by tonyazhuuki · Claude Skill · ★ 26
Deep Research Skill for Claude Code A drop-in Claude Code skill that turns Claude into a 10-18 agent research team. Three cycles, hypothesis-driven, adversarial review, domain-specific quality gates — all automated. One command. $3-15 per session. 300-800 line synthesis with evidence grades. What It Does This launches a 3-cycle research pipeline: Cycle 1 — Broad Search: 4-5 SCOUT agents explore the topic in parallel, each with a different reasoning style (analytical, contrarian, mechanistic, systems-thinking, pragmatic). A CRITIC tears apart their findings.
| Stars | 26 |
| Forks | 6 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 70.1273282989943/100 |
| Last Updated | 2026-07-05 |
| Created | 2026-02-16 |
| Platforms | claude-code, python |
| Est. Tokens | ~16k |
Explore other popular claude skill tools:
deep-research-skill is Deep Research skill for Claude Code — 3-cycle multi-agent adversarial ensemble methodology. It is categorized as a Claude Skill with 26 GitHub stars.
deep-research-skill is primarily written in Python.
You can find installation instructions and usage details in the deep-research-skill GitHub repository at github.com/tonyazhuuki/deep-research-skill. The project has 26 stars and 6 forks, indicating an active community.
deep-research-skill is released under the MIT license, making it free to use and modify according to the license terms.