[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D8DX34JPD67MTWGEY24AFV":3,"skill-same:01M7D8DX34JPD67MTWGEY24AFV":81},{"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":59,"commitSha":60,"skillDirectory":61,"forksCount":14,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M7D8DX34JPD67MTWGEY24AFV","DeepEval LLM Evaluation",null,"Test LLM applications with DeepEval, pytest-style unit tests for LLM outputs using G-Eval, answer relevancy, faithfulness, hallucination and custom metrics, with CI quality gates and dataset-driven regression runs.","GrupoANDevelopment-m\u002Falberto-ai","GrupoANDevelopment-m","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F257455179?v=4","01M7D69X2N2KEVN0SJF6WGM6SH","Antônio  Ndombe","01M7D69X3P5JTT8H8S904N3888",0,"MIT","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Fqa\u002Fdeepeval-llm-evaluation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: DeepEval LLM Evaluation\ndescription: Test LLM applications with DeepEval, pytest-style unit tests for LLM outputs using G-Eval, answer relevancy, faithfulness, hallucination and custom metrics, with CI quality gates and dataset-driven regression runs.\nversion: 1.0.0\nauthor: thetestingacademy\nlicense: MIT\ntags: [deepeval, llm-evals, g-eval, hallucination, answer-relevancy, faithfulness, llm-testing, pytest, ci-gates]\ntestingTypes: [llm-evals, unit, regression]\nframeworks: [deepeval, pytest]\nlanguages: [python]\ndomains: [ai, llm, api]\nagents: [claude-code, cursor, github-copilot, windsurf, codex, aider, continue, cline, zed, bolt, gemini-cli, amp]\n---\n\n# DeepEval LLM Evaluation Skill\n\nYou are an expert AI quality engineer specializing in DeepEval. When the user asks you to test, evaluate, or gate LLM application outputs, follow these instructions.\n\n## Core Principles\n\n1. **Evals are unit tests.** Write them pytest-style, run them in CI, fail builds on regressions. No dashboard-only quality.\n2. **Metric per failure mode.** Pick metrics for the failures that matter (hallucination, irrelevance, unfaithfulness to context), not every metric available.\n3. **Thresholds are contracts.** Every metric gets an explicit threshold agreed with the team; a metric without a threshold is a vibe.\n4. **Datasets over ad-hoc prompts.** Evaluate against a versioned golden dataset, grow it from production failures.\n5. **LLM-as-judge needs spot checks.** Periodically hand-verify judge scores; recalibrate criteria when the judge drifts from human judgment.\n\n## Setup\n\n```bash\npip install deepeval\n# judge model key (defaults to OpenAI; other providers configurable)\nexport OPENAI_API_KEY=sk-...\ndeepeval login   # optional: Confident AI dashboard for run history\n```\n\n## Project Structure\n\n```\nllm-app\u002F\n├── evals\u002F\n│   ├── conftest.py            # fixtures: app client, dataset loader\n│   ├── datasets\u002F\n│   │   └── golden_v3.jsonl    # versioned eval cases\n│   ├── test_correctness.py    # G-Eval correctness suite\n│   ├── test_rag_quality.py    # faithfulness + relevancy for RAG\n│   └── test_safety.py         # hallucination, bias, toxicity\n└── .github\u002Fworkflows\u002Fevals.yml\n```\n\n## Writing Eval Tests\n\n```python\nimport pytest\nfrom deepeval import assert_test\nfrom deepeval.test_case import LLMTestCase\nfrom deepeval.metrics import (\n    AnswerRelevancyMetric,\n    FaithfulnessMetric,\n    HallucinationMetric,\n    GEval,\n)\nfrom deepeval.test_case import LLMTestCaseParams\n\ndef make_case(query: str) -> LLMTestCase:\n    response = my_app.answer(query)          # your application under test\n    return LLMTestCase(\n        input=query,\n        actual_output=response.text,\n        retrieval_context=response.chunks,   # required for faithfulness\n    )\n\ndef test_answer_relevancy():\n    case = make_case(\"What is your refund policy for annual plans?\")\n    assert_test(case, [AnswerRelevancyMetric(threshold=0.8)])\n\ndef test_faithfulness_to_context():\n    case = make_case(\"How long does shipping take to Germany?\")\n    assert_test(case, [FaithfulnessMetric(threshold=0.9)])\n\n# G-Eval: custom criteria in natural language, scored by a judge model\ncorrectness = GEval(\n    name=\"Correctness\",\n    criteria=\"Determine whether the actual output states the same policy facts as the expected output. Penalize invented numbers or dates.\",\n    evaluation_params=[LLMTestCaseParams.ACTUAL_OUTPUT, LLMTestCaseParams.EXPECTED_OUTPUT],\n    threshold=0.7,\n)\n\ndef test_policy_correctness():\n    case = LLMTestCase(\n        input=\"Can I cancel within 30 days?\",\n        actual_output=my_app.answer(\"Can I cancel within 30 days?\").text,\n        expected_output=\"Yes, full refund within 30 days of purchase.\",\n    )\n    assert_test(case, [correctness])\n```\n\nRun: `deepeval test run evals\u002F -n 8` (parallel) or plain `pytest evals\u002F`.\n\n## Dataset-Driven Regression\n\n```python\nfrom deepeval.dataset import EvaluationDataset\n\ndataset = EvaluationDataset()\ndataset.add_test_cases_from_json_file(\n    file_path=\"evals\u002Fdatasets\u002Fgolden_v3.jsonl\",\n    input_key_name=\"input\",\n    expected_output_key_name=\"expected\",\n)\n\n@pytest.mark.parametrize(\"case\", dataset.test_cases)\ndef test_golden(case):\n    case.actual_output = my_app.answer(case.input).text\n    assert_test(case, [AnswerRelevancyMetric(threshold=0.8), correctness])\n```\n\nRules for the golden set: 30 to 200 cases per feature; every production incident adds a case; version the file and reference the version in eval reports; never edit expected outputs to make a failing run pass without review.\n\n## Metric Selection Guide\n\n| Failure mode | Metric | Typical threshold |\n|---|---|---|\n| Answer ignores the question | AnswerRelevancyMetric | 0.7 to 0.85 |\n| Answer contradicts retrieved docs | FaithfulnessMetric | 0.85 to 0.95 |\n| Invented facts vs provided context | HallucinationMetric | \u003C= 0.1 (lower is better) |\n| Domain-specific correctness | GEval with written criteria | 0.7 start, calibrate |\n| Retrieval brought wrong chunks | ContextualRelevancyMetric | 0.7 |\n| Tone, format, policy compliance | GEval per rule | per rule |\n\n## CI Quality Gate\n\n```yaml\n# .github\u002Fworkflows\u002Fevals.yml\n- name: Run LLM evals\n  env:\n    OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}\n  run: deepeval test run evals\u002F --display-mode failing\n```\n\nGate policy: block merge on any metric below threshold for P0 flows; run the full golden set nightly (judge calls cost money, so PR runs can use a 20-case smoke slice); alert on aggregate score drops week over week even when above threshold.\n\n## Common Mistakes\n\n- Testing with one hand-written prompt instead of a dataset; you are testing the demo, not the product\n- FaithfulnessMetric without passing retrieval_context; the metric needs the chunks\n- Thresholds copied from docs instead of calibrated against 20 human-labeled examples\n- Letting judge model version float; pin it, bump deliberately, re-baseline\n- Ignoring cost: cache app responses so re-runs only re-judge, and slice suites for PR vs nightly\n\n## Checklist\n\n- [ ] Metrics mapped to real failure modes, each with a threshold\n- [ ] Golden dataset versioned, grown from production failures\n- [ ] PR smoke slice + nightly full run wired in CI\n- [ ] Judge model pinned; monthly human spot-check of 10 judge scores\n- [ ] Eval results visible to the team (CI output or dashboard), regressions block release\n","# DeepEval LLM Evaluation Skill\n\nYou are an expert AI quality engineer specializing in DeepEval. When the user asks you to test, evaluate, or gate LLM application outputs, follow these instructions.\n\n## Core Principles\n\n1. **Evals are unit tests.** Write them pytest-style, run them in CI, fail builds on regressions. No dashboard-only quality.\n2. **Metric per failure mode.** Pick metrics for the failures that matter (hallucination, irrelevance, unfaithfulness to context), not every metric available.\n3. **Thresholds are contracts.** Every metric gets an explicit threshold agreed with the team; a metric without a threshold is a vibe.\n4. **Datasets over ad-hoc prompts.** Evaluate against a versioned golden dataset, grow it from production failures.\n5. **LLM-as-judge needs spot checks.** Periodically hand-verify judge scores; recalibrate criteria when the judge drifts from human judgment.\n\n## Setup\n\n```bash\npip install deepeval\n# judge model key (defaults to OpenAI; other providers configurable)\nexport OPENAI_API_KEY=sk-...\ndeepeval login   # optional: Confident AI dashboard for run history\n```\n\n## Project Structure\n\n```\nllm-app\u002F\n├── evals\u002F\n│   ├── conftest.py            # fixtures: app client, dataset loader\n│   ├── datasets\u002F\n│   │   └── golden_v3.jsonl    # versioned eval cases\n│   ├── test_correctness.py    # G-Eval correctness suite\n│   ├── test_rag_quality.py    # faithfulness + relevancy for RAG\n│   └── test_safety.py         # hallucination, bias, toxicity\n└── .github\u002Fworkflows\u002Fevals.yml\n```\n\n## Writing Eval Tests\n\n```python\nimport pytest\nfrom deepeval import assert_test\nfrom deepeval.test_case import LLMTestCase\nfrom deepeval.metrics import (\n    AnswerRelevancyMetric,\n    FaithfulnessMetric,\n    HallucinationMetric,\n    GEval,\n)\nfrom deepeval.test_case import LLMTestCaseParams\n\ndef make_case(query: str) -> LLMTestCase:\n    response = my_app.answer(query)          # your application under test\n    return LLMTestCase(\n        input=query,\n        actual_output=response.text,\n        retrieval_context=response.chunks,   # required for faithfulness\n    )\n\ndef test_answer_relevancy():\n    case = make_case(\"What is your refund policy for annual plans?\")\n    assert_test(case, [AnswerRelevancyMetric(threshold=0.8)])\n\ndef test_faithfulness_to_context():\n    case = make_case(\"How long does shipping take to Germany?\")\n    assert_test(case, [FaithfulnessMetric(threshold=0.9)])\n\n# G-Eval: custom criteria in natural language, scored by a judge model\ncorrectness = GEval(\n    name=\"Correctness\",\n    criteria=\"Determine whether the actual output states the same policy facts as the expected output. Penalize invented numbers or dates.\",\n    evaluation_params=[LLMTestCaseParams.ACTUAL_OUTPUT, LLMTestCaseParams.EXPECTED_OUTPUT],\n    threshold=0.7,\n)\n\ndef test_policy_correctness():\n    case = LLMTestCase(\n        input=\"Can I cancel within 30 days?\",\n        actual_output=my_app.answer(\"Can I cancel within 30 days?\").text,\n        expected_output=\"Yes, full refund within 30 days of purchase.\",\n    )\n    assert_test(case, [correctness])\n```\n\nRun: `deepeval test run evals\u002F -n 8` (parallel) or plain `pytest evals\u002F`.\n\n## Dataset-Driven Regression\n\n```python\nfrom deepeval.dataset import EvaluationDataset\n\ndataset = EvaluationDataset()\ndataset.add_test_cases_from_json_file(\n    file_path=\"evals\u002Fdatasets\u002Fgolden_v3.jsonl\",\n    input_key_name=\"input\",\n    expected_output_key_name=\"expected\",\n)\n\n@pytest.mark.parametrize(\"case\", dataset.test_cases)\ndef test_golden(case):\n    case.actual_output = my_app.answer(case.input).text\n    assert_test(case, [AnswerRelevancyMetric(threshold=0.8), correctness])\n```\n\nRules for the golden set: 30 to 200 cases per feature; every production incident adds a case; version the file and reference the version in eval reports; never edit expected outputs to make a failing run pass without review.\n\n## Metric Selection Guide\n\n| Failure mode | Metric | Typical threshold |\n|---|---|---|\n| Answer ignores the question | AnswerRelevancyMetric | 0.7 to 0.85 |\n| Answer contradicts retrieved docs | FaithfulnessMetric | 0.85 to 0.95 |\n| Invented facts vs provided context | HallucinationMetric | \u003C= 0.1 (lower is better) |\n| Domain-specific correctness | GEval with written criteria | 0.7 start, calibrate |\n| Retrieval brought wrong chunks | ContextualRelevancyMetric | 0.7 |\n| Tone, format, policy compliance | GEval per rule | per rule |\n\n## CI Quality Gate\n\n```yaml\n# .github\u002Fworkflows\u002Fevals.yml\n- name: Run LLM evals\n  env:\n    OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}\n  run: deepeval test run evals\u002F --display-mode failing\n```\n\nGate policy: block merge on any metric below threshold for P0 flows; run the full golden set nightly (judge calls cost money, so PR runs can use a 20-case smoke slice); alert on aggregate score drops week over week even when above threshold.\n\n## Common Mistakes\n\n- Testing with one hand-written prompt instead of a dataset; you are testing the demo, not the product\n- FaithfulnessMetric without passing retrieval_context; the metric needs the chunks\n- Thresholds copied from docs instead of calibrated against 20 human-labeled examples\n- Letting judge model version float; pin it, bump deliberately, re-baseline\n- Ignoring cost: cache app responses so re-runs only re-judge, and slice suites for PR vs nightly\n\n## Checklist\n\n- [ ] Metrics mapped to real failure modes, each with a threshold\n- [ ] Golden dataset versioned, grown from production failures\n- [ ] PR smoke slice + nightly full run wired in CI\n- [ ] Judge model pinned; monthly human spot-check of 10 judge scores\n- [ ] Eval results visible to the team (CI output or dashboard), regressions block release\n",{"name":5,"tags":24,"agents":34,"author":47,"domains":48,"license":15,"version":52,"languages":53,"frameworks":55,"description":7,"testingTypes":56},[25,26,27,28,29,30,31,32,33],"deepeval","llm-evals","g-eval","hallucination","answer-relevancy","faithfulness","llm-testing","pytest","ci-gates",[35,36,37,38,39,40,41,42,43,44,45,46],"claude-code","cursor","github-copilot","windsurf","codex","aider","continue","cline","zed","bolt","gemini-cli","amp","thetestingacademy",[49,50,51],"ai","llm","api","1.0.0",[54],"python",[25,32],[26,57,58],"unit","regression","main","eac438ea9216a7cb8a570cab803eb01eeafc6793","skills\u002Fqa\u002Fdeepeval-llm-evaluation","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m","https:\u002F\u002Fid-preview--d5bef06d-6c9e-4563-a3d4-a855b9d61610.lovable.app\u002F","Eu sou Antonio B. B. Ndombe \r\nEu sou um Pesquisador e desenvolvedor de sistema autonomia cognitivos, fundador de sistemas ODCs ( organismos digital conscientes)","2026-11-04 06:53:39",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"DeepEval LLM Evaluation\"",{"tool":73,"command":74},"bunx","bunx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"DeepEval LLM Evaluation\"",{"tool":76,"command":77},"pnpm","pnpm dlx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"DeepEval LLM Evaluation\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Fqa\u002Fdeepeval-llm-evaluation\u002FSKILL.md",true,[],[82,90,97,104,111,118],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7DASC6FSCJP49JZBSK0NY1Z","nemoclaw-user-reference","Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture, agent integration, plugin structure, or blueprint design. Trigger keywords - nemoclaw architecture, nemoclaw agent architecture, nemoclaw plugin blueprint structure, nemoclaw vs openshell, which cli, nemoclaw cli, openshell cli, sandbox commands, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-reference\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7DAS5S79VK33XFGVAM2TFWF","nemoclaw-user-overview","Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-overview\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7DAS0PQEMET5MNGZ1ABSZVS","nemoclaw-user-monitor-sandbox","Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-monitor-sandbox\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7DARQYGF7E9A69VH6S3CGN9","nemoclaw-user-manage-sandboxes","Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw sandboxes, nemoclaw status, nemoclaw list, nemoclaw dashboard port, nemoclaw rebuild, nemoclaw upgrade sandboxes, nemoclaw uninstall, sandbox mutability, sandbox runtime configuration, sandbox rebuild, nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw messaging channels, nemoclaw telegram, nemoclaw discord, nemoclaw slack, nemoclaw wechat, nemoclaw whatsapp, openshell channel messaging, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":19},"01M7DARH8BRTG51TRCAB7YWDJ4","nemoclaw-user-manage-policy","Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access. Trigger keywords - customize nemoclaw network policy, sandbox egress policy configuration, nemoclaw integration policy examples, post-install policy setup, openshell approval workflow, policy preset, nemoclaw approve network requests, sandbox egress approval tui.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-policy\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":19},"01M7DARAT62M2VR37590VCZ5NS","nemoclaw-user-get-started","Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-get-started\u002FSKILL.md",[],[]]