Menu
Sequential thinking tool for multi-step problem solving with structured reasoning, confidence tracking, and assumption management.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Address reviewer and bot comments on a GitHub pull request — validate each comment, apply fixes where valid, reply with reasoning, and resolve threads.
Iterative, human-in-the-loop code review that detects gaps, presents them for selection, and fixes them in cycles. Supports both diff-based PR review and holistic codebase analysis.
Safe database access via CLI with mandatory schema exploration before queries. Supports MySQL, PostgreSQL, SQLite, and Redis.
Facilitate brainstorming as a thinking partner that extracts and expands latent ideas rather than generating them outright.
Deep requirements gathering through probing questions that surface hidden requirements, edge cases, and trade-offs before implementation.
Guide for authoring effective skills that extend Claude's capabilities with specialized knowledge, workflows, or tool integrations.
| name | ultrathink |
| description | Sequential thinking tool for multi-step problem solving with structured reasoning, confidence tracking, and assumption management. |
| when_to_use | Use when breaking down complex problems into steps, planning implementations, debugging multi-layered issues, or when explicit step-by-step reasoning is beneficial. |
A tool for dynamic and reflective problem-solving through structured, sequential thoughts.
Use this skill for:
Do NOT use for:
session_id from response--confidence to track uncertainty (0.0-1.0)--is-revision --revises <num>--branch-from <num> --branch-id <name>--assumptions, --depends-on, --invalidatesrisky_assumptions in responsenext_thought_needed is false# 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"}]'
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."
For complete documentation including all CLI options, response schema, and advanced examples, see references/REFERENCE.md.