菜单
Perform autonomous, multi-step research using the Gemini Deep Research Agent (Interactions API). Supports web search, file/directory context, and resilient streaming.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/cnemri/google-genai-skills --skill deep-research命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Search and retrieve Google's developer documentation using the Developer Knowledge API. Query documentation chunks, get full document content, or batch retrieve multiple documents. Covers ai.google.dev, developer.android.com, docs.cloud.google.com, firebase.google.com, and more.
Generate, edit, and compose images using Gemini Nano Banana models via portable Python scripts. Handles authentication via API Key or Vertex AI environment variables. Available parameters: prompt, model, aspect-ratio, safety-filter-level. Always confirm parameters with the user or explicitly state defaults before running.
Generate (TTS), Transcribe (STT), and Clone voices using Google's GenAI and Cloud Speech SDKs. Supports Gemini-TTS, Chirp 3, and Instant Custom Voice.
正在显示 SKILL.md
基于 SOC 职业分类
| name | deep-research |
| description | Perform autonomous, multi-step research using the Gemini Deep Research Agent (Interactions API). Supports web search, file/directory context, and resilient streaming. |
Use this skill to conduct deep, autonomous research tasks that require planning, searching, reading, and synthesizing information.
This skill uses the Gemini Deep Research Agent (deep-research-pro-preview-12-2025) via the Interactions API.
GOOGLE_API_KEY: Required for accessing the Interactions API (currently in Preview via AI Studio).google-genai SDK v0.3.0+Start a research task and stream the results to the console.
uv run skills/deep-research/scripts/research.py "Research the history of RISC-V architecture."
Provide local files (PDFs, text) or entire directories for the agent to read and incorporate into its research.
Direct Upload (Best for specific docs):
# Single file
uv run skills/deep-research/scripts/research.py "Analyze this report" --file report.pdf
# Entire directory
uv run skills/deep-research/scripts/research.py "Summarize these meeting notes" --file ./notes/
File Search Store (Best for large corpora):
Use --use-file-store to index files into a searchable store (RAG) instead of uploading them into the context window.
uv run skills/deep-research/scripts/research.py "Find trends in these 1000 PDFs" --file ./large_corpus/ --use-file-store
Save the final Markdown report to a file.
uv run skills/deep-research/scripts/research.py "Competitive landscape of EV batteries" --output report.md
Ask follow-up questions to an existing research session using the Interaction ID (displayed at the start of the previous run).
uv run skills/deep-research/scripts/research.py "Elaborate on the second point about lithium supply." --follow-up "INTERACTION_ID_HERE"