[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M736TB6C8B4B4CKSWKA3ZBJ4":3,"skill-same:01M736TB6C8B4B4CKSWKA3ZBJ4":69},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M736TB6C8B4B4CKSWKA3ZBJ4","ragas",null,"Evaluate RAG pipelines with Ragas — measure faithfulness, answer relevancy, context precision\u002Frecall, and noise sensitivity using LLM-as-judge metrics; run automated test suite generation with TestsetGenerator; integrate with LangChain, LlamaIndex, and CI pipelines.","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fragas\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: ragas\ndescription: Evaluate RAG pipelines with Ragas — measure faithfulness, answer relevancy, context precision\u002Frecall, and noise sensitivity using LLM-as-judge metrics; run automated test suite generation with TestsetGenerator; integrate with LangChain, LlamaIndex, and CI pipelines.\ntriggers:\n  - \"ragas\"\n  - \"rag evaluation\"\n  - \"evaluate rag pipeline\"\n  - \"ragas metrics\"\n  - \"faithfulness metric\"\n  - \"answer relevancy\"\n  - \"context precision\"\n  - \"context recall\"\n  - \"ragas testset\"\n  - \"llm evaluation framework\"\n  - \"rag benchmark\"\n  - \"ragas score\"\n  - \"automated rag testing\"\ndo_not_use_for:\n  - Agent evaluation — use deepeval or custom eval instead\n  - LLM fine-tuning evaluation — use llamafactory instead\n  - General LLM benchmarks (MMLU etc.) — use lm-evaluation-harness instead\nsee_also:\n  - langgraph\n  - litellm\n  - dspy\n---\n\n# Ragas — RAG Pipeline Evaluation\n\n**Source:** explodinggradients\u002Fragas (Apache 2.0) — evaluation framework for RAG applications\n\n## Core Metrics\n\n| Metric | What it measures | Range |\n|--------|-----------------|-------|\n| `Faithfulness` | Does the answer contain only info from context? | 0–1 |\n| `AnswerRelevancy` | How relevant is the answer to the question? | 0–1 |\n| `ContextPrecision` | Are retrieved contexts ranked by relevance? | 0–1 |\n| `ContextRecall` | Does context cover all facts in ground truth? | 0–1 |\n| `AnswerCorrectness` | Factual + semantic similarity to ground truth | 0–1 |\n| `AnswerSimilarity` | Semantic similarity to ground truth answer | 0–1 |\n| `ContextEntityRecall` | Entities from ground truth present in context | 0–1 |\n| `NoiseSensitivity` | How much noise in context affects answer | 0–1 |\n\n## Install\n\n```bash\npip install ragas\npip install ragas[all]   # all integrations\n```\n\n## Basic Evaluation\n\n```python\nfrom datasets import Dataset\nfrom ragas import evaluate\nfrom ragas.metrics import (\n    faithfulness,\n    answer_relevancy,\n    context_precision,\n    context_recall,\n    answer_correctness,\n)\n\n# Prepare evaluation dataset\n# Each sample: question + answer + contexts + ground_truth\ndata = {\n    \"question\": [\n        \"What is the capital of France?\",\n        \"Who invented the telephone?\",\n    ],\n    \"answer\": [\n        \"The capital of France is Paris.\",\n        \"Alexander Graham Bell invented the telephone in 1876.\",\n    ],\n    \"contexts\": [\n        [\"Paris is the capital and most populous city of France.\"],\n        [\"Alexander Graham Bell was the inventor of the telephone.\",\n         \"Bell made the first successful telephone call in 1876.\"],\n    ],\n    \"ground_truth\": [\n        \"Paris\",\n        \"Alexander Graham Bell\",\n    ],\n}\n\ndataset = Dataset.from_dict(data)\n\n# Evaluate — uses OpenAI by default; configure below for other LLMs\nresult = evaluate(\n    dataset=dataset,\n    metrics=[\n        faithfulness,\n        answer_relevancy,\n        context_precision,\n        context_recall,\n        answer_correctness,\n    ],\n)\n\nprint(result)\n# {'faithfulness': 0.97, 'answer_relevancy': 0.95, ...}\ndf = result.to_pandas()\n```\n\n## Configure Evaluation LLM (Anthropic\u002FCustom)\n\n```python\nfrom ragas import evaluate\nfrom ragas.metrics import faithfulness, answer_relevancy\nfrom ragas.llms import LangchainLLMWrapper\nfrom ragas.embeddings import LangchainEmbeddingsWrapper\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_openai import OpenAIEmbeddings\n\n# Use Claude as evaluator\nevaluator_llm = LangchainLLMWrapper(\n    ChatAnthropic(model=\"claude-sonnet-4-5\", api_key=\"your-key\")\n)\nevaluator_embeddings = LangchainEmbeddingsWrapper(\n    OpenAIEmbeddings(model=\"text-embedding-3-small\")\n)\n\n# Apply to metrics\nfaithfulness.llm = evaluator_llm\nanswer_relevancy.llm = evaluator_llm\nanswer_relevancy.embeddings = evaluator_embeddings\n\nresult = evaluate(dataset=dataset, metrics=[faithfulness, answer_relevancy])\n```\n\n## Testset Generation (Auto-create Q&A pairs)\n\n```python\nfrom ragas.testset import TestsetGenerator\nfrom ragas.testset.evolutions import simple, reasoning, multi_context\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_openai import OpenAIEmbeddings\nfrom langchain_community.document_loaders import DirectoryLoader\n\n# Load your documents\nloader = DirectoryLoader(\".\u002Fdocs\", glob=\"**\u002F*.md\")\ndocuments = loader.load()\n\n# Configure generator\ngenerator_llm = ChatAnthropic(model=\"claude-sonnet-4-5\")\ncritic_llm = ChatAnthropic(model=\"claude-opus-4-5\")\nembeddings = OpenAIEmbeddings()\n\ngenerator = TestsetGenerator.from_langchain(\n    generator_llm,\n    critic_llm,\n    embeddings,\n)\n\n# Generate test set with different question types\ntestset = generator.generate_with_langchain_docs(\n    documents,\n    test_size=20,\n    distributions={\n        simple: 0.5,       # straightforward factual questions\n        reasoning: 0.25,   # questions requiring reasoning\n        multi_context: 0.25,  # questions spanning multiple docs\n    },\n)\n\n# Export to pandas\ndf = testset.to_pandas()\nprint(df[[\"question\", \"ground_truth\", \"contexts\"]].head())\n```\n\n## Evaluate a LangChain RAG Pipeline\n\n```python\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_openai import OpenAIEmbeddings\nfrom langchain_community.vectorstores import FAISS\nfrom langchain.chains import RetrievalQA\nfrom langchain.text_splitter import RecursiveCharacterTextSplitter\nfrom datasets import Dataset\nfrom ragas import evaluate\nfrom ragas.metrics import faithfulness, answer_relevancy, context_recall\n\n# Build RAG\nsplitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)\nchunks = splitter.split_documents(documents)\n\nvectorstore = FAISS.from_documents(chunks, OpenAIEmbeddings())\nretriever = vectorstore.as_retriever(search_kwargs={\"k\": 4})\n\nrag_chain = RetrievalQA.from_chain_type(\n    llm=ChatAnthropic(model=\"claude-sonnet-4-5\"),\n    retriever=retriever,\n    return_source_documents=True,\n)\n\n# Run questions through RAG\nquestions = [\"What is X?\", \"How does Y work?\"]\nground_truths = [\"X is ...\", \"Y works by ...\"]\n\nanswers, contexts = [], []\nfor q in questions:\n    result = rag_chain(q)\n    answers.append(result[\"result\"])\n    contexts.append([doc.page_content for doc in result[\"source_documents\"]])\n\n# Evaluate\ndataset = Dataset.from_dict({\n    \"question\": questions,\n    \"answer\": answers,\n    \"contexts\": contexts,\n    \"ground_truth\": ground_truths,\n})\n\nscores = evaluate(dataset=dataset, metrics=[faithfulness, answer_relevancy, context_recall])\nprint(scores)\n```\n\n## Single Sample Evaluation\n\n```python\nfrom ragas.metrics import faithfulness\nfrom ragas import SingleTurnSample\n\nsample = SingleTurnSample(\n    user_input=\"What is photosynthesis?\",\n    response=\"Photosynthesis is the process by which plants convert sunlight into energy.\",\n    retrieved_contexts=[\n        \"Photosynthesis is a biological process used by plants, algae and cyanobacteria to convert light energy into chemical energy stored as glucose.\",\n        \"The process uses carbon dioxide, water, and light to produce glucose and oxygen.\",\n    ],\n)\n\nscorer = faithfulness\nscore = await scorer.single_turn_ascore(sample)\nprint(f\"Faithfulness: {score:.2f}\")\n```\n\n## CI\u002FCD Integration\n\n```python\nimport pytest\nfrom datasets import Dataset\nfrom ragas import evaluate\nfrom ragas.metrics import faithfulness, answer_relevancy\n\nFAITHFULNESS_THRESHOLD = 0.85\nRELEVANCY_THRESHOLD = 0.80\n\ndef test_rag_quality():\n    dataset = load_eval_dataset()  # your eval set\n    result = evaluate(\n        dataset=dataset,\n        metrics=[faithfulness, answer_relevancy],\n    )\n\n    assert result[\"faithfulness\"] >= FAITHFULNESS_THRESHOLD, (\n        f\"Faithfulness {result['faithfulness']:.2f} below threshold {FAITHFULNESS_THRESHOLD}\"\n    )\n    assert result[\"answer_relevancy\"] >= RELEVANCY_THRESHOLD, (\n        f\"Relevancy {result['answer_relevancy']:.2f} below threshold {RELEVANCY_THRESHOLD}\"\n    )\n```\n\n## Anti-Fake-Pass Checks\n\n- [ ] `contexts` must be `list[list[str]]` — outer list per question, inner list of retrieved chunks\n- [ ] `context_recall` requires `ground_truth` — other metrics can run without it\n- [ ] Default evaluator uses OpenAI — explicitly set `metric.llm` for non-OpenAI providers\n- [ ] `evaluate()` makes LLM API calls per metric per sample — costs scale with dataset size\n- [ ] `result[\"faithfulness\"]` is the mean across all samples — check `result.to_pandas()` for per-sample\n- [ ] `TestsetGenerator` requires `critic_llm` separate from `generator_llm` — both needed\n- [ ] Scores of 1.0 on small datasets often indicate degenerate cases — test with ≥20 samples\n","# Ragas — RAG Pipeline Evaluation\n\n**Source:** explodinggradients\u002Fragas (Apache 2.0) — evaluation framework for RAG applications\n\n## Core Metrics\n\n| Metric | What it measures | Range |\n|--------|-----------------|-------|\n| `Faithfulness` | Does the answer contain only info from context? | 0–1 |\n| `AnswerRelevancy` | How relevant is the answer to the question? | 0–1 |\n| `ContextPrecision` | Are retrieved contexts ranked by relevance? | 0–1 |\n| `ContextRecall` | Does context cover all facts in ground truth? | 0–1 |\n| `AnswerCorrectness` | Factual + semantic similarity to ground truth | 0–1 |\n| `AnswerSimilarity` | Semantic similarity to ground truth answer | 0–1 |\n| `ContextEntityRecall` | Entities from ground truth present in context | 0–1 |\n| `NoiseSensitivity` | How much noise in context affects answer | 0–1 |\n\n## Install\n\n```bash\npip install ragas\npip install ragas[all]   # all integrations\n```\n\n## Basic Evaluation\n\n```python\nfrom datasets import Dataset\nfrom ragas import evaluate\nfrom ragas.metrics import (\n    faithfulness,\n    answer_relevancy,\n    context_precision,\n    context_recall,\n    answer_correctness,\n)\n\n# Prepare evaluation dataset\n# Each sample: question + answer + contexts + ground_truth\ndata = {\n    \"question\": [\n        \"What is the capital of France?\",\n        \"Who invented the telephone?\",\n    ],\n    \"answer\": [\n        \"The capital of France is Paris.\",\n        \"Alexander Graham Bell invented the telephone in 1876.\",\n    ],\n    \"contexts\": [\n        [\"Paris is the capital and most populous city of France.\"],\n        [\"Alexander Graham Bell was the inventor of the telephone.\",\n         \"Bell made the first successful telephone call in 1876.\"],\n    ],\n    \"ground_truth\": [\n        \"Paris\",\n        \"Alexander Graham Bell\",\n    ],\n}\n\ndataset = Dataset.from_dict(data)\n\n# Evaluate — uses OpenAI by default; configure below for other LLMs\nresult = evaluate(\n    dataset=dataset,\n    metrics=[\n        faithfulness,\n        answer_relevancy,\n        context_precision,\n        context_recall,\n        answer_correctness,\n    ],\n)\n\nprint(result)\n# {'faithfulness': 0.97, 'answer_relevancy': 0.95, ...}\ndf = result.to_pandas()\n```\n\n## Configure Evaluation LLM (Anthropic\u002FCustom)\n\n```python\nfrom ragas import evaluate\nfrom ragas.metrics import faithfulness, answer_relevancy\nfrom ragas.llms import LangchainLLMWrapper\nfrom ragas.embeddings import LangchainEmbeddingsWrapper\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_openai import OpenAIEmbeddings\n\n# Use Claude as evaluator\nevaluator_llm = LangchainLLMWrapper(\n    ChatAnthropic(model=\"claude-sonnet-4-5\", api_key=\"your-key\")\n)\nevaluator_embeddings = LangchainEmbeddingsWrapper(\n    OpenAIEmbeddings(model=\"text-embedding-3-small\")\n)\n\n# Apply to metrics\nfaithfulness.llm = evaluator_llm\nanswer_relevancy.llm = evaluator_llm\nanswer_relevancy.embeddings = evaluator_embeddings\n\nresult = evaluate(dataset=dataset, metrics=[faithfulness, answer_relevancy])\n```\n\n## Testset Generation (Auto-create Q&A pairs)\n\n```python\nfrom ragas.testset import TestsetGenerator\nfrom ragas.testset.evolutions import simple, reasoning, multi_context\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_openai import OpenAIEmbeddings\nfrom langchain_community.document_loaders import DirectoryLoader\n\n# Load your documents\nloader = DirectoryLoader(\".\u002Fdocs\", glob=\"**\u002F*.md\")\ndocuments = loader.load()\n\n# Configure generator\ngenerator_llm = ChatAnthropic(model=\"claude-sonnet-4-5\")\ncritic_llm = ChatAnthropic(model=\"claude-opus-4-5\")\nembeddings = OpenAIEmbeddings()\n\ngenerator = TestsetGenerator.from_langchain(\n    generator_llm,\n    critic_llm,\n    embeddings,\n)\n\n# Generate test set with different question types\ntestset = generator.generate_with_langchain_docs(\n    documents,\n    test_size=20,\n    distributions={\n        simple: 0.5,       # straightforward factual questions\n        reasoning: 0.25,   # questions requiring reasoning\n        multi_context: 0.25,  # questions spanning multiple docs\n    },\n)\n\n# Export to pandas\ndf = testset.to_pandas()\nprint(df[[\"question\", \"ground_truth\", \"contexts\"]].head())\n```\n\n## Evaluate a LangChain RAG Pipeline\n\n```python\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_openai import OpenAIEmbeddings\nfrom langchain_community.vectorstores import FAISS\nfrom langchain.chains import RetrievalQA\nfrom langchain.text_splitter import RecursiveCharacterTextSplitter\nfrom datasets import Dataset\nfrom ragas import evaluate\nfrom ragas.metrics import faithfulness, answer_relevancy, context_recall\n\n# Build RAG\nsplitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)\nchunks = splitter.split_documents(documents)\n\nvectorstore = FAISS.from_documents(chunks, OpenAIEmbeddings())\nretriever = vectorstore.as_retriever(search_kwargs={\"k\": 4})\n\nrag_chain = RetrievalQA.from_chain_type(\n    llm=ChatAnthropic(model=\"claude-sonnet-4-5\"),\n    retriever=retriever,\n    return_source_documents=True,\n)\n\n# Run questions through RAG\nquestions = [\"What is X?\", \"How does Y work?\"]\nground_truths = [\"X is ...\", \"Y works by ...\"]\n\nanswers, contexts = [], []\nfor q in questions:\n    result = rag_chain(q)\n    answers.append(result[\"result\"])\n    contexts.append([doc.page_content for doc in result[\"source_documents\"]])\n\n# Evaluate\ndataset = Dataset.from_dict({\n    \"question\": questions,\n    \"answer\": answers,\n    \"contexts\": contexts,\n    \"ground_truth\": ground_truths,\n})\n\nscores = evaluate(dataset=dataset, metrics=[faithfulness, answer_relevancy, context_recall])\nprint(scores)\n```\n\n## Single Sample Evaluation\n\n```python\nfrom ragas.metrics import faithfulness\nfrom ragas import SingleTurnSample\n\nsample = SingleTurnSample(\n    user_input=\"What is photosynthesis?\",\n    response=\"Photosynthesis is the process by which plants convert sunlight into energy.\",\n    retrieved_contexts=[\n        \"Photosynthesis is a biological process used by plants, algae and cyanobacteria to convert light energy into chemical energy stored as glucose.\",\n        \"The process uses carbon dioxide, water, and light to produce glucose and oxygen.\",\n    ],\n)\n\nscorer = faithfulness\nscore = await scorer.single_turn_ascore(sample)\nprint(f\"Faithfulness: {score:.2f}\")\n```\n\n## CI\u002FCD Integration\n\n```python\nimport pytest\nfrom datasets import Dataset\nfrom ragas import evaluate\nfrom ragas.metrics import faithfulness, answer_relevancy\n\nFAITHFULNESS_THRESHOLD = 0.85\nRELEVANCY_THRESHOLD = 0.80\n\ndef test_rag_quality():\n    dataset = load_eval_dataset()  # your eval set\n    result = evaluate(\n        dataset=dataset,\n        metrics=[faithfulness, answer_relevancy],\n    )\n\n    assert result[\"faithfulness\"] >= FAITHFULNESS_THRESHOLD, (\n        f\"Faithfulness {result['faithfulness']:.2f} below threshold {FAITHFULNESS_THRESHOLD}\"\n    )\n    assert result[\"answer_relevancy\"] >= RELEVANCY_THRESHOLD, (\n        f\"Relevancy {result['answer_relevancy']:.2f} below threshold {RELEVANCY_THRESHOLD}\"\n    )\n```\n\n## Anti-Fake-Pass Checks\n\n- [ ] `contexts` must be `list[list[str]]` — outer list per question, inner list of retrieved chunks\n- [ ] `context_recall` requires `ground_truth` — other metrics can run without it\n- [ ] Default evaluator uses OpenAI — explicitly set `metric.llm` for non-OpenAI providers\n- [ ] `evaluate()` makes LLM API calls per metric per sample — costs scale with dataset size\n- [ ] `result[\"faithfulness\"]` is the mean across all samples — check `result.to_pandas()` for per-sample\n- [ ] `TestsetGenerator` requires `critic_llm` separate from `generator_llm` — both needed\n- [ ] Scores of 1.0 on small datasets often indicate degenerate cases — test with ≥20 samples\n",{"name":5,"see_also":24,"triggers":28,"description":7,"do_not_use_for":41},[25,26,27],"langgraph","litellm","dspy",[5,29,30,31,32,33,34,35,36,37,38,39,40],"rag evaluation","evaluate rag pipeline","ragas metrics","faithfulness metric","answer relevancy","context precision","context recall","ragas testset","llm evaluation framework","rag benchmark","ragas score","automated rag testing",[42,43,44],"Agent evaluation — use deepeval or custom eval instead","LLM fine-tuning evaluation — use llamafactory instead","General LLM benchmarks (MMLU etc.) — use lm-evaluation-harness instead","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa",".claude\u002Fskills\u002Fragas",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-14 13:24:09",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill ragas",{"tool":61,"command":62},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill ragas",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill ragas","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fragas\u002FSKILL.md",true,[],[70,78,85,93,101,109],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":6,"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":114,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]