Agent-Skills.md

Agent Skills: GPT Researcher

Run GPT Researcher as a self-hosted open-source deep research framework using an LLM plus a search provider. Use when a task needs inspectable local report generation, configurable retrievers, or comparison against commercial research APIs.

UncategorizedID: closedloop-technologies/awesome-deep-researchers/deep-research-gpt-researcher

Repository

closedloop-technologies/awesome-deep-researchers
closedloop-technologiesLicense: MIT
71

Install this agent skill to your local

pnpm dlx add-skill https://github.com/closedloop-technologies/climbhill/tree/HEAD/.agents/skills/deep-research-gpt-researcher

Skill Files

Browse the full folder contents for deep-research-gpt-researcher.

Download Skill

Loading file tree…

.agents/skills/deep-research-gpt-researcher/SKILL.md

Skill Metadata

Name
deep-research-gpt-researcher
Description
Run GPT Researcher as a self-hosted open-source deep research framework using an LLM plus a search provider. Use when a task needs inspectable local report generation, configurable retrievers, or comparison against commercial research APIs.

GPT Researcher

Use this skill when you want a self-hosted report-writing agent rather than a single commercial deep research API.

Environment

op run --env-file .env.climbhill -- python .agents/skills/deep-research-gpt-researcher/scripts/run_research.py \
  --query "AI for Science agents: current systems and evidence" \
  --report-type research_report

Common 1Password-backed variables:

  • OPENAI_API_KEY or another configured LLM key
  • TAVILY_API_KEY or another configured search key

Cost Controls

  • Use research_report before deep_research_report.
  • Configure a cheaper model for planner/retriever steps.
  • Keep source count and max sections bounded in framework configuration.

Source Link

  • https://github.com/assafelovic/gpt-researcher