research

Included with Lifetime

$97 forever

Deep research via Gemini CLI — runs in background sub-agent so you don't burn your Claude tokens.

AI Agents

What this skill does

# Research Skill

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.

## How It Works

**When user says "Research: [topic]" or asks for deep research:**

### Step 1: Clarifying Questions (Always)

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:
- "Any specific aspect you're most interested in?"
- "How technical should I go? (High-level overview vs deep technical detail)"

If decision-making:
- "What decision are you trying to make?"
- "Any specific criteria or constraints I should focus on?"

If writing/creating:
- "What's the output? (Blog post, report, presentation?)"
- "Who's the audience?"

**Keep it natural — 2-3 questions max.** Don't interrogate.

### Step 2: Spawn Research Agent

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.

### Step 3: When You Receive Wake Event

You'll receive a wake with the research summary. Then:
- Share the findings with the user
- Offer to read the full report or dive deeper on sections

## Output Location

Research saved to:
```
~/clawd/research/<slug>/research.md
```

## Tips

- Research typically takes 3-8 minutes depending on complexity
- Gemini CLI uses your Google AI subscription quota
- The `--yolo` flag auto-approves file operations (non-interactive)
- Check `~/clawd/research/` for all past research
- Always include conversation context in the spawn task for better results

Files: 1

Size: 3.2 KB

Complexity: 11/100

Category: AI Agents

Source: https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/research

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts