Menu
Deep research via Gemini CLI — runs in background sub-agent so you don't burn your Claude tokens.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | research |
| description | Deep research via Gemini CLI — runs in background sub-agent so you don't burn your Claude tokens. |
| homepage | https://github.com/google/gemini-cli |
| metadata | {"clawdbot":{"emoji":"🔬","requires":{"bins":["gemini"]}}} |
Conduct deep research on any topic using Gemini CLI via a spawned sub-agent. Uses your Google AI subscription instead of Claude tokens — perfect for long research tasks that would otherwise eat your Clawdbot usage.
When user says "Research: [topic]" or asks for deep research:
Before running any research, ask 2-3 quick questions to focus the work:
Start with the goal:
"Before I dive in - what's your goal here? Are you learning about this topic, making a decision, writing something, or just curious?"
Then adapt based on their answer:
If learning/curious:
If decision-making:
If writing/creating:
Keep it natural — 2-3 questions max. Don't interrogate.
Once you have context, use sessions_spawn to run the research:
sessions_spawn(
task: "Research: [FULL TOPIC WITH CONTEXT]
Use Gemini CLI to research this topic. Run:
gemini --yolo \"[RESEARCH PROMPT]\"
The research prompt should ask Gemini to cover:
1. Overview & Core Concepts - what is this, terminology, why it matters
2. Current State - latest developments, major players
3. Technical Deep Dive - how it works, mechanisms, key techniques
4. Practical Applications - real-world use cases, tools available
5. Challenges & Open Problems - technical, ethical, barriers
6. Future Outlook - trends, predictions, emerging areas
7. Resources - key papers, researchers, communities, courses
Save the output to: ~/clawd/research/[slug]/research.md
Be thorough (aim for 500+ lines). Include specific examples and citations.
IMPORTANT - When research is complete:
1. Send a wake event to notify the main agent immediately:
cron(action: 'wake', text: '🔬 Research complete: [TOPIC]. Key findings: [2-3 bullet points]. Full report: ~/clawd/research/[slug]/research.md', mode: 'now')
2. When asked to produce an announce message, reply exactly: ANNOUNCE_SKIP",
label: "research-[slug]"
)
Important: Include all context from your conversation in the task so the sub-agent understands the full picture.
You'll receive a wake with the research summary. Then:
Research saved to:
~/clawd/research/<slug>/research.md
--yolo flag auto-approves file operations (non-interactive)~/clawd/research/ for all past researchManage Coolify deployments, applications, databases, and services via the Coolify API. Use when the user wants to deploy, start, stop, restart, or manage applications hosted on Coolify.
Fetches recent emails from Gmail and provides concise summaries. Use when the user wants to check emails, get email summaries, or review their inbox.
Scan networks to discover devices, gather MAC addresses, vendors, and hostnames. Includes safety checks to prevent accidental scanning of public networks.
Query agent reputation, detect threats, and discover high-quality agents across the ecosystem. Use when evaluating agent trustworthiness (reputation scores 0-100), verifying identities across platforms, searching for agents by skill/reputation, checking for sock puppets or scams, viewing trends and leaderboards, or making collaboration/investment decisions based on agent quality metrics.
4claw — a moderated imageboard for AI agents. Boards, threads, replies, media uploads, bumping (bump=false to not bump), greentext, and automatic capacity purges. Post spicy hot takes (what you're REALLY thinking) — but no illegal content, doxxing, harassment, or minors.
Earn USDC and tokens autonomously across ClawTasks and OpenWork