Skip to content
Agentmart
Submit a tool

DeepReasoning

Extended thinking for complex problems.

Skill by bharathrajp14

IndexedMIT
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/bharathrajp14-deepreasoning

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

Extended thinking for complex problems. USE WHEN user needs deep analysis, complex reasoning, multi-step problem solving, architectural decisions, OR thorough evaluation of tradeoffs.

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/deepreasoning

What's inside

Skill name
DeepReasoning
Description
Extended thinking for complex problems. USE WHEN user needs deep analysis, complex reasoning, multi-step problem solving, architectural decisions, OR thorough evaluation of tradeoffs.
License
MIT
Instructions
40 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed

Files (1)

  • SKILL.md

SKILL.md (first lines)

# DeepReasoning

Extended thinking mode for complex problems requiring multi-step analysis, tradeoff evaluation, and thorough reasoning.

## Workflow Routing

| Workflow | Trigger | File |
|----------|---------|------|
| **Analyze** | "analyze deeply", "think about", "evaluate" | `Workflows/Analyze.md` |
| **Compare** | "compare options", "tradeoff analysis" | `Workflows/Compare.md` |
| **FirstPrinciples** | "first principles", "from scratch", "fundamentals" | `Workflows/FirstPrinciples.md` |
| **Council** | "debate", "multiple perspectives", "council" | `Workflows/Council.md` |

## Examples

**Example 1: Architecture decision**
```
User: "Should I use PostgreSQL or MongoDB for my real-time analytics platform?"
→ Invokes Compare workflow
→ Analyzes requirements against both options
→ Evaluates: performance, scalability, query patterns, ecosystem
→ Delivers decision matrix with clear recommendation
```

**Example 2: First principles analysis**
```
User: "First principles analysis of why our deployment pipeline is slow"
→ Invokes FirstPrinciples workflow
→ Decomposes to root causes
→ Identifies fundamental constraints
→ Proposes solutions from the ground up
```

## Quick Reference

- **Thinking Modes:** Analysis, Comparison, First Principles, Council (multi-agent debate)
- **Output:** Structured reasoning with evidence and confidence levels
- **Integration:** Can spawn sub-agents for parallel analysis

From bharathrajp14/myai, MIT.

More from bharathrajp14/myai

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 12, 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 bharathrajp14

Cite this page

DeepReasoning skill. Agent Mart. https://agentmart.dev/skills/bharathrajp14-deepreasoning (last updated 2026-10-24)