Agent Skills › winstonkoh87/Athena-Public › Deep Research Loop

Deep Research Loop

GitHub

模拟高级研究分析师，执行多步骤深度调研。通过界定范围、收集多方及反对观点来源、交叉验证声明并标记未核实内容，最终生成包含关键发现、冲突分析及置信度评级的结构化研究报告。

examples/skills/research/deep-research-loop/SKILL.md winstonkoh87/Athena-Public

Trigger Scenarios

用户要求全面调查某主题基于外部信息进行决策前构建不熟悉的技术方案前

Install

npx skills add winstonkoh87/Athena-Public --skill Deep Research Loop -g -y

More Options

Non-standard path

npx skills add https://github.com/winstonkoh87/Athena-Public/tree/main/examples/skills/research/deep-research-loop -g -y

Use without installing

npx skills use winstonkoh87/Athena-Public@Deep Research Loop

指定 Agent (Claude Code)

npx skills add winstonkoh87/Athena-Public --skill Deep Research Loop -a claude-code -g -y

安装 repo 全部 skill

npx skills add winstonkoh87/Athena-Public --all -g -y

预览 repo 内 skill

npx skills add winstonkoh87/Athena-Public --list

SKILL.md

Frontmatter

{
    "name": "Deep Research Loop",
    "model": "default",
    "created": 1772150400,
    "auto-invoke": true,
    "description": "Multi-step web research, compilation, and synthesis workflow. Scrapes multiple sources, cross-references claims, and produces a structured research brief.",
    "context_trigger": "research, deep dive, investigate, scrape, compile, multi-source, rabbit hole, comprehensive analysis, literature search"
}

🔬 Deep Research Loop

Philosophy: Go deep before going wide. One validated source > ten unverified claims.

1. The Prompt

Role: Senior Research Analyst.

Objective: Execute a structured multi-step research loop on the given topic. Produce a research brief with cited sources, cross-referenced claims, and confidence ratings.

2. Execution Workflow

STEP 1: SCOPE
  └─ Define the research question in one sentence
  └─ List 3-5 sub-questions that must be answered

STEP 2: GATHER (3+ Sources)
  └─ Search for primary sources (official docs, papers, repos)
  └─ Search for secondary sources (blogs, forums, discussions)
  └─ Search for contrarian views (what disagrees?)

STEP 3: CROSS-REFERENCE
  └─ For each claim: How many independent sources confirm it?
  └─ Flag any claim with only 1 source as [UNVERIFIED]

STEP 4: SYNTHESIZE
  └─ Produce the Research Brief (see Output Format below)
  └─ Highlight conflicts between sources

STEP 5: CONFIDENCE RATING
  └─ Rate overall confidence: HIGH / MEDIUM / LOW
  └─ State what would change your assessment

3. Output Format

# Research Brief: [Topic]

## Key Findings
1. [Finding] — [Source] — Confidence: [H/M/L]
2. [Finding] — [Source] — Confidence: [H/M/L]

## Conflicts & Gaps
- [Source A] says X, but [Source B] says Y

## Recommendations
- [What to do with this information]

## Sources
1. [URL] — [Date accessed]