[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ADPFPKTMSAMVQYE62N2WZ3":3,"skill-same:01M6ADPFPKTMSAMVQYE62N2WZ3":331},{"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":23,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":61,"commitSha":62,"skillDirectory":63,"forksCount":64,"repositoryHtmlUrl":65,"repositoryHomepageUrl":66,"ownerHtmlUrl":67,"ownerBlogUrl":68,"ownerDescription":69,"updatedAt":70,"install":71,"resources":84},"01M6ADPFPKTMSAMVQYE62N2WZ3","evaluation-bigcode-evaluation-harness",null,"Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fevaluation-bigcode-evaluation-harness\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"bigcode evaluation harness","harness","evaluation bigcode evaluation harness","MultiPL-E","when","multipl","Accelerate","project","across","Transformers","Code Models","BigCode","Pass@k","testing","MBPP","HumanEval","Code Generation","Evaluation","metrics","code","benchmarking","support","research","2026-11-10 10:12:30",false,"---\nname: evaluation-bigcode-evaluation-harness\ndescription: Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.\nversion: 1.0.0\nauthor: Orchestra Research\nlicense: MIT\ntags: [Evaluation, Code Generation, HumanEval, MBPP, MultiPL-E, Pass@k, BigCode, Benchmarking, Code Models]\ndependencies: [bigcode-evaluation-harness, transformers>=4.25.1, accelerate>=0.13.2, datasets>=2.6.1]\n---\n\n# BigCode Evaluation Harness - Code Model Benchmarking\n\n## Quick Start\n\nBigCode Evaluation Harness evaluates code generation models across 15+ benchmarks including HumanEval, MBPP, and MultiPL-E (18 languages).\n\n**Installation**:\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fbigcode-project\u002Fbigcode-evaluation-harness.git\ncd bigcode-evaluation-harness\npip install -e .\naccelerate config\n```\n\n**Evaluate on HumanEval**:\n```bash\naccelerate launch main.py \\\n  --model bigcode\u002Fstarcoder2-7b \\\n  --tasks humaneval \\\n  --max_length_generation 512 \\\n  --temperature 0.2 \\\n  --n_samples 20 \\\n  --batch_size 10 \\\n  --allow_code_execution \\\n  --save_generations\n```\n\n**View available tasks**:\n```bash\npython -c \"from bigcode_eval.tasks import ALL_TASKS; print(ALL_TASKS)\"\n```\n\n## Common Workflows\n\n### Workflow 1: Standard Code Benchmark Evaluation\n\nEvaluate model on core code benchmarks (HumanEval, MBPP, HumanEval+).\n\n**Checklist**:\n```\nCode Benchmark Evaluation:\n- [ ] Step 1: Choose benchmark suite\n- [ ] Step 2: Configure model and generation\n- [ ] Step 3: Run evaluation with code execution\n- [ ] Step 4: Analyze pass@k results\n```\n\n**Step 1: Choose benchmark suite**\n\n**Python code generation** (most common):\n- **HumanEval**: 164 handwritten problems, function completion\n- **HumanEval+**: Same 164 problems with 80× more tests (stricter)\n- **MBPP**: 500 crowd-sourced problems, entry-level difficulty\n- **MBPP+**: 399 curated problems with 35× more tests\n\n**Multi-language** (18 languages):\n- **MultiPL-E**: HumanEval\u002FMBPP translated to C++, Java, JavaScript, Go, Rust, etc.\n\n**Advanced**:\n- **APPS**: 10,000 problems (introductory\u002Finterview\u002Fcompetition)\n- **DS-1000**: 1,000 data science problems across 7 libraries\n\n**Step 2: Configure model and generation**\n\n```bash\n# Standard HuggingFace model\naccelerate launch main.py \\\n  --model bigcode\u002Fstarcoder2-7b \\\n  --tasks humaneval \\\n  --max_length_generation 512 \\\n  --temperature 0.2 \\\n  --do_sample True \\\n  --n_samples 200 \\\n  --batch_size 50 \\\n  --allow_code_execution\n\n# Quantized model (4-bit)\naccelerate launch main.py \\\n  --model codellama\u002FCodeLlama-34b-hf \\\n  --tasks humaneval \\\n  --load_in_4bit \\\n  --max_length_generation 512 \\\n  --allow_code_execution\n\n# Custom\u002Fprivate model\naccelerate launch main.py \\\n  --model \u002Fpath\u002Fto\u002Fmy-code-model \\\n  --tasks humaneval \\\n  --trust_remote_code \\\n  --use_auth_token \\\n  --allow_code_execution\n```\n\n**Step 3: Run evaluation**\n\n```bash\n# Full evaluation with pass@k estimation (k=1,10,100)\naccelerate launch main.py \\\n  --model bigcode\u002Fstarcoder2-7b \\\n  --tasks humaneval \\\n  --temperature 0.8 \\\n  --n_samples 200 \\\n  --batch_size 50 \\\n  --allow_code_execution \\\n  --save_generations \\\n  --metric_output_path results\u002Fstarcoder2-humaneval.json\n```\n\n**Step 4: Analyze results**\n\nResults in `results\u002Fstarcoder2-humaneval.json`:\n```json\n{\n  \"humaneval\": {\n    \"pass@1\": 0.354,\n    \"pass@10\": 0.521,\n    \"pass@100\": 0.689\n  },\n  \"config\": {\n    \"model\": \"bigcode\u002Fstarcoder2-7b\",\n    \"temperature\": 0.8,\n    \"n_samples\": 200\n  }\n}\n```\n\n### Workflow 2: Multi-Language Evaluation (MultiPL-E)\n\nEvaluate code generation across 18 programming languages.\n\n**Checklist**:\n```\nMulti-Language Evaluation:\n- [ ] Step 1: Generate solutions (host machine)\n- [ ] Step 2: Run evaluation in Docker (safe execution)\n- [ ] Step 3: Compare across languages\n```\n\n**Step 1: Generate solutions on host**\n\n```bash\n# Generate without execution (safe)\naccelerate launch main.py \\\n  --model bigcode\u002Fstarcoder2-7b \\\n  --tasks multiple-py,multiple-js,multiple-java,multiple-cpp \\\n  --max_length_generation 650 \\\n  --temperature 0.8 \\\n  --n_samples 50 \\\n  --batch_size 50 \\\n  --generation_only \\\n  --save_generations \\\n  --save_generations_path generations_multi.json\n```\n\n**Step 2: Evaluate in Docker container**\n\n```bash\n# Pull the MultiPL-E Docker image\ndocker pull ghcr.io\u002Fbigcode-project\u002Fevaluation-harness-multiple\n\n# Run evaluation inside container\ndocker run -v $(pwd)\u002Fgenerations_multi.json:\u002Fapp\u002Fgenerations.json:ro \\\n  -it evaluation-harness-multiple python3 main.py \\\n  --model bigcode\u002Fstarcoder2-7b \\\n  --tasks multiple-py,multiple-js,multiple-java,multiple-cpp \\\n  --load_generations_path \u002Fapp\u002Fgenerations.json \\\n  --allow_code_execution \\\n  --n_samples 50\n```\n\n**Supported languages**: Python, JavaScript, Java, C++, Go, Rust, TypeScript, C#, PHP, Ruby, Swift, Kotlin, Scala, Perl, Julia, Lua, R, Racket\n\n### Workflow 3: Instruction-Tuned Model Evaluation\n\nEvaluate chat\u002Finstruction models with proper formatting.\n\n**Checklist**:\n```\nInstruction Model Evaluation:\n- [ ] Step 1: Use instruction-tuned tasks\n- [ ] Step 2: Configure instruction tokens\n- [ ] Step 3: Run evaluation\n```\n\n**Step 1: Choose instruction tasks**\n\n- **instruct-humaneval**: HumanEval with instruction prompts\n- **humanevalsynthesize-{lang}**: HumanEvalPack synthesis tasks\n\n**Step 2: Configure instruction tokens**\n\n```bash\n# For models with chat templates (e.g., CodeLlama-Instruct)\naccelerate launch main.py \\\n  --model codellama\u002FCodeLlama-7b-Instruct-hf \\\n  --tasks instruct-humaneval \\\n  --instruction_tokens \"\u003Cs>[INST],\u003C\u002Fs>,[\u002FINST]\" \\\n  --max_length_generation 512 \\\n  --allow_code_execution\n```\n\n**Step 3: HumanEvalPack for instruction models**\n\n```bash\n# Test code synthesis across 6 languages\naccelerate launch main.py \\\n  --model codellama\u002FCodeLlama-7b-Instruct-hf \\\n  --tasks humanevalsynthesize-python,humanevalsynthesize-js \\\n  --prompt instruct \\\n  --max_length_generation 512 \\\n  --allow_code_execution\n```\n\n### Workflow 4: Compare Multiple Models\n\nBenchmark suite for model comparison.\n\n**Step 1: Create evaluation script**\n\n```bash\n#!\u002Fbin\u002Fbash\n# eval_models.sh\n\nMODELS=(\n  \"bigcode\u002Fstarcoder2-7b\"\n  \"codellama\u002FCodeLlama-7b-hf\"\n  \"deepseek-ai\u002Fdeepseek-coder-6.7b-base\"\n)\nTASKS=\"humaneval,mbpp\"\n\nfor model in \"${MODELS[@]}\"; do\n  model_name=$(echo $model | tr '\u002F' '-')\n  echo \"Evaluating $model\"\n\n  accelerate launch main.py \\\n    --model $model \\\n    --tasks $TASKS \\\n    --temperature 0.2 \\\n    --n_samples 20 \\\n    --batch_size 20 \\\n    --allow_code_execution \\\n    --metric_output_path results\u002F${model_name}.json\ndone\n```\n\n**Step 2: Generate comparison table**\n\n```python\nimport json\nimport pandas as pd\n\nmodels = [\"bigcode-starcoder2-7b\", \"codellama-CodeLlama-7b-hf\", \"deepseek-ai-deepseek-coder-6.7b-base\"]\nresults = []\n\nfor model in models:\n    with open(f\"results\u002F{model}.json\") as f:\n        data = json.load(f)\n        results.append({\n            \"Model\": model,\n            \"HumanEval pass@1\": f\"{data['humaneval']['pass@1']:.3f}\",\n            \"MBPP pass@1\": f\"{data['mbpp']['pass@1']:.3f}\"\n        })\n\ndf = pd.DataFrame(results)\nprint(df.to_markdown(index=False))\n```\n\n## When to Use vs Alternatives\n\n**Use BigCode Evaluation Harness when:**\n- Evaluating **code generation** models specifically\n- Need **multi-language** evaluation (18 languages via MultiPL-E)\n- Testing **functional correctness** with unit tests (pass@k)\n- Benchmarking for **BigCode\u002FHuggingFace leaderboards**\n- Evaluating **fill-in-the-middle** (FIM) capabilities\n\n**Use alternatives instead:**\n- **lm-evaluation-harness**: General LLM benchmarks (MMLU, GSM8K, HellaSwag)\n- **EvalPlus**: Stricter HumanEval+\u002FMBPP+ with more test cases\n- **SWE-bench**: Real-world GitHub issue resolution\n- **LiveCodeBench**: Contamination-free, continuously updated problems\n- **CodeXGLUE**: Code understanding tasks (clone detection, defect prediction)\n\n## Supported Benchmarks\n\n| Benchmark | Problems | Languages | Metric | Use Case |\n|-----------|----------|-----------|--------|----------|\n| HumanEval | 164 | Python | pass@k | Standard code completion |\n| HumanEval+ | 164 | Python | pass@k | Stricter evaluation (80× tests) |\n| MBPP | 500 | Python | pass@k | Entry-level problems |\n| MBPP+ | 399 | Python | pass@k | Stricter evaluation (35× tests) |\n| MultiPL-E | 164×18 | 18 languages | pass@k | Multi-language evaluation |\n| APPS | 10,000 | Python | pass@k | Competition-level |\n| DS-1000 | 1,000 | Python | pass@k | Data science (pandas, numpy, etc.) |\n| HumanEvalPack | 164×3×6 | 6 languages | pass@k | Synthesis\u002Ffix\u002Fexplain |\n| Mercury | 1,889 | Python | Efficiency | Computational efficiency |\n\n## Common Issues\n\n**Issue: Different results than reported in papers**\n\nCheck these factors:\n```bash\n# 1. Verify n_samples (need 200 for accurate pass@k)\n--n_samples 200\n\n# 2. Check temperature (0.2 for greedy-ish, 0.8 for sampling)\n--temperature 0.8\n\n# 3. Verify task name matches exactly\n--tasks humaneval  # Not \"human_eval\" or \"HumanEval\"\n\n# 4. Check max_length_generation\n--max_length_generation 512  # Increase for longer problems\n```\n\n**Issue: CUDA out of memory**\n\n```bash\n# Use quantization\n--load_in_8bit\n# OR\n--load_in_4bit\n\n# Reduce batch size\n--batch_size 1\n\n# Set memory limit\n--max_memory_per_gpu \"20GiB\"\n```\n\n**Issue: Code execution hangs or times out**\n\nUse Docker for safe execution:\n```bash\n# Generate on host (no execution)\n--generation_only --save_generations\n\n# Evaluate in Docker\ndocker run ... --allow_code_execution --load_generations_path ...\n```\n\n**Issue: Low scores on instruction models**\n\nEnsure proper instruction formatting:\n```bash\n# Use instruction-specific tasks\n--tasks instruct-humaneval\n\n# Set instruction tokens for your model\n--instruction_tokens \"\u003Cs>[INST],\u003C\u002Fs>,[\u002FINST]\"\n```\n\n**Issue: MultiPL-E language failures**\n\nUse the dedicated Docker image:\n```bash\ndocker pull ghcr.io\u002Fbigcode-project\u002Fevaluation-harness-multiple\n```\n\n## Command Reference\n\n| Argument | Default | Description |\n|----------|---------|-------------|\n| `--model` | - | HuggingFace model ID or local path |\n| `--tasks` | - | Comma-separated task names |\n| `--n_samples` | 1 | Samples per problem (200 for pass@k) |\n| `--temperature` | 0.2 | Sampling temperature |\n| `--max_length_generation` | 512 | Max tokens (prompt + generation) |\n| `--batch_size` | 1 | Batch size per GPU |\n| `--allow_code_execution` | False | Enable code execution (required) |\n| `--generation_only` | False | Generate without evaluation |\n| `--load_generations_path` | - | Load pre-generated solutions |\n| `--save_generations` | False | Save generated code |\n| `--metric_output_path` | results.json | Output file for metrics |\n| `--load_in_8bit` | False | 8-bit quantization |\n| `--load_in_4bit` | False | 4-bit quantization |\n| `--trust_remote_code` | False | Allow custom model code |\n| `--precision` | fp32 | Model precision (fp32\u002Ffp16\u002Fbf16) |\n\n## Hardware Requirements\n\n| Model Size | VRAM (fp16) | VRAM (4-bit) | Time (HumanEval, n=200) |\n|------------|-------------|--------------|-------------------------|\n| 7B | 14GB | 6GB | ~30 min (A100) |\n| 13B | 26GB | 10GB | ~1 hour (A100) |\n| 34B | 68GB | 20GB | ~2 hours (A100) |\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fbigcode-project\u002Fbigcode-evaluation-harness\n- **Documentation**: https:\u002F\u002Fgithub.com\u002Fbigcode-project\u002Fbigcode-evaluation-harness\u002Ftree\u002Fmain\u002Fdocs\n- **BigCode Leaderboard**: https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fbigcode\u002Fbigcode-models-leaderboard\n- **HumanEval Dataset**: https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fopenai\u002Fopenai_humaneval\n- **MultiPL-E**: https:\u002F\u002Fgithub.com\u002Fnuprl\u002FMultiPL-E\n","# BigCode Evaluation Harness - Code Model Benchmarking\n\n## Quick Start\n\nBigCode Evaluation Harness evaluates code generation models across 15+ benchmarks including HumanEval, MBPP, and MultiPL-E (18 languages).\n\n**Installation**:\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fbigcode-project\u002Fbigcode-evaluation-harness.git\ncd bigcode-evaluation-harness\npip install -e .\naccelerate config\n```\n\n**Evaluate on HumanEval**:\n```bash\naccelerate launch main.py \\\n  --model bigcode\u002Fstarcoder2-7b \\\n  --tasks humaneval \\\n  --max_length_generation 512 \\\n  --temperature 0.2 \\\n  --n_samples 20 \\\n  --batch_size 10 \\\n  --allow_code_execution \\\n  --save_generations\n```\n\n**View available tasks**:\n```bash\npython -c \"from bigcode_eval.tasks import ALL_TASKS; print(ALL_TASKS)\"\n```\n\n## Common Workflows\n\n### Workflow 1: Standard Code Benchmark Evaluation\n\nEvaluate model on core code benchmarks (HumanEval, MBPP, HumanEval+).\n\n**Checklist**:\n```\nCode Benchmark Evaluation:\n- [ ] Step 1: Choose benchmark suite\n- [ ] Step 2: Configure model and generation\n- [ ] Step 3: Run evaluation with code execution\n- [ ] Step 4: Analyze pass@k results\n```\n\n**Step 1: Choose benchmark suite**\n\n**Python code generation** (most common):\n- **HumanEval**: 164 handwritten problems, function completion\n- **HumanEval+**: Same 164 problems with 80× more tests (stricter)\n- **MBPP**: 500 crowd-sourced problems, entry-level difficulty\n- **MBPP+**: 399 curated problems with 35× more tests\n\n**Multi-language** (18 languages):\n- **MultiPL-E**: HumanEval\u002FMBPP translated to C++, Java, JavaScript, Go, Rust, etc.\n\n**Advanced**:\n- **APPS**: 10,000 problems (introductory\u002Finterview\u002Fcompetition)\n- **DS-1000**: 1,000 data science problems across 7 libraries\n\n**Step 2: Configure model and generation**\n\n```bash\n# Standard HuggingFace model\naccelerate launch main.py \\\n  --model bigcode\u002Fstarcoder2-7b \\\n  --tasks humaneval \\\n  --max_length_generation 512 \\\n  --temperature 0.2 \\\n  --do_sample True \\\n  --n_samples 200 \\\n  --batch_size 50 \\\n  --allow_code_execution\n\n# Quantized model (4-bit)\naccelerate launch main.py \\\n  --model codellama\u002FCodeLlama-34b-hf \\\n  --tasks humaneval \\\n  --load_in_4bit \\\n  --max_length_generation 512 \\\n  --allow_code_execution\n\n# Custom\u002Fprivate model\naccelerate launch main.py \\\n  --model \u002Fpath\u002Fto\u002Fmy-code-model \\\n  --tasks humaneval \\\n  --trust_remote_code \\\n  --use_auth_token \\\n  --allow_code_execution\n```\n\n**Step 3: Run evaluation**\n\n```bash\n# Full evaluation with pass@k estimation (k=1,10,100)\naccelerate launch main.py \\\n  --model bigcode\u002Fstarcoder2-7b \\\n  --tasks humaneval \\\n  --temperature 0.8 \\\n  --n_samples 200 \\\n  --batch_size 50 \\\n  --allow_code_execution \\\n  --save_generations \\\n  --metric_output_path results\u002Fstarcoder2-humaneval.json\n```\n\n**Step 4: Analyze results**\n\nResults in `results\u002Fstarcoder2-humaneval.json`:\n```json\n{\n  \"humaneval\": {\n    \"pass@1\": 0.354,\n    \"pass@10\": 0.521,\n    \"pass@100\": 0.689\n  },\n  \"config\": {\n    \"model\": \"bigcode\u002Fstarcoder2-7b\",\n    \"temperature\": 0.8,\n    \"n_samples\": 200\n  }\n}\n```\n\n### Workflow 2: Multi-Language Evaluation (MultiPL-E)\n\nEvaluate code generation across 18 programming languages.\n\n**Checklist**:\n```\nMulti-Language Evaluation:\n- [ ] Step 1: Generate solutions (host machine)\n- [ ] Step 2: Run evaluation in Docker (safe execution)\n- [ ] Step 3: Compare across languages\n```\n\n**Step 1: Generate solutions on host**\n\n```bash\n# Generate without execution (safe)\naccelerate launch main.py \\\n  --model bigcode\u002Fstarcoder2-7b \\\n  --tasks multiple-py,multiple-js,multiple-java,multiple-cpp \\\n  --max_length_generation 650 \\\n  --temperature 0.8 \\\n  --n_samples 50 \\\n  --batch_size 50 \\\n  --generation_only \\\n  --save_generations \\\n  --save_generations_path generations_multi.json\n```\n\n**Step 2: Evaluate in Docker container**\n\n```bash\n# Pull the MultiPL-E Docker image\ndocker pull ghcr.io\u002Fbigcode-project\u002Fevaluation-harness-multiple\n\n# Run evaluation inside container\ndocker run -v $(pwd)\u002Fgenerations_multi.json:\u002Fapp\u002Fgenerations.json:ro \\\n  -it evaluation-harness-multiple python3 main.py \\\n  --model bigcode\u002Fstarcoder2-7b \\\n  --tasks multiple-py,multiple-js,multiple-java,multiple-cpp \\\n  --load_generations_path \u002Fapp\u002Fgenerations.json \\\n  --allow_code_execution \\\n  --n_samples 50\n```\n\n**Supported languages**: Python, JavaScript, Java, C++, Go, Rust, TypeScript, C#, PHP, Ruby, Swift, Kotlin, Scala, Perl, Julia, Lua, R, Racket\n\n### Workflow 3: Instruction-Tuned Model Evaluation\n\nEvaluate chat\u002Finstruction models with proper formatting.\n\n**Checklist**:\n```\nInstruction Model Evaluation:\n- [ ] Step 1: Use instruction-tuned tasks\n- [ ] Step 2: Configure instruction tokens\n- [ ] Step 3: Run evaluation\n```\n\n**Step 1: Choose instruction tasks**\n\n- **instruct-humaneval**: HumanEval with instruction prompts\n- **humanevalsynthesize-{lang}**: HumanEvalPack synthesis tasks\n\n**Step 2: Configure instruction tokens**\n\n```bash\n# For models with chat templates (e.g., CodeLlama-Instruct)\naccelerate launch main.py \\\n  --model codellama\u002FCodeLlama-7b-Instruct-hf \\\n  --tasks instruct-humaneval \\\n  --instruction_tokens \"\u003Cs>[INST],\u003C\u002Fs>,[\u002FINST]\" \\\n  --max_length_generation 512 \\\n  --allow_code_execution\n```\n\n**Step 3: HumanEvalPack for instruction models**\n\n```bash\n# Test code synthesis across 6 languages\naccelerate launch main.py \\\n  --model codellama\u002FCodeLlama-7b-Instruct-hf \\\n  --tasks humanevalsynthesize-python,humanevalsynthesize-js \\\n  --prompt instruct \\\n  --max_length_generation 512 \\\n  --allow_code_execution\n```\n\n### Workflow 4: Compare Multiple Models\n\nBenchmark suite for model comparison.\n\n**Step 1: Create evaluation script**\n\n```bash\n#!\u002Fbin\u002Fbash\n# eval_models.sh\n\nMODELS=(\n  \"bigcode\u002Fstarcoder2-7b\"\n  \"codellama\u002FCodeLlama-7b-hf\"\n  \"deepseek-ai\u002Fdeepseek-coder-6.7b-base\"\n)\nTASKS=\"humaneval,mbpp\"\n\nfor model in \"${MODELS[@]}\"; do\n  model_name=$(echo $model | tr '\u002F' '-')\n  echo \"Evaluating $model\"\n\n  accelerate launch main.py \\\n    --model $model \\\n    --tasks $TASKS \\\n    --temperature 0.2 \\\n    --n_samples 20 \\\n    --batch_size 20 \\\n    --allow_code_execution \\\n    --metric_output_path results\u002F${model_name}.json\ndone\n```\n\n**Step 2: Generate comparison table**\n\n```python\nimport json\nimport pandas as pd\n\nmodels = [\"bigcode-starcoder2-7b\", \"codellama-CodeLlama-7b-hf\", \"deepseek-ai-deepseek-coder-6.7b-base\"]\nresults = []\n\nfor model in models:\n    with open(f\"results\u002F{model}.json\") as f:\n        data = json.load(f)\n        results.append({\n            \"Model\": model,\n            \"HumanEval pass@1\": f\"{data['humaneval']['pass@1']:.3f}\",\n            \"MBPP pass@1\": f\"{data['mbpp']['pass@1']:.3f}\"\n        })\n\ndf = pd.DataFrame(results)\nprint(df.to_markdown(index=False))\n```\n\n## When to Use vs Alternatives\n\n**Use BigCode Evaluation Harness when:**\n- Evaluating **code generation** models specifically\n- Need **multi-language** evaluation (18 languages via MultiPL-E)\n- Testing **functional correctness** with unit tests (pass@k)\n- Benchmarking for **BigCode\u002FHuggingFace leaderboards**\n- Evaluating **fill-in-the-middle** (FIM) capabilities\n\n**Use alternatives instead:**\n- **lm-evaluation-harness**: General LLM benchmarks (MMLU, GSM8K, HellaSwag)\n- **EvalPlus**: Stricter HumanEval+\u002FMBPP+ with more test cases\n- **SWE-bench**: Real-world GitHub issue resolution\n- **LiveCodeBench**: Contamination-free, continuously updated problems\n- **CodeXGLUE**: Code understanding tasks (clone detection, defect prediction)\n\n## Supported Benchmarks\n\n| Benchmark | Problems | Languages | Metric | Use Case |\n|-----------|----------|-----------|--------|----------|\n| HumanEval | 164 | Python | pass@k | Standard code completion |\n| HumanEval+ | 164 | Python | pass@k | Stricter evaluation (80× tests) |\n| MBPP | 500 | Python | pass@k | Entry-level problems |\n| MBPP+ | 399 | Python | pass@k | Stricter evaluation (35× tests) |\n| MultiPL-E | 164×18 | 18 languages | pass@k | Multi-language evaluation |\n| APPS | 10,000 | Python | pass@k | Competition-level |\n| DS-1000 | 1,000 | Python | pass@k | Data science (pandas, numpy, etc.) |\n| HumanEvalPack | 164×3×6 | 6 languages | pass@k | Synthesis\u002Ffix\u002Fexplain |\n| Mercury | 1,889 | Python | Efficiency | Computational efficiency |\n\n## Common Issues\n\n**Issue: Different results than reported in papers**\n\nCheck these factors:\n```bash\n# 1. Verify n_samples (need 200 for accurate pass@k)\n--n_samples 200\n\n# 2. Check temperature (0.2 for greedy-ish, 0.8 for sampling)\n--temperature 0.8\n\n# 3. Verify task name matches exactly\n--tasks humaneval  # Not \"human_eval\" or \"HumanEval\"\n\n# 4. Check max_length_generation\n--max_length_generation 512  # Increase for longer problems\n```\n\n**Issue: CUDA out of memory**\n\n```bash\n# Use quantization\n--load_in_8bit\n# OR\n--load_in_4bit\n\n# Reduce batch size\n--batch_size 1\n\n# Set memory limit\n--max_memory_per_gpu \"20GiB\"\n```\n\n**Issue: Code execution hangs or times out**\n\nUse Docker for safe execution:\n```bash\n# Generate on host (no execution)\n--generation_only --save_generations\n\n# Evaluate in Docker\ndocker run ... --allow_code_execution --load_generations_path ...\n```\n\n**Issue: Low scores on instruction models**\n\nEnsure proper instruction formatting:\n```bash\n# Use instruction-specific tasks\n--tasks instruct-humaneval\n\n# Set instruction tokens for your model\n--instruction_tokens \"\u003Cs>[INST],\u003C\u002Fs>,[\u002FINST]\"\n```\n\n**Issue: MultiPL-E language failures**\n\nUse the dedicated Docker image:\n```bash\ndocker pull ghcr.io\u002Fbigcode-project\u002Fevaluation-harness-multiple\n```\n\n## Command Reference\n\n| Argument | Default | Description |\n|----------|---------|-------------|\n| `--model` | - | HuggingFace model ID or local path |\n| `--tasks` | - | Comma-separated task names |\n| `--n_samples` | 1 | Samples per problem (200 for pass@k) |\n| `--temperature` | 0.2 | Sampling temperature |\n| `--max_length_generation` | 512 | Max tokens (prompt + generation) |\n| `--batch_size` | 1 | Batch size per GPU |\n| `--allow_code_execution` | False | Enable code execution (required) |\n| `--generation_only` | False | Generate without evaluation |\n| `--load_generations_path` | - | Load pre-generated solutions |\n| `--save_generations` | False | Save generated code |\n| `--metric_output_path` | results.json | Output file for metrics |\n| `--load_in_8bit` | False | 8-bit quantization |\n| `--load_in_4bit` | False | 4-bit quantization |\n| `--trust_remote_code` | False | Allow custom model code |\n| `--precision` | fp32 | Model precision (fp32\u002Ffp16\u002Fbf16) |\n\n## Hardware Requirements\n\n| Model Size | VRAM (fp16) | VRAM (4-bit) | Time (HumanEval, n=200) |\n|------------|-------------|--------------|-------------------------|\n| 7B | 14GB | 6GB | ~30 min (A100) |\n| 13B | 26GB | 10GB | ~1 hour (A100) |\n| 34B | 68GB | 20GB | ~2 hours (A100) |\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fbigcode-project\u002Fbigcode-evaluation-harness\n- **Documentation**: https:\u002F\u002Fgithub.com\u002Fbigcode-project\u002Fbigcode-evaluation-harness\u002Ftree\u002Fmain\u002Fdocs\n- **BigCode Leaderboard**: https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fbigcode\u002Fbigcode-models-leaderboard\n- **HumanEval Dataset**: https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fopenai\u002Fopenai_humaneval\n- **MultiPL-E**: https:\u002F\u002Fgithub.com\u002Fnuprl\u002FMultiPL-E\n",{"name":5,"tags":52,"author":54,"license":15,"version":55,"description":7,"dependencies":56},[41,40,39,38,27,36,35,53,34],"Benchmarking","Orchestra Research","1.0.0",[57,58,59,60],"bigcode-evaluation-harness","transformers>=4.25.1","accelerate>=0.13.2","datasets>=2.6.1","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fevaluation-bigcode-evaluation-harness",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":72,"prompt":82,"zipAvailable":83},[73,76,79],{"tool":74,"command":75},"npx","npx skills add davila7\u002Fclaude-code-templates --skill evaluation-bigcode-evaluation-harness",{"tool":77,"command":78},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill evaluation-bigcode-evaluation-harness",{"tool":80,"command":81},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill evaluation-bigcode-evaluation-harness","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fevaluation-bigcode-evaluation-harness\u002FSKILL.md",true,[85,91,97,101,105,111,115,119,123,127,131,135,139,143,147,151,155,159,163,167,171,175,179,183,187,191,195,199,203,207,211,215,219,223,227,231,235,239,243,247,251,255,259,263,267,271,275,279,283,287,291,295,299,303,307,311,315,319,323,327],{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"LICENSE.txt","LICENSE","许可证",1467,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002FLICENSE.txt",{"path":92,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fbenchmarks.md","REFERENCE","参考文档",9168,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fevaluation-bigcode-evaluation-harness\u002Freferences\u002Fbenchmarks.md",{"path":98,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fcustom-tasks.md",10378,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fevaluation-bigcode-evaluation-harness\u002Freferences\u002Fcustom-tasks.md",{"path":102,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fissues.md",8085,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fevaluation-bigcode-evaluation-harness\u002Freferences\u002Fissues.md",{"path":106,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":109,"sourceHtmlUrl":110},"scripts\u002F__init__.py","SCRIPT","脚本",0,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002F__init__.py",{"path":112,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":113,"sourceHtmlUrl":114},"scripts\u002Fadd_slide.py",14537,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Fadd_slide.py",{"path":116,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":117,"sourceHtmlUrl":118},"scripts\u002Fapply_theme.js",5334,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Fapply_theme.js",{"path":120,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":121,"sourceHtmlUrl":122},"scripts\u002Fclean.py",10415,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Fclean.py",{"path":124,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":125,"sourceHtmlUrl":126},"scripts\u002Foffice\u002Fhelpers\u002F__init__.py",3380,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fhelpers\u002F__init__.py",{"path":128,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":129,"sourceHtmlUrl":130},"scripts\u002Foffice\u002Fhelpers\u002Fpptx_chart.py",5862,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fhelpers\u002Fpptx_chart.py",{"path":132,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":133,"sourceHtmlUrl":134},"scripts\u002Foffice\u002Fhelpers\u002Fpptx_slide.py",1675,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fhelpers\u002Fpptx_slide.py",{"path":136,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":137,"sourceHtmlUrl":138},"scripts\u002Foffice\u002Fhelpers\u002Fpptx_theme.py",3510,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fhelpers\u002Fpptx_theme.py",{"path":140,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":141,"sourceHtmlUrl":142},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-contentTypes.xsd",1963,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-contentTypes.xsd",{"path":144,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":145,"sourceHtmlUrl":146},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-coreProperties.xsd",2515,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-coreProperties.xsd",{"path":148,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":149,"sourceHtmlUrl":150},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-digSig.xsd",2856,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-digSig.xsd",{"path":152,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":153,"sourceHtmlUrl":154},"scripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-relationships.xsd",1344,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fecma\u002Ffouth-edition\u002Fopc-relationships.xsd",{"path":156,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":157,"sourceHtmlUrl":158},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chart.xsd",74984,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chart.xsd",{"path":160,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":161,"sourceHtmlUrl":162},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chartDrawing.xsd",6956,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-chartDrawing.xsd",{"path":164,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":165,"sourceHtmlUrl":166},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-diagram.xsd",51302,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-diagram.xsd",{"path":168,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":169,"sourceHtmlUrl":170},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-lockedCanvas.xsd",624,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-lockedCanvas.xsd",{"path":172,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":173,"sourceHtmlUrl":174},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-main.xsd",152039,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-main.xsd",{"path":176,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":177,"sourceHtmlUrl":178},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-picture.xsd",1231,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-picture.xsd",{"path":180,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":181,"sourceHtmlUrl":182},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-spreadsheetDrawing.xsd",8862,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-spreadsheetDrawing.xsd",{"path":184,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":185,"sourceHtmlUrl":186},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-wordprocessingDrawing.xsd",14795,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fdml-wordprocessingDrawing.xsd",{"path":188,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":189,"sourceHtmlUrl":190},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fpml.xsd",83612,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fpml.xsd",{"path":192,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":193,"sourceHtmlUrl":194},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-additionalCharacteristics.xsd",1269,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-additionalCharacteristics.xsd",{"path":196,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":197,"sourceHtmlUrl":198},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-bibliography.xsd",7328,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-bibliography.xsd",{"path":200,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":201,"sourceHtmlUrl":202},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-commonSimpleTypes.xsd",6382,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-commonSimpleTypes.xsd",{"path":204,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":205,"sourceHtmlUrl":206},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlDataProperties.xsd",1248,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlDataProperties.xsd",{"path":208,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":209,"sourceHtmlUrl":210},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlSchemaProperties.xsd",880,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-customXmlSchemaProperties.xsd",{"path":212,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":213,"sourceHtmlUrl":214},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesCustom.xsd",2608,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesCustom.xsd",{"path":216,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":217,"sourceHtmlUrl":218},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesExtended.xsd",3507,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesExtended.xsd",{"path":220,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":221,"sourceHtmlUrl":222},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesVariantTypes.xsd",7507,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-documentPropertiesVariantTypes.xsd",{"path":224,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":225,"sourceHtmlUrl":226},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-math.xsd",23313,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-math.xsd",{"path":228,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":229,"sourceHtmlUrl":230},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-relationshipReference.xsd",1367,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fshared-relationshipReference.xsd",{"path":232,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":233,"sourceHtmlUrl":234},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fsml.xsd",242277,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fsml.xsd",{"path":236,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":237,"sourceHtmlUrl":238},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-main.xsd",26148,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-main.xsd",{"path":240,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":241,"sourceHtmlUrl":242},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-officeDrawing.xsd",25279,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-officeDrawing.xsd",{"path":244,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":245,"sourceHtmlUrl":246},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-presentationDrawing.xsd",535,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-presentationDrawing.xsd",{"path":248,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":249,"sourceHtmlUrl":250},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-spreadsheetDrawing.xsd",5712,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-spreadsheetDrawing.xsd",{"path":252,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":253,"sourceHtmlUrl":254},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-wordprocessingDrawing.xsd",4010,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fvml-wordprocessingDrawing.xsd",{"path":256,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":257,"sourceHtmlUrl":258},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fwml.xsd",171367,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fwml.xsd",{"path":260,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":261,"sourceHtmlUrl":262},"scripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fxml.xsd",4646,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002FISO-IEC29500-4_2016\u002Fxml.xsd",{"path":264,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":265,"sourceHtmlUrl":266},"scripts\u002Foffice\u002Fschemas\u002Fmce\u002Fmc.xsd",3127,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmce\u002Fmc.xsd",{"path":268,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":269,"sourceHtmlUrl":270},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2010.xsd",26549,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2010.xsd",{"path":272,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":273,"sourceHtmlUrl":274},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2012.xsd",3745,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2012.xsd",{"path":276,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":277,"sourceHtmlUrl":278},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2018.xsd",901,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-2018.xsd",{"path":280,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":281,"sourceHtmlUrl":282},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cex-2018.xsd",1778,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cex-2018.xsd",{"path":284,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":285,"sourceHtmlUrl":286},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cid-2016.xsd",1002,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-cid-2016.xsd",{"path":288,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":289,"sourceHtmlUrl":290},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-sdtdatahash-2020.xsd",600,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-sdtdatahash-2020.xsd",{"path":292,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":293,"sourceHtmlUrl":294},"scripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-symex-2015.xsd",745,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fschemas\u002Fmicrosoft\u002Fwml-symex-2015.xsd",{"path":296,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":297,"sourceHtmlUrl":298},"scripts\u002Foffice\u002Fsoffice.py",5945,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fsoffice.py",{"path":300,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":301,"sourceHtmlUrl":302},"scripts\u002Foffice\u002Fvalidate.py",6142,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidate.py",{"path":304,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":305,"sourceHtmlUrl":306},"scripts\u002Foffice\u002Fvalidators\u002F__init__.py",336,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidators\u002F__init__.py",{"path":308,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":309,"sourceHtmlUrl":310},"scripts\u002Foffice\u002Fvalidators\u002Fbase.py",33721,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fbase.py",{"path":312,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":313,"sourceHtmlUrl":314},"scripts\u002Foffice\u002Fvalidators\u002Fdocx.py",17482,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fdocx.py",{"path":316,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":317,"sourceHtmlUrl":318},"scripts\u002Foffice\u002Fvalidators\u002Fpptx.py",15966,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fpptx.py",{"path":320,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":321,"sourceHtmlUrl":322},"scripts\u002Foffice\u002Fvalidators\u002Fredlining.py",18017,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Foffice\u002Fvalidators\u002Fredlining.py",{"path":324,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":325,"sourceHtmlUrl":326},"scripts\u002Fslide_text.py",4446,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Fslide_text.py",{"path":328,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":329,"sourceHtmlUrl":330},"scripts\u002Fthumbnail.py",9802,"https:\u002F\u002Fgithub.com\u002Fderseitenschneider\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude-config\u002F.claude\u002Fskills\u002Fsynced\u002F0ce0b40f-f33c-4454-8a14-bd4a36250724_492d02ae-7d32-4227-a9d4-d9f601100de4\u002Fpptx\u002Fscripts\u002Fthumbnail.py",[332,363,388,419,454,477],{"skillNo":333,"name":334,"nameZh":6,"description":335,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":336,"categories":337,"keywords":343,"publishedAt":47},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[338],{"categoryNo":339,"categoryName":340,"taxonomyType":341,"taxonomyTypeDesc":342},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[344,345,346,347,348,349,350,351,352,28,353,354,355,356,357,358,359,360,361,362],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","use","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":364,"name":365,"nameZh":6,"description":366,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":367,"categories":368,"keywords":370,"publishedAt":47},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[369],{"categoryNo":339,"categoryName":340,"taxonomyType":341,"taxonomyTypeDesc":342},[371,372,373,374,375,376,377,378,31,379,380,28,43,381,382,383,384,385,386,387],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","cleanup","unused","todo","work","plan","focus","signals","audit","dependency",{"skillNo":389,"name":390,"nameZh":6,"description":391,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":392,"categories":393,"keywords":401,"publishedAt":47},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[394,397,398],{"categoryNo":395,"categoryName":396,"taxonomyType":341,"taxonomyTypeDesc":342},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":339,"categoryName":340,"taxonomyType":341,"taxonomyTypeDesc":342},{"categoryNo":399,"categoryName":400,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师",[402,403,404,405,406,407,408,349,409,410,411,412,413,414,415,352,416,417,28,418],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":420,"name":421,"nameZh":6,"description":422,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":423,"licenseFileUrl":424,"sourceHtmlUrl":425,"categories":426,"keywords":430,"publishedAt":47},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[427],{"categoryNo":428,"categoryName":429,"taxonomyType":341,"taxonomyTypeDesc":342},"01JBSEEDCAT000000000000009","前端开发",[431,432,433,434,435,436,437,438,439,440,441,442,443,444,445,446,447,448,449,450,451,452,349,453],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":455,"name":456,"nameZh":6,"description":457,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":423,"licenseFileUrl":458,"sourceHtmlUrl":459,"categories":460,"keywords":465,"publishedAt":47},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[461,464],{"categoryNo":462,"categoryName":463,"taxonomyType":341,"taxonomyTypeDesc":342},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":428,"categoryName":429,"taxonomyType":341,"taxonomyTypeDesc":342},[466,37,467,468,469,432,470,441,442,471,472,473,474,349,475,354,476],"webapp testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":478,"name":479,"nameZh":6,"description":480,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":423,"licenseFileUrl":481,"sourceHtmlUrl":482,"categories":483,"keywords":491,"publishedAt":47},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[484,487,488],{"categoryNo":485,"categoryName":486,"taxonomyType":341,"taxonomyTypeDesc":342},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":339,"categoryName":340,"taxonomyType":341,"taxonomyTypeDesc":342},{"categoryNo":489,"categoryName":490,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000036","内容创作者",[492,493,494,495,496,497,498,499,434,500,444,43,501,502,503,504,505,414,506,28,507,508,509,510,511,360,512],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]