본문으로 건너뛰기
cccskills
무료GitHub에 공개

deep-analyze

Router for DeepAnalyze agentic data-science workflows.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

VectorSpaceLab/AREX-Skill
연동 도구DockerOpenAI
설치 방법 보기

포함된 파일(36)

  • SKILL.md3.8 KB
  • references/install-and-environment.md2.3 KB
  • references/repo-provenance.md1.1 KB
  • references/repo-routing-metadata.json561 B
  • references/troubleshooting.md3.5 KB
  • scripts/check_deepanalyze_environment.py8.9 KB
  • sub-skills/api-and-clients/references/api-reference.md4.5 KB
  • sub-skills/api-and-clients/references/case-study-patterns.md2.8 KB
  • sub-skills/api-and-clients/references/programmatic-usage.md2.9 KB
  • sub-skills/api-and-clients/references/troubleshooting.md4.8 KB
  • sub-skills/api-and-clients/scripts/api_client_smoke.py12.3 KB
  • sub-skills/api-and-clients/scripts/deepanalyze_vllm_smoke.py4.8 KB
  • sub-skills/api-and-clients/scripts/mock_vllm_server.py8.2 KB
  • sub-skills/api-and-clients/scripts/openai_client_smoke.py10.6 KB
  • sub-skills/api-and-clients/SKILL.md1.6 KB
  • sub-skills/interactive-frontends/references/cli-reference.md2.9 KB
  • sub-skills/interactive-frontends/references/jupyter-frontend.md2.6 KB
  • sub-skills/interactive-frontends/references/troubleshooting.md4.2 KB
  • sub-skills/interactive-frontends/references/webui-v2.md5.7 KB
  • sub-skills/interactive-frontends/scripts/check_webui_prereqs.py14.0 KB
  • sub-skills/interactive-frontends/SKILL.md2.2 KB
  • sub-skills/model-serving/references/cloud-api-usage.md1.6 KB
  • sub-skills/model-serving/references/model-customization.md3.1 KB
  • sub-skills/model-serving/references/troubleshooting.md3.0 KB
  • sub-skills/model-serving/references/vllm-and-docker.md4.4 KB
  • sub-skills/model-serving/scripts/quantization_command_builder.py3.1 KB
  • sub-skills/model-serving/scripts/token_tag_plan.py3.0 KB
  • sub-skills/model-serving/scripts/vllm_command_builder.py6.7 KB
  • sub-skills/model-serving/SKILL.md2.0 KB
  • sub-skills/training-and-evaluation/references/benchmark-playgrounds.md9.3 KB
  • sub-skills/training-and-evaluation/references/contribution-and-case-studies.md3.3 KB
  • sub-skills/training-and-evaluation/references/training-recipes.md10.0 KB
  • sub-skills/training-and-evaluation/references/troubleshooting.md7.2 KB
  • sub-skills/training-and-evaluation/scripts/benchmark_command_builder.py18.2 KB
  • sub-skills/training-and-evaluation/scripts/render_training_command.py15.4 KB
  • sub-skills/training-and-evaluation/SKILL.md2.8 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

DeepAnalyze

DeepAnalyze is an agentic data-science repo built around a local reasoning loop, an OpenAI-compatible API server, browser and notebook frontends, model-serving helpers, and official training/evaluation recipes.

Use this router when the request names DeepAnalyze, DeepAnalyze-8B, the OpenAI-compatible API, the browser demo, the CLI, Jupyter, vLLM serving, quantization, tokenizer customization, SFT/RL recipes, or the bundled benchmark playgrounds.

If the checkout may be stale, consult references/repo-provenance.md before trusting any route or claim.

Start here

  1. If you are setting up or checking an environment, read references/install-and-environment.md.
  2. If something fails, read references/troubleshooting.md.
  3. For a read-only health check, run scripts/check_deepanalyze_environment.py against a DeepAnalyze checkout.
  4. Then route to the sub-skill that owns the task surface.

Route map

Task familyRead firstWhy
Programmatic agent loop, workspace execution, file-aware client flowssub-skills/api-and-clients/SKILL.mdCovers DeepAnalyzeVLLM, OpenAI-style clients, file/thread semantics, and API smoke scripts.
CLI, browser WebUI v2, or Jupyter frontendsub-skills/interactive-frontends/SKILL.mdCovers the terminal client, workspace UI, Docker execution mode, and Jupyter MCP flow.
Model download, vLLM launch, quantization, or tokenizer tag extensionsub-skills/model-serving/SKILL.mdCovers the memory table, dry-run vLLM commands, Docker deployment, and model customization.
SFT, RL, benchmark runs, or case-study contributionsub-skills/training-and-evaluation/SKILL.mdCovers the official DeepAnalyze training recipes and benchmark playgrounds.

What this router should answer

  • How to call DeepAnalyze from Python or through an OpenAI-compatible client.
  • How to upload files, keep a thread workspace, and interpret generated files.
  • How to launch or preflight the browser and notebook experiences.
  • How to choose a DeepAnalyze vLLM command from GPU memory and context requirements.
  • How to plan tag-extension, quantization, SFT, RL, or benchmark commands without running placeholder-heavy jobs blindly.

Minimal read-only check

If you need a quick confidence check without starting services, use the bundled checker:

python scripts/check_deepanalyze_environment.py --repo-root <DeepAnalyze checkout>

That checker verifies the core Python imports, selected source-file compilation, DeepAnalyzeVLLM, API TestClient behavior, and WebUI v2 TestClient behavior.

Route away from this root when

  • You already know the exact sub-skill and only need its detailed reference.
  • The task is only about the older legacy browser demo, unless the user explicitly asks for it.
  • The task is about a different package's agent framework, model server, or benchmark harness.

Preferred mental model

  • api-and-clients = "How do I use DeepAnalyze programmatically or test the API?"
  • interactive-frontends = "How do I use the CLI, browser demo, or notebook UI?"
  • model-serving = "How do I size, serve, or customize DeepAnalyze-8B?"
  • training-and-evaluation = "How do I dry-run training, RL, or benchmark jobs?"

When a request spans multiple areas, pick the owner of the primary workflow first and then follow its cross-links.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

3d-resnets-pytorch

무료

Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

VectorSpaceLab/AREX-Skill3392026년 9월 3일 업데이트

3ddfa

무료

Guide 3DDFA Python inference, geometry rendering, training/evaluation, and optional C++ ONNX workflows for 3D dense face alignment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

VectorSpaceLab/AREX-Skill3392026년 9월 3일 업데이트

3ddfa-v2

무료

Routes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

VectorSpaceLab/AREX-Skill3392026년 9월 3일 업데이트

ab3dmot

무료

Operate AB3DMOT 3D multi-object tracking workflows for KITTI and nuScenes data, tracking, evaluation, and visualization.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

VectorSpaceLab/AREX-Skill3392026년 9월 3일 업데이트

accelerate

무료

Use Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model inference/offload, checkpointing, tracking, and troubleshooting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

VectorSpaceLab/AREX-Skill3392026년 9월 3일 업데이트

acme

무료

Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

VectorSpaceLab/AREX-Skill3392026년 9월 3일 업데이트

VectorSpaceLab의 스킬 모두 보기

이 스킬의 문제 신고