Skip to content
Agentmart
Submit a tool

deep-analyze

Deep analysis mode — multi-agent investigation of complex systems or problems

Skill by TheTrustedAdvisor

IndexedMIT★ 7
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/thetrustedadvisor-deep-analyze

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Deep analysis mode — multi-agent investigation of complex systems or problems

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/deep-analyze

What's inside

Skill name
deep-analyze
Description
Deep analysis mode — multi-agent investigation of complex systems or problems
License
MIT
Instructions
41 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

## When to Use

- User says "deep-analyze" or "deep analyze"
- Complex system needs thorough understanding from multiple angles
- Architecture review, performance analysis, or security audit

## Workflow

1. **Explore** — map all files and patterns related to the topic. @omg:explore can help with this.

2. **Analyze from multiple perspectives** (in parallel where possible):
   - Review for architectural soundness, trade-offs, and design patterns. @omg:architect can help.
   - Review for security vulnerabilities and threat surface. @omg:security-reviewer can help.
   - Review for code quality, maintainability, and anti-patterns. @omg:code-reviewer can help.

3. **Synthesize** findings from all perspectives:
   - Areas of agreement
   - Areas of disagreement
   - Prioritized recommendations

4. **Persist** analysis to `.omg/research/analysis-{topic}.md`

## Output

Structured multi-perspective report with evidence, trade-offs, and prioritized action items.

## Trigger Keywords

deep-analyze, deep analyze, thorough analysis

## Example

```bash
copilot -i "deep-analyze: the auth subsystem"
```

## Quality Contract

- Multi-angle parallel investigation, findings persisted to .omg/research/

From TheTrustedAdvisor/omg, MIT.

More from TheTrustedAdvisor/omg

Signals

Stars
7
Forks
1
Open issues
0
Last commit (this folder)
Apr 8, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from TheTrustedAdvisor

Cite this page

deep-analyze skill. Agent Mart. https://agentmart.dev/skills/thetrustedadvisor-deep-analyze (last updated 2026-10-24)