Get the FREE Ultimate OpenClaw Setup Guide →

ultrathink

Scanned
npx machina-cli add skill husniadil/ekstend/ultrathink --openclaw
Files (1)
SKILL.md
2.4 KB

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

  1. Start a session with initial thought and estimated total
  2. Continue session using session_id from response
  3. 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 response
  8. 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.

Source

git clone https://github.com/husniadil/ekstend/blob/main/plugins/ultrathink/skills/ultrathink/SKILL.mdView on GitHub

Overview

UltraThink is a tool for dynamic and reflective problem-solving through structured, sequential thoughts. It enables breaking down complex problems into steps, planning implementations, debugging multi-layered issues, and keeping explicit step-by-step reasoning with confidence tracking and assumption management.

How This Skill Works

Start a session with an initial thought and estimated total, then continue the session using the provided session_id from each response. You control reasoning with flags like --confidence (0.0-1.0), --assumptions, --depends-on, and --invalidates, and you can revise with --is-revision, or branch from a thought using --branch-from and --branch-id. The tool signals when more thoughts are needed via next_thought_needed, and you can monitor risky_assumptions in the response.

When to Use It

  • 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

Quick Start

  1. Step 1: Start new session
  2. uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Analyzing the problem..." -n 5
  3. Step 2: Continue session
  4. uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Next step..." -n 5 -s <session-id>
  5. Step 3: With confidence
  6. uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "I believe X is correct" -n 3 -c 0.8
  7. Step 4: With assumption
  8. uv run ${CLAUDE_PLUGIN_ROOT}/skills/ultrathink/scripts/ultrathink.py -t "Assuming Redis available" -n 3 \ --assumptions '[{"id":"A1","text":"Redis is available"}]'

Best Practices

  • Start with an explicit initial thought and total estimate.
  • Use --confidence to track uncertainty (0.0-1.0).
  • Branch and compare alternatives with --branch-from and --branch-id.
  • Track assumptions with --assumptions, --depends-on, and --invalidates.
  • Revise and re-evaluate steps using --is-revision and monitor risky_assumptions.

Example Use Cases

  • Designing a multi-layer caching strategy: analyze LRU vs LFU with TTL expiration and compare outcomes.
  • Architecting a microservices deployment: weigh trade-offs between consistency, latency, and reliability.
  • Algorithm design optimization: evaluate few-path approaches for a shortest-path problem with proofs of correctness.
  • Debugging a multi-service failure: trace dependencies, caches, and timeouts across components.
  • Refactoring a legacy module: perform step-by-step reasoning with revisions and risk tracking.

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers ↗