIP=1\n```\n\n### Download model\n\n```bash\n# Download from HuggingFace (GGUF format)\nhuggingface-cli download \\\n    TheBloke\u002FLlama-2-7B-Chat-GGUF \\\n    llama-2-7b-chat.Q4_K_M.gguf \\\n    --local-dir models\u002F\n\n# Or convert from HuggingFace\npython convert_hf_to_gguf.py models\u002Fllama-2-7b-chat\u002F\n```\n\n### Run inference\n\n```bash\n# Simple chat\n.\u002Fllama-cli \\\n    -m models\u002Fllama-2-7b-chat.Q4_K_M.gguf \\\n    -p \"Explain quantum computing\" \\\n    -n 256  # Max tokens\n\n# Interactive chat\n.\u002Fllama-cli \\\n    -m models\u002Fllama-2-7b-chat.Q4_K_M.gguf \\\n    --interactive\n```\n\n### Server mode\n\n```bash\n# Start OpenAI-compatible server\n.\u002Fllama-server \\\n    -m models\u002Fllama-2-7b-chat.Q4_K_M.gguf \\\n    --host 0.0.0.0 \\\n    --port 8080 \\\n    -ngl 32  # Offload 32 layers to GPU\n\n# Client request\ncurl http:\u002F\u002Flocalhost:8080\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"llama-2-7b-chat\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n    \"temperature\": 0.7,\n    \"max_tokens\": 100\n  }'\n```\n\n## Quantization formats\n\n### GGUF format overview\n\n| Format | Bits | Size (7B) | Speed | Quality | Use Case |\n|--------|------|-----------|-------|---------|----------|\n| **Q4_K_M** | 4.5 | 4.1 GB | Fast | Good | **Recommended default** |\n| Q4_K_S | 4.3 | 3.9 GB | Faster | Lower | Speed critical |\n| Q5_K_M | 5.5 | 4.8 GB | Medium | Better | Quality critical |\n| Q6_K | 6.5 | 5.5 GB | Slower | Best | Maximum quality |\n| Q8_0 | 8.0 | 7.0 GB | Slow | Excellent | Minimal degradation |\n| Q2_K | 2.5 | 2.7 GB | Fastest | Poor | Testing only |\n\n### Choosing quantization\n\n```bash\n# General use (balanced)\nQ4_K_M  # 4-bit, medium quality\n\n# Maximum speed (more degradation)\nQ2_K or Q3_K_M\n\n# Maximum quality (slower)\nQ6_K or Q8_0\n\n# Very large models (70B, 405B)\nQ3_K_M or Q4_K_S  # Lower bits to fit in memory\n```\n\n## Hardware acceleration\n\n### Apple Silicon (Metal)\n\n```bash\n# Build with Metal\nmake LLAMA_METAL=1\n\n# Run with GPU acceleration (automatic)\n.\u002Fllama-cli -m model.gguf -ngl 999  # Offload all layers\n\n# Performance: M3 Max 40-60 tokens\u002Fsec (Llama 2-7B Q4_K_M)\n```\n\n### NVIDIA GPUs (CUDA)\n\n```bash\n# Build with CUDA\nmake LLAMA_CUDA=1\n\n# Offload layers to GPU\n.\u002Fllama-cli -m model.gguf -ngl 35  # Offload 35\u002F40 layers\n\n# Hybrid CPU+GPU for large models\n.\u002Fllama-cli -m llama-70b.Q4_K_M.gguf -ngl 20  # GPU: 20 layers, CPU: rest\n```\n\n### AMD GPUs (ROCm)\n\n```bash\n# Build with ROCm\nmake LLAMA_HIP=1\n\n# Run with AMD GPU\n.\u002Fllama-cli -m model.gguf -ngl 999\n```\n\n## Common patterns\n\n### Batch processing\n\n```bash\n# Process multiple prompts from file\ncat prompts.txt | .\u002Fllama-cli \\\n    -m model.gguf \\\n    --batch-size 512 \\\n    -n 100\n```\n\n### Constrained generation\n\n```bash\n# JSON output with grammar\n.\u002Fllama-cli \\\n    -m model.gguf \\\n    -p \"Generate a person: \" \\\n    --grammar-file grammars\u002Fjson.gbnf\n\n# Outputs valid JSON only\n```\n\n### Context size\n\n```bash\n# Increase context (default 512)\n.\u002Fllama-cli \\\n    -m model.gguf \\\n    -c 4096  # 4K context window\n\n# Very long context (if model supports)\n.\u002Fllama-cli -m model.gguf -c 32768  # 32K context\n```\n\n## Performance benchmarks\n\n### CPU performance (Llama 2-7B Q4_K_M)\n\n| CPU | Threads | Speed | Cost |\n|-----|---------|-------|------|\n| Apple M3 Max | 16 | 50 tok\u002Fs | $0 (local) |\n| AMD Ryzen 9 7950X | 32 | 35 tok\u002Fs | $0.50\u002Fhour |\n| Intel i9-13900K | 32 | 30 tok\u002Fs | $0.40\u002Fhour |\n| AWS c7i.16xlarge | 64 | 40 tok\u002Fs | $2.88\u002Fhour |\n\n### GPU acceleration (Llama 2-7B Q4_K_M)\n\n| GPU | Speed | vs CPU | Cost |\n|-----|-------|--------|------|\n| NVIDIA RTX 4090 | 120 tok\u002Fs | 3-4× | $0 (local) |\n| NVIDIA A10 | 80 tok\u002Fs | 2-3× | $1.00\u002Fhour |\n| AMD MI250 | 70 tok\u002Fs | 2× | $2.00\u002Fhour |\n| Apple M3 Max (Metal) | 50 tok\u002Fs | ~Same | $0 (local) |\n\n## Supported models\n\n**LLaMA family**:\n- Llama 2 (7B, 13B, 70B)\n- Llama 3 (8B, 70B, 405B)\n- Code Llama\n\n**Mistral family**:\n- Mistral 7B\n- Mixtral 8x7B, 8x22B\n\n**Other**:\n- Falcon, BLOOM, GPT-J\n- Phi-3, Gemma, Qwen\n- LLaVA (vision), Whisper (audio)\n\n**Find models**: https:\u002F\u002Fhuggingface.co\u002Fmodels?library=gguf\n\n## References\n\n- **[Quantization Guide](references\u002Fquantization.md)** - GGUF formats, conversion, quality comparison\n- **[Server Deployment](references\u002Fserver.md)** - API endpoints, Docker, monitoring\n- **[Optimization](references\u002Foptimization.md)** - Performance tuning, hybrid CPU+GPU\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fggerganov\u002Fllama.cpp\n- **Models**: https:\u002F\u002Fhuggingface.co\u002Fmodels?library=gguf\n- **Discord**: https:\u002F\u002Fdiscord.gg\u002Fllama-cpp\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm hardware, framework and server versions, model format, and expected load.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Serve or log a single request or run end to end before scaling.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Measure latency, throughput and output correctness against a reference; check resource usage and costs.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| The server fails to start or OOMs | Check model size versus memory, quantization and parallelism settings. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Do not expose services or credentials publicly; confirm cloud costs before provisioning.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `gguf-quantization`: GGUF format and llama.cpp quantization for efficient CPU\u002FGPU inference.\n- `tensorrt-llm`: Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency.\n- `gptq`: Quantizes LLMs to 4-bit (also 3-bit) with GPTQ using group-wise quantization (group size 128 by default), via AutoGPTQ and transformers.\n",{"name":5,"license":15,"metadata":44,"description":7},{"tags":45,"version":46,"category":47,"maintainer":48,"dependencies":49},"Inference Serving, Llama.cpp, CPU Inference, Apple Silicon, Edge Deployment, GGUF, Quantization, Non-NVIDIA, AMD GPUs, Intel GPUs, Embedded","1.0.0","ml-inference-and-ops","Kalaris Labs","llama-cpp-python","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkal-llama-cpp","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill llama-cpp",{"tool":65,"command":66},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill llama-cpp",{"tool":68,"command":69},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill llama-cpp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-llama-cpp\u002FSKILL.md",true,[73,79,83],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Foptimization.md","REFERENCE","参考文档",1659,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-llama-cpp\u002Freferences\u002Foptimization.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fquantization.md",4956,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-llama-cpp\u002Freferences\u002Fquantization.md",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fserver.md",2259,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-llama-cpp\u002Freferences\u002Fserver.md",[88,119,143,170,194,218],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":99,"publishedAt":39},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[94],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,24,116,117,118],"youtube full","youtube","full","transcript","search","monitoring","data","Video","Audio","list","files","do","get","age","trigger","URL","browsing","request","youtube transcripts",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":39},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[126,127,128,129,104,130,131,132,133,134,135,136,137,138,33,139,140,141,142,24],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","platform","grow","posting","competitive",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":152,"publishedAt":39},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[149],{"categoryNo":150,"categoryName":151,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000023","Skill与智能体开发",[153,137,154,155,156,157,158,159,33,160,161,50,162,163,164,165,166,167,168,169],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":39},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[177,178,179,180,37,181,182,183,184,33,185,111,186,187,188,189,190,191,192,193],"wrap up","up","wrap","gemini","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":201,"publishedAt":39},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[200],{"categoryNo":150,"categoryName":151,"taxonomyType":97,"taxonomyTypeDesc":98},[202,203,204,205,206,155,181,207,208,209,210,211,137,212,110,213,214,215,216,217],"workflow","workflow builder","builder","design","workflows","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":222,"categories":223,"keywords":224,"publishedAt":39},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[225,226,227,228,229,230,231,232,233,210,234,235,236,237,238,239,112,240,241,193],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]