# Weizhena/Deep-Research-skills

Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control

Repository: https://github.com/Weizhena/Deep-Research-skills
Canonical: https://ross.abutalabs.com/products/deep-research-skills
Language: Python
License: MIT
License Family: permissive
Topics: claude-code, claude-code-skills, deep-research-agent, llm-agent, research, gpt-skills, opencode, opencode-skills
Last push: 2026-08-23T03:25:28+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 17
- inputs: {"age_days": 247, "days_push": 10, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2028, forks 169 (observed 2026-08-28T04:06:06.853492+00:00)

## What it is
A structured deep research skill (prompt/workflow package) for Claude Code, OpenCode, and Codex that runs a two-phase research process: outline generation followed by deep investigation with web search agents. It emphasizes human-in-the-loop control so users can review and steer each research stage.

## Use cases
- run deep research reports inside claude code
- literature survey and paper review automation
- compare frameworks and tools for technology selection
- competitor and market trend analysis
- due diligence research on companies
- structured multi-step research with human approval checkpoints

## When to choose
- you already use Claude Code, OpenCode, or Codex and want a repeatable research workflow
- you want human-in-the-loop control over each research phase
- you need both English and Chinese research skill variants

## When to avoid
- you want a standalone research app rather than a coding-agent skill
- your agent setup cannot enable web search (e.g., OPENCODE_ENABLE_EXA)
- you need a hosted or GUI research tool

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, rag, prompt-engineering, web-scraping, llm-inference
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: cli, python, cross-platform
- tags: claude-code-skills, opencode, codex, deep-research, human-in-the-loop, research-workflow, skills, ai-agents, research

## Member repositories
- Weizhena/Deep-Research-skills (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:06.853492+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:59:39.252415+00:00, confidence not recorded.
  - readme: https://github.com/Weizhena/Deep-Research-skills (fetched 2026-08-28T04:06:06.853492+00:00, sha 73fa6f61cf01)
- Data as of 2026-08-30T08:39:29.467469+00:00.