gpt-research — for Claude Code gpt-research, codex-skills-project, community, for Claude Code, ide skills, agents-md, ai-agents, developer-tools, openai-codex, plugins

v1.0.0
GitHub

À propos de ce Skill

Scenario recommande : Ideal for AI agents that need 원본 gpt-research를 codex 환경용으로 옮긴 스킬입니다. Resume localise : Codex-native skill workspace with repo-local skills, custom agents, local packaged plugins, and validation/smoke-test tooling. It covers agents-md, ai-agents, automation workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Fonctionnalités

원본 gpt-research를 Codex 환경용으로 옮긴 스킬입니다.
외부 GPT 또는 deep research에 넘길 구조화된 프롬프트와 컨텍스트 패키지가 필요할 때
모듈/아키텍처/이슈 단위로 관련 파일을 압축해 handoff해야 할 때
산출물이 구현이 아니라 붙여넣어 바로 쓸 research prompt 일 때
가설을 반복 검증하며 best state를 찾는 장기 연구 작업 → goal-research-loop

# Sujets clés

for Claude Code agents-md ai-agents developer-tools openai-codex plugins
oozoofrog oozoofrog
[0]
[0]
Mis à jour: 4/7/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

Scenario recommande : Ideal for AI agents that need 원본 gpt-research를 codex 환경용으로 옮긴 스킬입니다. Resume localise : Codex-native skill workspace with repo-local skills, custom agents, local packaged plugins, and validation/smoke-test tooling. It covers agents-md, ai-agents, automation workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Pourquoi utiliser cette compétence

Recommandation : gpt-research helps agents 원본 gpt-research를 codex 환경용으로 옮긴 스킬입니다. Codex-native skill workspace with repo-local skills, custom agents, local packaged plugins, and validation/smoke-test tooling. This AI

Meilleur pour

Scenario recommande : Ideal for AI agents that need 원본 gpt-research를 codex 환경용으로 옮긴 스킬입니다.

↓ Cas d'utilisation exploitables for gpt-research

Cas d'usage : Applying 원본 gpt-research를 Codex 환경용으로 옮긴 스킬입니다
Cas d'usage : Applying 외부 GPT 또는 deep research에 넘길 구조화된 프롬프트와 컨텍스트 패키지가 필요할 때
Cas d'usage : Applying 모듈/아키텍처/이슈 단위로 관련 파일을 압축해 handoff해야 할 때

! Sécurité et Limitations

  • Limitation : evaluator: source coverage, chunking, 민감정보 포함 여부를 read-only checklist로 재검토한다
  • Limitation : Requires repository-specific context from the skill documentation
  • Limitation : Works best when the underlying tools and dependencies are already configured

About The Source

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Démo Labs

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ et étapes d’installation

These questions and steps mirror the structured data on this page for better search understanding.

? Questions fréquentes

Qu’est-ce que gpt-research ?

Scenario recommande : Ideal for AI agents that need 원본 gpt-research를 codex 환경용으로 옮긴 스킬입니다. Resume localise : Codex-native skill workspace with repo-local skills, custom agents, local packaged plugins, and validation/smoke-test tooling. It covers agents-md, ai-agents, automation workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Comment installer gpt-research ?

Exécutez la commande : npx killer-skills add oozoofrog/codex-skills-project. Elle fonctionne avec Cursor, Windsurf, VS Code, Claude Code et plus de 19 autres IDE.

Quels sont les cas d’usage de gpt-research ?

Les principaux cas d’usage incluent : Cas d'usage : Applying 원본 gpt-research를 Codex 환경용으로 옮긴 스킬입니다, Cas d'usage : Applying 외부 GPT 또는 deep research에 넘길 구조화된 프롬프트와 컨텍스트 패키지가 필요할 때, Cas d'usage : Applying 모듈/아키텍처/이슈 단위로 관련 파일을 압축해 handoff해야 할 때.

Quels IDE sont compatibles avec gpt-research ?

Cette skill est compatible avec Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Utilisez la CLI Killer-Skills pour une installation unifiée.

Y a-t-il des limites pour gpt-research ?

Limitation : evaluator: source coverage, chunking, 민감정보 포함 여부를 read-only checklist로 재검토한다. Limitation : Requires repository-specific context from the skill documentation. Limitation : Works best when the underlying tools and dependencies are already configured.

↓ Comment installer ce skill

  1. 1. Ouvrir le terminal

    Ouvrez le terminal ou la ligne de commande dans le dossier du projet.

  2. 2. Lancer la commande d’installation

    Exécutez : npx killer-skills add oozoofrog/codex-skills-project. La CLI détectera automatiquement votre IDE ou votre agent et configurera la skill.

  3. 3. Commencer à utiliser le skill

    Le skill est maintenant actif. Votre agent IA peut utiliser gpt-research immédiatement dans le projet.

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

gpt-research

Install gpt-research, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.

SKILL.md
Readonly
Upstream Repository Material
The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

GPT Research

원본 gpt-research를 Codex 환경용으로 옮긴 스킬입니다.

When to use

  • 외부 GPT 또는 deep research에 넘길 구조화된 프롬프트와 컨텍스트 패키지가 필요할 때
  • 모듈/아키텍처/이슈 단위로 관련 파일을 압축해 handoff해야 할 때
  • 산출물이 구현이 아니라 붙여넣어 바로 쓸 research prompt일 때

Do not use when

  • 가설을 반복 검증하며 best state를 찾는 장기 연구 작업 → goal-research-loop
  • 현재 세션에서 바로 구현·수정하면 되는 작업
  • 한 번의 짧은 요약만 있으면 충분하고 외부 handoff prompt가 필요 없는 작업

Quick start

  1. module / arch / issue / custom 중 모드를 고른다.
  2. 관련 소스·설정·문서를 모으고 chunking 범위를 정한다.
  3. 템플릿에 맞춰 최종 프롬프트를 만든다.
  4. 포함 파일 목록과 함께 prompt를 반환한다.

Modes

  • module — 특정 모듈/파일 중심 맥락 추출
  • arch — 프로젝트 구조와 의존성 요약
  • issue — 오류/버그 조사 맥락 정리
  • custom — 사용자가 범위를 직접 지정

Use references

  • references/context-extraction-guide.md
  • references/output-templates.md
  • references/prompting-best-practices.md
  • references/size-limits-and-chunking.md

Workflow

  1. 모드를 결정한다.
  2. 관련 소스, 테스트, 설정, AGENTS.md, README, 빌드 파일을 모은다.
  3. 너무 큰 입력은 chunking 규칙에 따라 압축·분리한다.
  4. 템플릿에 맞춘 최종 프롬프트를 만든다.
  5. 가능하면 pbcopy로 클립보드에 복사하고, 응답에도 프롬프트 본문을 남긴다.

Review Harness

  • mode: optional
  • 공통 기준: ../../../docs/review-harness.md
  • generator: research prompt와 컨텍스트 패키지를 구성한다
  • evaluator: source coverage, chunking, 민감정보 포함 여부를 read-only checklist로 재검토한다
  • 평가축: 소스 커버리지, chunking 적절성, 민감정보 누락, prompt 사용 가능성
  • artifacts/evidence: 포함 파일 목록, chunking 결과, 최종 프롬프트 본문
  • pass condition: 누락·중복·과잉맥락 없이 바로 붙여넣어 쓸 수 있어야 한다
  • 자동 다음 행동: pass면 prompt 반환, refine이면 맥락 추가/제거, pivot이면 mode 변경, escalate면 사람이 범위를 다시 지정한다

Output expectation

  • 선택한 모드
  • 포함한 파일/문서 목록
  • 최종 리서치 프롬프트

Compétences associées

Looking for an alternative to gpt-research or another community skill for your workflow? Explore these related open-source skills.

Voir tout

openclaw-release-maintainer

Logo of openclaw
openclaw

Resume localise : 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 333.8k
⑂ 0
Intelligence artificielle

widget-generator

Logo of f
f

Resume localise : Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and

★ 149.6k
⑂ 0
Intelligence artificielle

flags

Logo of vercel
vercel

Resume localise : The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 138.4k
⑂ 0
Navigateur

pr-review

Logo of pytorch
pytorch

Resume localise : Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 98.6k
⑂ 0
Développeur