deep-research

90 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By LeoYeAI/agent-master-skills (GitHub) · coding · 2,186 stars · scanned at commit 8f88f9a

深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（`claude -p`）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付"成品报告文件路径 + 关键结论/建议摘要"。用于：系统性网页/资料调研、竞品/行业分析、批量链接/数据集分片检索、长文写作与证据整合，或用户提及"深度调研/Deep Research/Wide Research/多 Agent 并行调研/多进程调研"等场景。

Works with any agent that supports SKILL.md skills.

What this skill can do

Connects to the internet

The author does not mention this.

Found in 5 places.

skills/deep-research-skill/SKILL.md, line 80- 推荐形式：`claude -p "prompt" --allowedTools "Read,Write,Edit,Bash,WebFetch,WebSearch,mcp__firecrawl__*"`（以 `claude --help` 为准）。
skills/deep-research-skill/SKILL.md, line 87--allowedTools "Read,Write,Edit,Bash,Glob,Grep,WebFetch,WebSearch,mcp__firecrawl__firecrawl_scrape,mcp__firecrawl__firecrawl_search" \
skills/deep-research-skill/SKILL.md, line 180--allowedTools "Read,Write,Edit,Bash,Glob,Grep,WebFetch,WebSearch,mcp__firecrawl__firecrawl_scrape,mcp__firecrawl__firecrawl_search,mcp__firecrawl__firecrawl_ma

Show 2 more

skills/deep-research-skill/SKILL.md, line 200--allowedTools 'Read,Write,Edit,Bash,WebFetch,WebSearch' \
skills/deep-research-skill/SKILL.md, line 207--allowedTools "Read,Write,Edit,Bash,WebFetch,WebSearch" \

Runs commands on your computer

The author does not mention this. Expected for a coding skill.

Found in 4 places.

skills/deep-research-skill/SKILL.md, line 86timeout 600 claude -p "$(cat "$prompt_file")" \
skills/deep-research-skill/SKILL.md, line 150claude -p "Your prompt here"
skills/deep-research-skill/SKILL.md, line 174prompt_file="$1"

Show 1 more

skills/deep-research-skill/SKILL.md, line 194max_parallel=8

Other copies in this repository

LeoYeAI/agent-master-skills has 2 more folders with a skill named deep-research. This page shows the lowest-scoring copy.

skills/deep-research 100/100 · Low risk
skills/deep-research-2 100/100 · Low risk

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'deep-research' ] || [ -L ~/.agents/skills/'deep-research' ]; then echo 'A skill folder named deep-research already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/LeoYeAI/agent-master-skills' "$d" && git -C "$d" checkout --quiet '8f88f9a0dd5a1075d4f0c7626f9d960844d57575' -- 'skills/deep-research-skill' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/deep-research-skill' ~/.agents/skills/'deep-research' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'deep-research' ~/.claude/skills/'deep-research' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for LeoYeAI/agent-master-skills shows the score of its lowest-scoring skill.

SkillTrust badge for LeoYeAI/agent-master-skills

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/LeoYeAI/agent-master-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/LeoYeAI/agent-master-skills/)

Score history

Date	Version	Score
2026-11-08	`8f88f9a`	90
2026-11-07	`8f88f9a`	90