Skip to content
Back to skills

Deep Research

ASecurity

Deep research on technical topics using EXA tools with intelligent two-tier caching. Use when user asks to research a topic, investigate best practices, look up information, find patterns, or explore architectures. Also invoked by /research command. Triggers: "research", "look up", "investigate", "deep dive", "find information about", "what are best practices for", "how do others implement".

  • 21 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added February 8, 2026
toolsreact

Works with

  • mcp

Security analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned February 12, 2026

npx -y skills add joaquimscosta/arkhe-claude-plugins --skill deep-research --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Deep Research?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Deep Research
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/joaquimscosta-deep-research/badge)](https://www.skillsdirectory.com/skills/joaquimscosta-deep-research)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: deep-research
description: >
  Deep research on technical topics using EXA tools with intelligent two-tier caching.
  Use when user asks to research a topic, investigate best practices, look up information,
  find patterns, or explore architectures. Also invoked by /research command.
  Triggers: "research", "look up", "investigate", "deep dive", "find information about",
  "what are best practices for", "how do others implement".
---

# Deep Research

Coordinate deep technical research with intelligent caching for cross-project reuse and team knowledge sharing.

## Quick Start

When research is needed:

1. **Check cache first** - Read `~/.claude/plugins/research/index.json`
2. **If cached and valid** - Return cached content, note source
3. **If cache miss or expired** - Invoke `deep-researcher` agent
4. **Report findings** - Include cache status and promote suggestion

## Cache Architecture

| Tier | Location | Purpose | Shared |
|------|----------|---------|--------|
| 1 | `~/.claude/plugins/research/` | Fast, cross-project | User only |
| 2 | `docs/research/` | Curated, version controlled | Team |

## Operations

| Operation | Trigger | Action |
|-----------|---------|--------|
| Research | `/research <topic>` or natural language | Check cache → research if needed → cache results |
| Promote | `/research promote <slug>` | Cache → project docs with section markers |
| Refresh | `/research refresh <slug>` | Force re-research, preserve team notes |
| List | `/research list` | Show inventory of cached + promoted |

## Slug Normalization

Convert topics to cache keys:
- "Domain-Driven Design" → `domain-driven-design`
- "DDD" → `domain-driven-design` (via alias)
- "React Hooks" → `react-hooks`

## Output Format

After research, report:
```
## Research: {Topic}

**Cache:** {Hit | Miss | Expired}
**Source:** {Cached | Fresh research}
**Path:** ~/.claude/plugins/research/entries/{slug}/

[Brief summary of findings]

💡 Run `/research promote {slug}` to add to project docs.
```

## Agent Delegation

For actual research execution, delegate to `deep-researcher` agent:
- Has MCP tool access (EXA web search, code context)
- Handles cache read/write operations
- Structures research output consistently

## Additional Resources

- [WORKFLOW.md](WORKFLOW.md) - Detailed process flows
- [EXAMPLES.md](EXAMPLES.md) - Usage examples
- [TROUBLESHOOTING.md](TROUBLESHOOTING.md) - Common issues and solutions

Files in this skill

  • EXAMPLES.md6.5 KB
  • SKILL.md2.4 KB
  • TROUBLESHOOTING.md4.1 KB
  • WORKFLOW.md18.1 KB
  • scripts/cache_manager.py11.9 KB
  • scripts/index_generator.py9.9 KB
  • scripts/promote.py8.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.