[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XFN96T11K8SM8495R7X84A":3,"skill-same:01M6XFN96T11K8SM8495R7X84A":78},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":14,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6XFN96T11K8SM8495R7X84A","tinker-training-cost",null,"Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.","fadrienne\u002FMyGitHub","fadrienne","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F197874571?v=4","01M6X64V8VWCRSMFZ4EPS2BWXG","Francesca Adrienne","01M6X64VD5MW4F9PHDWQKS7ZAF",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Ftinker-training-cost\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"training","tinker training cost","Tinker","cost","synthetic","pricing","Token Counting","Training Cost","Fine-Tuning","when","for","prices","counting","tuning","tokens","compute","datasets","Transformers","use","model","correct","2026-11-10 10:12:30",false,"---\nname: tinker-training-cost\ndescription: Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.\ncategory: cloud-compute\nversion: 1.0.0\nauthor: Synthetic Sciences\nlicense: MIT\ntags: [Tinker, Training Cost, Token Counting, Fine-Tuning, Pricing]\ndependencies: [transformers>=4.40.0]\n---\n\n# Tinker Training Cost Calculator\n\nCalculate training costs for Tinker fine-tuning jobs by tokenizing your dataset with the correct model tokenizer and applying current pricing.\n\n## Quick Start\n\nUse the bundled script to calculate training costs:\n\n```bash\n# List available models and pricing\npython scripts\u002Fcalculate_cost.py --list-models\n\n# Calculate cost for a JSONL dataset\npython scripts\u002Fcalculate_cost.py training_data.jsonl --model Qwen3-8B --epochs 3\n\n# Output as JSON\npython scripts\u002Fcalculate_cost.py training_data.jsonl --model Llama-3.1-70B --json\n```\n\nThe script:\n1. Loads the correct tokenizer for the selected model\n2. Counts tokens in your JSONL file (supports chat, text, and instruction formats)\n3. Calculates the estimated training cost\n\n## Cost Formula\n\n```\nTraining Cost = (total_tokens × epochs × train_price_per_million) \u002F 1_000_000\n```\n\nWhere:\n- `total_tokens` = tokens in your training dataset (from tokenization)\n- `epochs` = number of training passes (default: 3)\n- `train_price_per_million` = model-specific training rate from pricing table\n\n---\n\n## Tinker Pricing\n\n> **All prices as of January 5, 2026**\n> Source: https:\u002F\u002Fthinkingmachines.ai\u002Ftinker\u002F\n\nAll prices are in **USD per million tokens**.\n\n| Category | Description |\n|----------|-------------|\n| **Prefill** | Processing input context (inference) |\n| **Sample** | Generating output tokens (inference) |\n| **Train** | Training\u002Ffine-tuning tokens |\n\n### Qwen Models\n\n| Model | Prefill | Sample | Train |\n|-------|---------|--------|-------|\n| Qwen3-4B-Instruct-2507 | $0.07 | $0.22 | $0.22 |\n| Qwen3-8B | $0.13 | $0.40 | $0.40 |\n| Qwen3-30B-A3B | $0.12 | $0.30 | $0.36 |\n| Qwen3-VL-30B-A3B-Instruct | $0.18 | $0.44 | $0.53 |\n| Qwen3-32B | $0.49 | $1.47 | $1.47 |\n| Qwen3-235B-Instruct-2507 | $0.68 | $1.70 | $2.04 |\n| Qwen3-VL-235B-A22B-Instruct | $1.02 | $2.56 | $3.07 |\n\n### Llama Models\n\n| Model | Prefill | Sample | Train |\n|-------|---------|--------|-------|\n| Llama-3.2-1B | $0.03 | $0.09 | $0.09 |\n| Llama-3.2-3B | $0.06 | $0.18 | $0.18 |\n| Llama-3.1-8B | $0.13 | $0.40 | $0.40 |\n| Llama-3.1-70B | $1.05 | $3.16 | $3.16 |\n\n### DeepSeek Models\n\n| Model | Prefill | Sample | Train |\n|-------|---------|--------|-------|\n| DeepSeek-V3.1 | $1.13 | $2.81 | $3.38 |\n\n### GPT-OSS Models\n\n| Model | Prefill | Sample | Train |\n|-------|---------|--------|-------|\n| GPT-OSS-120B | $0.18 | $0.44 | $0.52 |\n| GPT-OSS-20B | $0.12 | $0.30 | $0.36 |\n\n### Moonshot Models\n\n| Model | Prefill | Sample | Train |\n|-------|---------|--------|-------|\n| Kimi-K2-Thinking | $0.98 | $2.44 | $2.93 |\n\n---\n\n## Model-to-Tokenizer Mapping\n\nUse the correct HuggingFace tokenizer for accurate token counting:\n\n| Model | HuggingFace Tokenizer |\n|-------|----------------------|\n| Qwen3-4B-Instruct-2507 | `Qwen\u002FQwen3-4B` |\n| Qwen3-8B | `Qwen\u002FQwen3-8B` |\n| Qwen3-30B-A3B | `Qwen\u002FQwen3-30B-A3B` |\n| Qwen3-32B | `Qwen\u002FQwen3-32B` |\n| Qwen3-235B-Instruct-2507 | `Qwen\u002FQwen3-235B-A22B-Instruct` |\n| Qwen3-VL-* | `Qwen\u002FQwen2.5-VL-7B-Instruct` (shared VL tokenizer) |\n| Llama-3.2-1B | `meta-llama\u002FLlama-3.2-1B-Instruct` |\n| Llama-3.2-3B | `meta-llama\u002FLlama-3.2-3B-Instruct` |\n| Llama-3.1-8B | `meta-llama\u002FLlama-3.1-8B-Instruct` |\n| Llama-3.1-70B | `meta-llama\u002FLlama-3.1-70B-Instruct` |\n| DeepSeek-V3.1 | `deepseek-ai\u002FDeepSeek-V3` |\n| GPT-OSS-* | `Qwen\u002FQwen3-8B` (compatible tokenizer) |\n| Kimi-K2-Thinking | `moonshotai\u002FKimi-K2-Instruct` |\n\n---\n\n## Tokenization\n\nThe bundled `scripts\u002Fcalculate_cost.py` handles tokenization automatically. For custom use:\n\n```python\nfrom transformers import AutoTokenizer\n\ntokenizer = AutoTokenizer.from_pretrained(\"Qwen\u002FQwen3-8B\", trust_remote_code=True)\ntoken_count = len(tokenizer.encode(\"Your training text here\"))\n```\n\n### Supported JSONL Formats\n\nThe script handles these training data formats:\n\n**Chat format** (recommended):\n```json\n{\"messages\": [{\"role\": \"user\", \"content\": \"...\"}, {\"role\": \"assistant\", \"content\": \"...\"}]}\n```\n\n**Text format**:\n```json\n{\"text\": \"Your training text here\"}\n```\n\n**Instruction format** (Alpaca-style):\n```json\n{\"instruction\": \"...\", \"input\": \"...\", \"output\": \"...\"}\n```\n\n---\n\n## Quick Cost Examples\n\n### Example 1: Qwen3-8B on 1M tokens, 3 epochs\n```\nDataset tokens: 1,000,000\nTraining tokens: 1,000,000 × 3 = 3,000,000\nCost: 3.0M × $0.40\u002FM = $1.20\n```\n\n### Example 2: Llama-3.1-70B on 5M tokens, 2 epochs\n```\nDataset tokens: 5,000,000\nTraining tokens: 5,000,000 × 2 = 10,000,000\nCost: 10.0M × $3.16\u002FM = $31.60\n```\n\n### Example 3: Qwen3-235B on 2M tokens, 4 epochs\n```\nDataset tokens: 2,000,000\nTraining tokens: 2,000,000 × 4 = 8,000,000\nCost: 8.0M × $2.04\u002FM = $16.32\n```\n\n---\n\n## Important Notes\n\n1. **LoRA Fine-Tuning**: Tinker uses Low-Rank Adaptation (LoRA), not full fine-tuning\n2. **Token Counting**: Always use the model's native tokenizer for accurate counts - different tokenizers produce different token counts for the same text\n3. **Vision Models**: VL models have higher costs due to image processing overhead\n4. **trust_remote_code**: Required for some tokenizers (Qwen, DeepSeek)\n","# Tinker Training Cost Calculator\n\nCalculate training costs for Tinker fine-tuning jobs by tokenizing your dataset with the correct model tokenizer and applying current pricing.\n\n## Quick Start\n\nUse the bundled script to calculate training costs:\n\n```bash\n# List available models and pricing\npython scripts\u002Fcalculate_cost.py --list-models\n\n# Calculate cost for a JSONL dataset\npython scripts\u002Fcalculate_cost.py training_data.jsonl --model Qwen3-8B --epochs 3\n\n# Output as JSON\npython scripts\u002Fcalculate_cost.py training_data.jsonl --model Llama-3.1-70B --json\n```\n\nThe script:\n1. Loads the correct tokenizer for the selected model\n2. Counts tokens in your JSONL file (supports chat, text, and instruction formats)\n3. Calculates the estimated training cost\n\n## Cost Formula\n\n```\nTraining Cost = (total_tokens × epochs × train_price_per_million) \u002F 1_000_000\n```\n\nWhere:\n- `total_tokens` = tokens in your training dataset (from tokenization)\n- `epochs` = number of training passes (default: 3)\n- `train_price_per_million` = model-specific training rate from pricing table\n\n---\n\n## Tinker Pricing\n\n> **All prices as of January 5, 2026**\n> Source: https:\u002F\u002Fthinkingmachines.ai\u002Ftinker\u002F\n\nAll prices are in **USD per million tokens**.\n\n| Category | Description |\n|----------|-------------|\n| **Prefill** | Processing input context (inference) |\n| **Sample** | Generating output tokens (inference) |\n| **Train** | Training\u002Ffine-tuning tokens |\n\n### Qwen Models\n\n| Model | Prefill | Sample | Train |\n|-------|---------|--------|-------|\n| Qwen3-4B-Instruct-2507 | $0.07 | $0.22 | $0.22 |\n| Qwen3-8B | $0.13 | $0.40 | $0.40 |\n| Qwen3-30B-A3B | $0.12 | $0.30 | $0.36 |\n| Qwen3-VL-30B-A3B-Instruct | $0.18 | $0.44 | $0.53 |\n| Qwen3-32B | $0.49 | $1.47 | $1.47 |\n| Qwen3-235B-Instruct-2507 | $0.68 | $1.70 | $2.04 |\n| Qwen3-VL-235B-A22B-Instruct | $1.02 | $2.56 | $3.07 |\n\n### Llama Models\n\n| Model | Prefill | Sample | Train |\n|-------|---------|--------|-------|\n| Llama-3.2-1B | $0.03 | $0.09 | $0.09 |\n| Llama-3.2-3B | $0.06 | $0.18 | $0.18 |\n| Llama-3.1-8B | $0.13 | $0.40 | $0.40 |\n| Llama-3.1-70B | $1.05 | $3.16 | $3.16 |\n\n### DeepSeek Models\n\n| Model | Prefill | Sample | Train |\n|-------|---------|--------|-------|\n| DeepSeek-V3.1 | $1.13 | $2.81 | $3.38 |\n\n### GPT-OSS Models\n\n| Model | Prefill | Sample | Train |\n|-------|---------|--------|-------|\n| GPT-OSS-120B | $0.18 | $0.44 | $0.52 |\n| GPT-OSS-20B | $0.12 | $0.30 | $0.36 |\n\n### Moonshot Models\n\n| Model | Prefill | Sample | Train |\n|-------|---------|--------|-------|\n| Kimi-K2-Thinking | $0.98 | $2.44 | $2.93 |\n\n---\n\n## Model-to-Tokenizer Mapping\n\nUse the correct HuggingFace tokenizer for accurate token counting:\n\n| Model | HuggingFace Tokenizer |\n|-------|----------------------|\n| Qwen3-4B-Instruct-2507 | `Qwen\u002FQwen3-4B` |\n| Qwen3-8B | `Qwen\u002FQwen3-8B` |\n| Qwen3-30B-A3B | `Qwen\u002FQwen3-30B-A3B` |\n| Qwen3-32B | `Qwen\u002FQwen3-32B` |\n| Qwen3-235B-Instruct-2507 | `Qwen\u002FQwen3-235B-A22B-Instruct` |\n| Qwen3-VL-* | `Qwen\u002FQwen2.5-VL-7B-Instruct` (shared VL tokenizer) |\n| Llama-3.2-1B | `meta-llama\u002FLlama-3.2-1B-Instruct` |\n| Llama-3.2-3B | `meta-llama\u002FLlama-3.2-3B-Instruct` |\n| Llama-3.1-8B | `meta-llama\u002FLlama-3.1-8B-Instruct` |\n| Llama-3.1-70B | `meta-llama\u002FLlama-3.1-70B-Instruct` |\n| DeepSeek-V3.1 | `deepseek-ai\u002FDeepSeek-V3` |\n| GPT-OSS-* | `Qwen\u002FQwen3-8B` (compatible tokenizer) |\n| Kimi-K2-Thinking | `moonshotai\u002FKimi-K2-Instruct` |\n\n---\n\n## Tokenization\n\nThe bundled `scripts\u002Fcalculate_cost.py` handles tokenization automatically. For custom use:\n\n```python\nfrom transformers import AutoTokenizer\n\ntokenizer = AutoTokenizer.from_pretrained(\"Qwen\u002FQwen3-8B\", trust_remote_code=True)\ntoken_count = len(tokenizer.encode(\"Your training text here\"))\n```\n\n### Supported JSONL Formats\n\nThe script handles these training data formats:\n\n**Chat format** (recommended):\n```json\n{\"messages\": [{\"role\": \"user\", \"content\": \"...\"}, {\"role\": \"assistant\", \"content\": \"...\"}]}\n```\n\n**Text format**:\n```json\n{\"text\": \"Your training text here\"}\n```\n\n**Instruction format** (Alpaca-style):\n```json\n{\"instruction\": \"...\", \"input\": \"...\", \"output\": \"...\"}\n```\n\n---\n\n## Quick Cost Examples\n\n### Example 1: Qwen3-8B on 1M tokens, 3 epochs\n```\nDataset tokens: 1,000,000\nTraining tokens: 1,000,000 × 3 = 3,000,000\nCost: 3.0M × $0.40\u002FM = $1.20\n```\n\n### Example 2: Llama-3.1-70B on 5M tokens, 2 epochs\n```\nDataset tokens: 5,000,000\nTraining tokens: 5,000,000 × 2 = 10,000,000\nCost: 10.0M × $3.16\u002FM = $31.60\n```\n\n### Example 3: Qwen3-235B on 2M tokens, 4 epochs\n```\nDataset tokens: 2,000,000\nTraining tokens: 2,000,000 × 4 = 8,000,000\nCost: 8.0M × $2.04\u002FM = $16.32\n```\n\n---\n\n## Important Notes\n\n1. **LoRA Fine-Tuning**: Tinker uses Low-Rank Adaptation (LoRA), not full fine-tuning\n2. **Token Counting**: Always use the model's native tokenizer for accurate counts - different tokenizers produce different token counts for the same text\n3. **Vision Models**: VL models have higher costs due to image processing overhead\n4. **trust_remote_code**: Required for some tokenizers (Qwen, DeepSeek)\n",{"name":5,"tags":45,"author":47,"license":15,"version":48,"category":49,"description":7,"dependencies":50},[21,26,25,27,46],"Pricing","Synthetic Sciences","1.0.0","cloud-compute",[51],"transformers>=4.40.0","main","4aa39efd1cdab0b4657ecee16c92a92011a5b10f","openscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Ftinker-training-cost","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub","https:\u002F\u002Fgithub.com\u002Ffadrienne","2026-10-28 00:43:09",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add fadrienne\u002FMyGitHub --skill tinker-training-cost",{"tool":64,"command":65},"bunx","bunx skills add fadrienne\u002FMyGitHub --skill tinker-training-cost",{"tool":67,"command":68},"pnpm","pnpm dlx skills add fadrienne\u002FMyGitHub --skill tinker-training-cost","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Ftinker-training-cost\u002FSKILL.md",true,[72],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fcalculate_cost.py","SCRIPT","脚本",5271,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Ftinker-training-cost\u002Fscripts\u002Fcalculate_cost.py",[79,110,135,169,196,223],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":90,"publishedAt":40},"01M7167B28PK20HP7R7ZED2DY0","statistical-power","Sample size calculation, power analysis, and effect size conversion for scientific studies. Use BEFORE data collection (a priori) to determine required N, or after (post-hoc) to compute achieved power. Covers parametric tests (t-test, ANOVA, chi-square, proportions, correlation, regression), simulation-based power for complex\u002Fclustered\u002Fnested designs, and power curves. Use this skill when someone asks 'how many samples do I need', 'what is my power', 'what effect size can I detect', or any variant. Pairs with \u002Fexperimental-design (choose design first, then compute power) and \u002Fstatistical-analysis (analyze data after collection).","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fstatistical-power\u002FSKILL.md",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[91,92,93,94,95,96,97,98,28,99,100,101,102,103,104,105,106,107,108,109],"power","statistical power","effect","scipy","regression","choose","design","uv","Bash","collection","analysis","calculation","ANOVA","conversion","analyze","t-test","chi-square","simulation","sample",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":119,"publishedAt":40},"01M71677EBCM8EPCE9BZCK8505","statistical-analysis","Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fstatistical-analysis\u002FSKILL.md",[116],{"categoryNo":117,"categoryName":118,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000008","测试与质量",[101,120,91,121,122,123,28,124,125,126,29,127,37,128,129,130,131,132,133,134],"statistical analysis","academic research","implementing","selection","you","reporting","data","tests","with","test","research","results","statsmodels","models","help",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":150,"publishedAt":40},"01M71673R93XAHFH81DBNVNG7H","scientific-writing","Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA\u002FAMA\u002FVancouver), figures\u002Ftables, reporting guidelines (CONSORT\u002FSTROBE\u002FPRISMA), for research papers and journal submissions.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fscientific-writing\u002FSKILL.md",[141,144,145],{"categoryNo":142,"categoryName":143,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[151,152,153,154,155,156,157,158,159,160,99,161,162,163,164,165,166,167,125,168],"writing","scientific","scientific writing","Citations","deep","deep research","never","papers","journal","false","api","prisma","structure","openrouter","Outlines","core skill","read","features",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":179,"publishedAt":40},"01M7166ZPKXBF4EBPHVTJPQBB1","scientific-visualization","Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib\u002Fseaborn\u002Fplotly with publication styles. For quick exploration use seaborn or plotly directly.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fscientific-visualization\u002FSKILL.md",[175,178],{"categoryNo":176,"categoryName":177,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},[180,152,181,182,183,184,185,186,187,159,28,188,189,190,191,192,193,194,29,195],"visualization","scientific visualization","error","ready","quick","exploration","meta-skill","Meta","safe","plotly","annotations","formatting","Publication","figures","panel","submission",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":208,"publishedAt":40},"01M7166VXJWQSSC3RQZP60WBGR","research-code","Debug, profile, review, and restructure Python research and analysis code. Use when analysis scripts crash, produce wrong results, run too slowly, or need a correctness review. Covers: reading tracebacks and diagnosing root causes, hypothesis-driven debugging, reviewing code for common statistical\u002Fnumerical errors, profiling data pipelines, improving reproducibility (seeds, environments, determinism), and structuring analysis scripts for sharing. Distinct from \u002Fexploratory-data-analysis (which understands data) and \u002Fstatistical-analysis (which chooses and runs tests) — this skill focuses on the code itself.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fresearch-code\u002FSKILL.md",[202,205],{"categoryNo":203,"categoryName":204,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":206,"categoryName":207,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000030","开发工程师",[209,210,130,211,212,213,214,98,215,28,99,101,216,217,218,219,220,221,167,222],"code","research code","which","memory","data-analysis","errors","debugging","common","review","data pipelines","run","scripts","line","write",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":227,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":236,"publishedAt":40},"01M7166CF5HSR7SVZYZFWTDX55","markdown-mermaid-writing","Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fmarkdown-mermaid-writing\u002FSKILL.md",[230,233,234,235],{"categoryNo":231,"categoryName":232,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000002","文档处理",{"categoryNo":142,"categoryName":143,"taxonomyType":88,"taxonomyTypeDesc":89},{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},[151,237,238,239,240,241,180,242,243,28,99,101,244,245,246,247,248,249,152,167],"markdown mermaid writing","mermaid","markdown","community","diagrams","project","default","team","guides","text","documentation","references","diagram"]