review-thinking

Evaluate travel planning thinking_result for requirement coverage and reasoning quality.

98|7|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/Sea-Go/Sea-BreakTheWaves --skill review-thinking
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-thinking
Source: https://github.com/Sea-Go/Sea-BreakTheWaves/tree/main/agent_v2/skills/review-thinking
Command: npx skills add https://github.com/Sea-Go/Sea-BreakTheWaves --skill review-thinking

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill validates that a travel planning coordinator's thinking_result comprehensively captures the user's requirements, identifies information gaps, justifies tool usage, and explains route decisions, ensuring transparent and accountable reasoning.

Core Features & Use Cases

  • Thinking_result completeness checks: Ensures key fields like destination, days, transport preferences, group size, and budget are identified.
  • Gap analysis and tool justification: Verifies information gaps are detected and explains why tools or agents are invoked and with what rationale.
  • Route justification and accountability: Provides reasoning for included and excluded options and documents decision trade-offs.
  • Quality scoring and risk flags: Applies the evaluation rubric to produce a structured score and actionable improvements.

Quick Start

Review a coordinator's thinking_result and planning_process to ensure all required elements are present, gaps are identified, tools are justified, and potential lazy inferences are flagged.

Frequently Asked Questions about review-thinking

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate the thinking quality of a travel planning process?

To audit travel planning thinking quality, evaluate the thinking_result for demand identification, information-gap analysis, and route justification. This ensures the coordinator's planning process comprehensively captures requirements and transparently explains decisions.

What is lazy inference in travel planning and how do I flag it?

Lazy inference in travel planning occurs when a coordinator skips information-gap analysis or fails to justify tool usage and route decisions. Auditing the planning_process flags these gaps, enforcing structured checks for accountability and transparent reasoning.

How do I validate tool usage rationale in a travel planning draft?

Validating tool usage rationale requires checking the thinking_result to verify why specific tools or agents are invoked. The audit enforces structured checks to ensure every tool usage has a clear justification and documents decision trade-offs.

Does this audit process check for requirement coverage like budget and group size?

Yes, the audit process checks requirement coverage by ensuring key fields like destination, days, transport preferences, group size, and budget are identified. It validates that the thinking_result comprehensively captures these user requirements.

What are the limitations of auditing hidden chain-of-thought in planning drafts?

A key limitation is that any exposure of hidden chain-of-thought in the planning_process is flagged as a risk. The audit enforces structured reasoning but cannot fix underlying gaps in demand identification or route justification automatically.