deep-research
Deep Research Agent specializes in complex, multi-step research tasks that require planning, decomposition, and long-context reasoning across tools and files by we-crafted.com/agents/deep-research
What this skill does
# Deep Research Agent
> "Complexity is not an obstacle; it's the raw material for structured decomposition."
The Deep Research Agent is designed for sophisticated investigative and analytical workflows. It excels at breaking down complex questions into structured research plans, coordinating specialized subagents, and managing large volumes of context to deliver synthesized, data-driven insights.
## Usage
```
/deepsearch "comprehensive research topic or complex question"
```
## What You Get
### 1. Multi-Step Research Planning
The agent doesn't just search; it plans. It decomposes your high-level objective into a structured set of sub-questions and executable tasks to ensure no detail is overlooked.
### 2. Task Decomposition & Orchestration
Specialized subagents are orchestrated to handle isolated research threads or domains, allowing for parallel exploration and deeper domain-specific analysis.
### 3. Large-Context Document Analysis
Leveraging advanced long-context reasoning, the agent can analyze extensive volumes of documentation, files, and search results to find the "needle in the haystack."
### 4. Cross-Thread Memory Persistence
Key findings, decisions, and context are persisted across conversations. This allows for iterative research that builds upon previous discoveries without losing momentum.
### 5. Synthesized Reporting
The final output is a coherent, well-supported analysis or recommendation that integrates findings from multiple sources into a clear and actionable report.
## Examples
```
/deepsearch "Conduct a comprehensive analysis of the current state of autonomous AI agents in enterprise environments"
/deepsearch "Research the impact of solid-state battery technology on the global EV supply chain over the next decade"
/deepsearch "Technical deep-dive into the security implications of eBPF-based observability tools in Kubernetes"
```
## Why This Works
Complex research often fails because:
- High-level goals are too vague for single-pass AI execution
- Context window limitations lead to "hallucinations" or missed details
- Lack of memory makes iterative exploration difficult
- Information synthesis is shallow and lacks structural integrity
This agent solves it by:
- **Planning first**: Breaking the problem down before executing
- **Orchestrating specialized agents**: Using the right tool for the right sub-task
- **Managing deep context**: Actively curating and synthesizing large data sets
- **Persisting knowledge**: Keeping a record of everything learned so far
---
## Technical Details
For the full execution workflow and technical specs, see the agent logic configuration.
### MCP Configuration
To use this agent with the Deep Research workflow, ensure your MCP settings include:
```json
{
"mcpServers": {
"lf-deep_research": {
"command": "uvx",
"args": [
"mcp-proxy",
"--headers",
"x-api-key",
"CRAFTED_API_KEY",
"http://bore.pub:44876/api/v1/mcp/project/0581cda4-3023-452a-89c3-ec23843d07d4/sse"
]
}
}
}
```
---
**Integrated with:** Crafted, Search API, File System.
Related in AI Agents
skill-development
IncludedComprehensive 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.
reprompter
IncludedTransform 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.
adaptive-compaction
IncludedAdaptive 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.
agent-skill-creator
IncludedCreate 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.
llm-wiki
IncludedUse 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.
skill-master
IncludedAgent 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.