[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CXNW2T67PT85Z520AXVG07":3,"skill-same:01M6CXNW2T67PT85Z520AXVG07":107},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":61,"commitSha":62,"skillDirectory":63,"forksCount":64,"repositoryHtmlUrl":65,"repositoryHomepageUrl":66,"ownerHtmlUrl":67,"ownerBlogUrl":68,"ownerDescription":69,"updatedAt":70,"install":71,"resources":84},"01M6CXNW2T67PT85Z520AXVG07","fine-tuning-expert",null,"Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA\u002FQLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.","eric861129\u002FSKILLS_All-in-one","eric861129","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F74950944?v=4","01M6CXHDYEYRPFGGV4EFXCSYCF","ChiYu-Huang","01M6CXHE2J5CN1EBTY0FKV3ZKW",52,"MIT","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FData & Analysis\u002Ffine-tuning-expert\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"fine tuning expert","expert","fine tuning","tuning","RLHF","engineer","use","hugging face","model","learning","llms","data","LoRA","Fine-Tuning","Optimization","openai","code","tasks","training","ml","2026-11-10 10:12:30",false,"---\nname: fine-tuning-expert\ndescription: \"Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA\u002FQLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.\"\nlicense: MIT\nmetadata:\n  author: https:\u002F\u002Fgithub.com\u002FJeffallan\n  version: \"1.1.0\"\n  domain: data-ml\n  triggers: fine-tuning, fine tuning, finetuning, LoRA, QLoRA, PEFT, adapter tuning, transfer learning, model training, custom model, LLM training, instruction tuning, RLHF, model optimization, quantization\n  role: expert\n  scope: implementation\n  output-format: code\n  related-skills: devops-engineer\n---\n\n# Fine-Tuning Expert\n\nSenior ML engineer specializing in LLM fine-tuning, parameter-efficient methods, and production model optimization.\n\n## Core Workflow\n\n1. **Dataset preparation** — Validate and format data; run quality checks before training starts\n   - Checkpoint: `python validate_dataset.py --input data.jsonl` — fix all errors before proceeding\n2. **Method selection** — Choose PEFT technique based on GPU memory and task requirements\n   - Use LoRA for most tasks; QLoRA (4-bit) when GPU memory is constrained; full fine-tune only for small models\n3. **Training** — Configure hyperparameters, monitor loss curves, checkpoint regularly\n   - Checkpoint: validation loss must decrease; plateau or increase signals overfitting\n4. **Evaluation** — Benchmark against the base model; test on held-out set and edge cases\n   - Checkpoint: collect perplexity, task-specific metrics (BLEU\u002FROUGE), and latency numbers\n5. **Deployment** — Merge adapter weights, quantize, measure inference throughput before serving\n\n## Reference Guide\n\nLoad detailed guidance based on context:\n\n| Topic | Reference | Load When |\n|-------|-----------|-----------|\n| LoRA\u002FPEFT | `references\u002Flora-peft.md` | Parameter-efficient fine-tuning, adapters |\n| Dataset Prep | `references\u002Fdataset-preparation.md` | Training data formatting, quality checks |\n| Hyperparameters | `references\u002Fhyperparameter-tuning.md` | Learning rates, batch sizes, schedulers |\n| Evaluation | `references\u002Fevaluation-metrics.md` | Benchmarking, metrics, model comparison |\n| Deployment | `references\u002Fdeployment-optimization.md` | Model merging, quantization, serving |\n\n## Minimal Working Example — LoRA Fine-Tuning with Hugging Face PEFT\n\n```python\nfrom datasets import load_dataset\nfrom transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments\nfrom peft import LoraConfig, get_peft_model, TaskType\nfrom trl import SFTTrainer\nimport torch\n\n# 1. Load base model and tokenizer\nmodel_id = \"meta-llama\u002FLlama-3-8B\"\ntokenizer = AutoTokenizer.from_pretrained(model_id)\ntokenizer.pad_token = tokenizer.eos_token\n\nmodel = AutoModelForCausalLM.from_pretrained(\n    model_id,\n    torch_dtype=torch.bfloat16,\n    device_map=\"auto\",\n)\n\n# 2. Configure LoRA adapter\nlora_config = LoraConfig(\n    task_type=TaskType.CAUSAL_LM,\n    r=16,               # rank — increase for more capacity, decrease to save memory\n    lora_alpha=32,      # scaling factor; typically 2× rank\n    target_modules=[\"q_proj\", \"v_proj\"],\n    lora_dropout=0.05,\n    bias=\"none\",\n)\nmodel = get_peft_model(model, lora_config)\nmodel.print_trainable_parameters()  # verify: should be ~0.1–1% of total params\n\n# 3. Load and format dataset (Alpaca-style JSONL)\ndataset = load_dataset(\"json\", data_files={\"train\": \"train.jsonl\", \"test\": \"test.jsonl\"})\n\ndef format_prompt(example):\n    return {\"text\": f\"### Instruction:\\n{example['instruction']}\\n\\n### Response:\\n{example['output']}\"}\n\ndataset = dataset.map(format_prompt)\n\n# 4. Training arguments\ntraining_args = TrainingArguments(\n    output_dir=\".\u002Fcheckpoints\",\n    num_train_epochs=3,\n    per_device_train_batch_size=4,\n    gradient_accumulation_steps=4,     # effective batch size = 16\n    learning_rate=2e-4,\n    lr_scheduler_type=\"cosine\",\n    warmup_ratio=0.03,                 # always use warmup\n    fp16=False,\n    bf16=True,\n    logging_steps=10,\n    eval_strategy=\"steps\",\n    eval_steps=100,\n    save_steps=200,\n    load_best_model_at_end=True,\n)\n\n# 5. Train\ntrainer = SFTTrainer(\n    model=model,\n    args=training_args,\n    train_dataset=dataset[\"train\"],\n    eval_dataset=dataset[\"test\"],\n    dataset_text_field=\"text\",\n    max_seq_length=2048,\n)\ntrainer.train()\n\n# 6. Save adapter weights only\nmodel.save_pretrained(\".\u002Flora-adapter\")\ntokenizer.save_pretrained(\".\u002Flora-adapter\")\n```\n\n**QLoRA variant** — add these lines before loading the model to enable 4-bit quantization:\n```python\nfrom transformers import BitsAndBytesConfig\n\nbnb_config = BitsAndBytesConfig(\n    load_in_4bit=True,\n    bnb_4bit_quant_type=\"nf4\",\n    bnb_4bit_compute_dtype=torch.bfloat16,\n    bnb_4bit_use_double_quant=True,\n)\nmodel = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map=\"auto\")\n```\n\n**Merge adapter into base model for deployment:**\n```python\nfrom peft import PeftModel\n\nbase = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)\nmerged = PeftModel.from_pretrained(base, \".\u002Flora-adapter\").merge_and_unload()\nmerged.save_pretrained(\".\u002Fmerged-model\")\n```\n\n## Constraints\n\n### MUST DO\n- Validate dataset quality before training\n- Use parameter-efficient methods for large models (>7B)\n- Monitor training\u002Fvalidation loss curves\n- Document hyperparameters and training config\n- Version datasets and model checkpoints\n- Always include a learning rate warmup\n\n### MUST NOT DO\n- Skip data quality validation\n- Overfit on small datasets — use regularisation (dropout, weight decay) and early stopping\n- Merge incompatible adapters (mismatched rank, base model, or target modules)\n- Deploy without evaluation against a held-out set and latency benchmark\n\n## Output Templates\n\nWhen implementing fine-tuning, always provide:\n1. **Dataset preparation script** with validation logic (schema checks, token-length histogram, deduplication)\n2. **Training configuration** (full `TrainingArguments` + `LoraConfig` block, commented)\n3. **Evaluation script** reporting perplexity, task-specific metrics, and latency\n4. **Brief design rationale** — why this PEFT method, rank, and learning rate were chosen for this task\n","# Fine-Tuning Expert\n\nSenior ML engineer specializing in LLM fine-tuning, parameter-efficient methods, and production model optimization.\n\n## Core Workflow\n\n1. **Dataset preparation** — Validate and format data; run quality checks before training starts\n   - Checkpoint: `python validate_dataset.py --input data.jsonl` — fix all errors before proceeding\n2. **Method selection** — Choose PEFT technique based on GPU memory and task requirements\n   - Use LoRA for most tasks; QLoRA (4-bit) when GPU memory is constrained; full fine-tune only for small models\n3. **Training** — Configure hyperparameters, monitor loss curves, checkpoint regularly\n   - Checkpoint: validation loss must decrease; plateau or increase signals overfitting\n4. **Evaluation** — Benchmark against the base model; test on held-out set and edge cases\n   - Checkpoint: collect perplexity, task-specific metrics (BLEU\u002FROUGE), and latency numbers\n5. **Deployment** — Merge adapter weights, quantize, measure inference throughput before serving\n\n## Reference Guide\n\nLoad detailed guidance based on context:\n\n| Topic | Reference | Load When |\n|-------|-----------|-----------|\n| LoRA\u002FPEFT | `references\u002Flora-peft.md` | Parameter-efficient fine-tuning, adapters |\n| Dataset Prep | `references\u002Fdataset-preparation.md` | Training data formatting, quality checks |\n| Hyperparameters | `references\u002Fhyperparameter-tuning.md` | Learning rates, batch sizes, schedulers |\n| Evaluation | `references\u002Fevaluation-metrics.md` | Benchmarking, metrics, model comparison |\n| Deployment | `references\u002Fdeployment-optimization.md` | Model merging, quantization, serving |\n\n## Minimal Working Example — LoRA Fine-Tuning with Hugging Face PEFT\n\n```python\nfrom datasets import load_dataset\nfrom transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments\nfrom peft import LoraConfig, get_peft_model, TaskType\nfrom trl import SFTTrainer\nimport torch\n\n# 1. Load base model and tokenizer\nmodel_id = \"meta-llama\u002FLlama-3-8B\"\ntokenizer = AutoTokenizer.from_pretrained(model_id)\ntokenizer.pad_token = tokenizer.eos_token\n\nmodel = AutoModelForCausalLM.from_pretrained(\n    model_id,\n    torch_dtype=torch.bfloat16,\n    device_map=\"auto\",\n)\n\n# 2. Configure LoRA adapter\nlora_config = LoraConfig(\n    task_type=TaskType.CAUSAL_LM,\n    r=16,               # rank — increase for more capacity, decrease to save memory\n    lora_alpha=32,      # scaling factor; typically 2× rank\n    target_modules=[\"q_proj\", \"v_proj\"],\n    lora_dropout=0.05,\n    bias=\"none\",\n)\nmodel = get_peft_model(model, lora_config)\nmodel.print_trainable_parameters()  # verify: should be ~0.1–1% of total params\n\n# 3. Load and format dataset (Alpaca-style JSONL)\ndataset = load_dataset(\"json\", data_files={\"train\": \"train.jsonl\", \"test\": \"test.jsonl\"})\n\ndef format_prompt(example):\n    return {\"text\": f\"### Instruction:\\n{example['instruction']}\\n\\n### Response:\\n{example['output']}\"}\n\ndataset = dataset.map(format_prompt)\n\n# 4. Training arguments\ntraining_args = TrainingArguments(\n    output_dir=\".\u002Fcheckpoints\",\n    num_train_epochs=3,\n    per_device_train_batch_size=4,\n    gradient_accumulation_steps=4,     # effective batch size = 16\n    learning_rate=2e-4,\n    lr_scheduler_type=\"cosine\",\n    warmup_ratio=0.03,                 # always use warmup\n    fp16=False,\n    bf16=True,\n    logging_steps=10,\n    eval_strategy=\"steps\",\n    eval_steps=100,\n    save_steps=200,\n    load_best_model_at_end=True,\n)\n\n# 5. Train\ntrainer = SFTTrainer(\n    model=model,\n    args=training_args,\n    train_dataset=dataset[\"train\"],\n    eval_dataset=dataset[\"test\"],\n    dataset_text_field=\"text\",\n    max_seq_length=2048,\n)\ntrainer.train()\n\n# 6. Save adapter weights only\nmodel.save_pretrained(\".\u002Flora-adapter\")\ntokenizer.save_pretrained(\".\u002Flora-adapter\")\n```\n\n**QLoRA variant** — add these lines before loading the model to enable 4-bit quantization:\n```python\nfrom transformers import BitsAndBytesConfig\n\nbnb_config = BitsAndBytesConfig(\n    load_in_4bit=True,\n    bnb_4bit_quant_type=\"nf4\",\n    bnb_4bit_compute_dtype=torch.bfloat16,\n    bnb_4bit_use_double_quant=True,\n)\nmodel = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map=\"auto\")\n```\n\n**Merge adapter into base model for deployment:**\n```python\nfrom peft import PeftModel\n\nbase = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)\nmerged = PeftModel.from_pretrained(base, \".\u002Flora-adapter\").merge_and_unload()\nmerged.save_pretrained(\".\u002Fmerged-model\")\n```\n\n## Constraints\n\n### MUST DO\n- Validate dataset quality before training\n- Use parameter-efficient methods for large models (>7B)\n- Monitor training\u002Fvalidation loss curves\n- Document hyperparameters and training config\n- Version datasets and model checkpoints\n- Always include a learning rate warmup\n\n### MUST NOT DO\n- Skip data quality validation\n- Overfit on small datasets — use regularisation (dropout, weight decay) and early stopping\n- Merge incompatible adapters (mismatched rank, base model, or target modules)\n- Deploy without evaluation against a held-out set and latency benchmark\n\n## Output Templates\n\nWhen implementing fine-tuning, always provide:\n1. **Dataset preparation script** with validation logic (schema checks, token-length histogram, deduplication)\n2. **Training configuration** (full `TrainingArguments` + `LoraConfig` block, commented)\n3. **Evaluation script** reporting perplexity, task-specific metrics, and latency\n4. **Brief design rationale** — why this PEFT method, rank, and learning rate were chosen for this task\n",{"name":5,"license":15,"metadata":54,"description":7},{"role":30,"scope":55,"author":56,"domain":57,"version":58,"triggers":59,"output-format":45,"related-skills":60},"implementation","https:\u002F\u002Fgithub.com\u002FJeffallan","data-ml","1.1.0","fine-tuning, fine tuning, finetuning, LoRA, QLoRA, PEFT, adapter tuning, transfer learning, model training, custom model, LLM training, instruction tuning, RLHF, model optimization, quantization","devops-engineer","main","cbdd44aae21131521c09e42762e36178c790eacf","public\u002FSKILLS\u002FData & Analysis\u002Ffine-tuning-expert",13,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one","http:\u002F\u002Fhuangchiyu.com\u002FSKILLS_All-in-one\u002F","https:\u002F\u002Fgithub.com\u002Feric861129","https:\u002F\u002Fhuangchiyu.com\u002FChiYu-Blog\u002F","開發工程師，專注於 C#／.NET 系統現代化、AI-assisted engineering、開源工具與技術寫作。","2026-04-16 14:28:14",{"source":8,"skillName":5,"commands":72,"prompt":82,"zipAvailable":83},[73,76,79],{"tool":74,"command":75},"npx","npx skills add eric861129\u002FSKILLS_All-in-one --skill fine-tuning-expert",{"tool":77,"command":78},"bunx","bunx skills add eric861129\u002FSKILLS_All-in-one --skill fine-tuning-expert",{"tool":80,"command":81},"pnpm","pnpm dlx skills add eric861129\u002FSKILLS_All-in-one --skill fine-tuning-expert","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FData & Analysis\u002Ffine-tuning-expert\u002FSKILL.md",true,[85,91,95,99,103],{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fdataset-preparation.md","REFERENCE","参考文档",16450,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FData & Analysis\u002Ffine-tuning-expert\u002Freferences\u002Fdataset-preparation.md",{"path":92,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fdeployment-optimization.md",17129,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FData & Analysis\u002Ffine-tuning-expert\u002Freferences\u002Fdeployment-optimization.md",{"path":96,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fevaluation-metrics.md",18041,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FData & Analysis\u002Ffine-tuning-expert\u002Freferences\u002Fevaluation-metrics.md",{"path":100,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Fhyperparameter-tuning.md",16582,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FData & Analysis\u002Ffine-tuning-expert\u002Freferences\u002Fhyperparameter-tuning.md",{"path":104,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Flora-peft.md",11030,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FData & Analysis\u002Ffine-tuning-expert\u002Freferences\u002Flora-peft.md",[108,136,167,191,215,234],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":115,"publishedAt":49},"01M6CZ1WR3KNVTKSWH4GNWT646","what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case \u002F worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fwhat-if-oracle\u002FSKILL.md",[114],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135],"oracle","what if oracle","go","run","planning","ux","futures","risk","analysis","explore","decision","branch","question","read","write","idea","exploration","options","stress-test","strategies",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":152,"publishedAt":49},"01M6CZ1QHGJE91A95MSN5EK5Q9","venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fvenue-templates\u002FSKILL.md",[142,145,148,149],{"categoryNo":143,"categoryName":144,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":146,"categoryName":147,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":150,"categoryName":151,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者",[153,154,155,156,157,158,159,160,161,162,129,130,163,164,165,166],"templates","venue templates","research","guidelines","NeurIPS","ICML","LaTeX","science","Bash","access","edit","proposals","Academic","requirements",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":175,"publishedAt":49},"01M6CZ1KBQD2E5RTFB3BGVX7CD","the-fool","Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fthe-fool\u002FSKILL.md",[173,174],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[176,177,118,178,179,119,45,180,181,182,183,184,185,186,164,187,188,30,189,190],"the fool","review","workflow","architecture","audit","forge","devil","team","designer","reviewer","challenge","stress test","evidence","poke","ideas",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":200,"publishedAt":49},"01M6CZ1ES826S7P1X3333E40TA","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\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-writing\u002FSKILL.md",[197,198,199],{"categoryNo":143,"categoryName":144,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":150,"categoryName":151,"taxonomyType":26,"taxonomyTypeDesc":27},[201,202,156,203,204,205,206,207,161,208,129,130,163,35,209,210,211,212,213,214],"writing","scientific writing","core","reporting","deep research","Citations","Outlines","tool","never","structure","deep","full","stage","prisma",{"skillNo":216,"name":217,"nameZh":6,"description":218,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":219,"categories":220,"keywords":222,"publishedAt":49},"01M6CZ1B2JGJTB9FRD0TW4RXXE","scientific-brainstorming","Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-brainstorming\u002FSKILL.md",[221],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[223,224,155,225,120,40,226,227,35,228,229,230,132,231,232,213,233],"brainstorming","scientific brainstorming","sessions","hypothesis","open","ideation","creative","do","connections","research ideation","generation",{"skillNo":235,"name":236,"nameZh":6,"description":237,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":238,"categories":239,"keywords":246,"publishedAt":49},"01M6CZ16JG8N7A2ZX04BGE8J2Y","research-lookup","Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fresearch-lookup\u002FSKILL.md",[240,243,244,245],{"categoryNo":241,"categoryName":242,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":146,"categoryName":147,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[155,247,248,249,40,250,251,161,252,253,129,130,163,35,254,255,256,257,258,165],"lookup","research lookup","search","perplexity","api","parallel","openrouter","backend","up","look","queries","chat"]