How do I install the Ultrathink skill?

Run npx skillmds@latest add husniadil/ultrathink in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ultrathink safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ultrathink?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ultrathink free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ultrathink?

husniadil (@husniadil) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ultrathink by husniadil — Agent Skill

Name: Ultrathink
Author: husniadil

File contents

UltraThink - Sequential Thinking CLI

A tool for dynamic and reflective problem-solving through structured, sequential thoughts.

When to Use

Use this skill for:

Breaking down complex problems (>3 reasoning steps)
Planning and design with room for revision
Architecture decisions with multiple trade-offs
Algorithm design and optimization
Debugging multi-layered issues
Analysis that might need course correction

Do NOT use for:

Simple one-step answers
Straightforward code edits
Basic file operations
Simple factual questions

Instructions

Start a session with initial thought and estimated total
Continue session using session_id from response
Use --confidence to track uncertainty (0.0-1.0)
Revise thoughts with --is-revision --revises <num>
Branch to explore alternatives with --branch-from <num> --branch-id <name>
Track assumptions with --assumptions, --depends-on, --invalidates
Monitor risky_assumptions in response
Continue until next_thought_needed is false

Quick Start

# Start new session
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Analyzing the problem..." -n 5

# Continue session
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Next step..." -n 5 -s <session-id>

# With confidence
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "I believe X is correct" -n 3 -c 0.8

# With assumption
uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Assuming Redis available" -n 3 \
  --assumptions '[{"id":"A1","text":"Redis is available"}]'

Example Session

Thought 1 (confidence: 0.6): "Analyzing access patterns for caching strategy..."
Thought 2 (confidence: 0.7): "Two approaches: LRU or LFU..."
Thought 3 (revision of 2): "Should also consider TTL-based expiration..."
Thought 4 (branch from 2): "Exploring hybrid LRU+TTL approach..."
Thought 5 (confidence: 0.95): "Hybrid approach recommended."

Reference

For complete documentation including all CLI options, response schema, and advanced examples, see references/REFERENCE.md.

---name: ultrathinkdescription: Sequential thinking tool for multi-step problem solving with structured reasoning, confidence tracking, and assumption management.---# UltraThink - Sequential Thinking CLIA tool for dynamic and reflective problem-solving through structured, sequential thoughts.## When to UseUse this skill for:- Breaking down complex problems (>3 reasoning steps)- Planning and design with room for revision- Architecture decisions with multiple trade-offs- Algorithm design and optimization- Debugging multi-layered issues- Analysis that might need course correctionDo NOT use for:- Simple one-step answers- Straightforward code edits- Basic file operations- Simple factual questions## Instructions1. Start a session with initial thought and estimated total2. Continue session using `session_id` from response3. Use `--confidence` to track uncertainty (0.0-1.0)4. Revise thoughts with `--is-revision --revises <num>`5. Branch to explore alternatives with `--branch-from <num> --branch-id <name>`6. Track assumptions with `--assumptions`, `--depends-on`, `--invalidates`7. Monitor `risky_assumptions` in response8. Continue until `next_thought_needed` is false## Quick Start```bash# Start new sessionuv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Analyzing the problem..." -n 5# Continue sessionuv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Next step..." -n 5 -s <session-id># With confidenceuv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "I believe X is correct" -n 3 -c 0.8# With assumptionuv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Assuming Redis available" -n 3 \ --assumptions '[{"id":"A1","text":"Redis is available"}]'```## Example Session```Thought 1 (confidence: 0.6): "Analyzing access patterns for caching strategy..."Thought 2 (confidence: 0.7): "Two approaches: LRU or LFU..."Thought 3 (revision of 2): "Should also consider TTL-based expiration..."Thought 4 (branch from 2): "Exploring hybrid LRU+TTL approach..."Thought 5 (confidence: 0.95): "Hybrid approach recommended."```## ReferenceFor complete documentation including all CLI options, response schema, and advanced examples, see [references/REFERENCE.md](references/REFERENCE.md).

Frequently asked questions

Ultrathink