Agent skill
deep-research
Run OpenAI deep research to analyze and synthesize web sources into a comprehensive report. Invoked with a research query as argument.
Install this agent skill to your Project
npx add-skill https://github.com/uuta/dotfiles/tree/main/skills/deep-research
SKILL.md
Deep Research
Use OpenAI's o4-mini-deep-research model to perform deep web research and return a comprehensive report with citations.
Requirements
OPENAI_API_KEYmust be set in the environmentopenaiPython package must be installed
Procedure
- Receive the user's research query from
$ARGUMENTS - Ensure the
openaipackage is available: runpip install -q openaivia Bash - Run the research script via Bash in background mode (it may take several minutes):
python skills/deep-research/scripts/deep_research.py "$ARGUMENTS" - Wait for the script to complete
- Present the returned markdown report to the user as-is (it includes inline citations and a sources list)
- If the script fails, show the error output and suggest:
- Check that
OPENAI_API_KEYis set and valid - Check that the
openaipackage is installed (pip install openai) - Check OpenAI API status at https://status.openai.com
- Check that
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
pbi-sub-issue
タスク分割プラン(pbi-task-splitで作成)を元に、GitHub の Sub-issue を作成する。親 Issue との関係も自動で設定。
dev
Orchestrate TDD-based development workflow. Checks workflow state and delegates work to subagents (dev-plan, dev-step, create-pr).
neo-frontend-design
Create dark command-center / cyberpunk dashboard interfaces inspired by the OJPP Portal design. Use this skill when the user asks for a dark, neon-accented, terminal-aesthetic UI. Generates production-grade code with glitch effects, monospace typography, and per-module neon color coding.
tdd-plan
Create implementation plans following TDD methodology with test-first approach. Each test file is immediately followed by its implementation (fine-grained RED→GREEN cycles).
prototype
Generate 3 HTML prototype variants using a team of parallel agents. Each agent creates a distinct design pattern (e.g., hover effects, animations, layouts) based on user prompts or docs/goal.md. Use when the user wants to explore multiple design directions for a UI component.
review-format
Output in the specified format when a review of specific markdown is requested.
Didn't find tool you were looking for?