
openai-deep-research
by closedloop-technologies
SKILL.md
name: openai-deep-research description: Use OpenAI's Deep Research API (o3 / o4 models) to automate multi-step, citation-backed research workflows.
OpenAI Deep Research Skill
This skill wraps OpenAI's Deep Research API so you can launch autonomous research runs (using o3-deep-research or o4-mini-deep-research) directly from Claude Code.
Setup
-
Dependencies: Install the OpenAI SDK.
pip install openai python-dotenv -
API Key Configuration: Export your OpenAI API key.
echo "OPENAI_API_KEY=sk-..." >> .env if [ -f .gitignore ] && ! grep -q ".env" .gitignore; then echo ".env" >> .gitignore; fiThe Deep Research endpoint requires access to the Early Access program. Ensure your account is enabled before calling the API.
Usage
Use scripts/run_deep_research.py to start a research job and stream the final report to stdout.
Command
python3 scripts/run_deep_research.py --prompt "<research_question>" [--model o4-mini-deep-research] [--effort medium] [--json]
Parameters
--prompt(Required): The investigation prompt.--model(Optional):o4-mini-deep-research(default) oro3-deep-research.--effort(Optional): Reasoning depth, one oflow,medium,high(defaultmedium).--json(Optional): Emit the full response payload as JSON instead of just the synthesized report.--output(Optional): Write the report to a file path.
Example
python3 scripts/run_deep_research.py \
--prompt "Assess the projected market impact of solid state batteries by 2030" \
--model o3-deep-research \
--effort high \
--output reports/solid-state-batteries.md
Output
The script prints the synthesized Deep Research report (with citations) to stdout or saves it to the specified file. When --json is provided, the entire response payload (including intermediate steps, citations, and metadata) is emitted.
Features
- True Deep Research: Uses OpenAI's autonomous planning, browsing, and synthesis stack.
- Configurable Effort: Choose between faster runs (
o4-mini-deep-research) or higher-quality runs (o3-deep-research). - Intermediate Visibility: Optional JSON output exposes the tool traces and citations returned by the API.
Score
Total Score
Based on repository quality metrics
SKILL.mdファイルが含まれている
ライセンスが設定されている
100文字以上の説明がある
GitHub Stars 100以上
3ヶ月以内に更新がある
10回以上フォークされている
オープンIssueが50未満
プログラミング言語が設定されている
1つ以上のタグが設定されている
Reviews
Reviews coming soon