Tooluck logoTooluck
SKILL.md

deep-research

Agent skill fromdavila7/claude-code-templates

Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.

How to install deep-research

install deep-research
# install the claude-code-templates pack with the skills CLI
npx skills add davila7/claude-code-templates

# or add only this skill to Claude Code: copy the folder

cli-tool/components/skills/ai-research/deep-research/

# into

~/.claude/skills/deep-research/ (all projects)

.claude/skills/deep-research/ (one project)

cli-tool/components/skills/ai-research/deep-research/SKILL.md

MITFull file
1# Gemini Deep Research Skill
2
3Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.
4
5## When to Use This Skill
6
7Use this skill when:
8- Performing market analysis
9- Conducting competitive landscaping
10- Creating literature reviews
11- Doing technical research
12- Performing due diligence
13- Need detailed, cited research reports
14
15## Requirements
16
17- Python 3.8+
18- httpx: `pip install -r requirements.txt`
19- GEMINI_API_KEY environment variable
20
21## Setup
22
231. Get a Gemini API key from [Google AI Studio](https://aistudio.google.com/)
242. Set the environment variable:
25 ```bash
26 export GEMINI_API_KEY=your-api-key-here
27 ```
28 Or create a `.env` file in the skill directory.
29
30## Usage
31
32### Start a research task
33```bash
34python3 scripts/research.py --query "Research the history of Kubernetes"
35```
36
37### With structured output format
38```bash
39python3 scripts/research.py --query "Compare Python web frameworks" \
40 --format "1. Executive Summary\n2. Comparison Table\n3. Recommendations"
41```
42
43### Stream progress in real-time
44```bash
45python3 scripts/research.py --query "Analyze EV battery market" --stream
46```
47
48### Start without waiting
49```bash
50python3 scripts/research.py --query "Research topic" --no-wait
51```
52
53### Check status of running research
54```bash
55python3 scripts/research.py --status <interaction_id>
56```
57
58### Wait for completion
59```bash
60python3 scripts/research.py --wait <interaction_id>
61```
62
63### Continue from previous research
64```bash
65…

Excerpt shown under the repository's MIT license.

More skills in claude-code-templates

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates