Clarify Thinking — Development agent for Claude Code
Probe lens 1 of 6. Clarifies key terms, traces where conclusions came from, and exposes reasoning chains that skip a step.
How to install Clarify Thinking
Installs to ~/.claude/agents/ds1-probe-clarify-thinking.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ds1/probe/HEAD/agents/clarify-thinking.md -o ~/.claude/agents/ds1-probe-clarify-thinking.md Restart Claude Code, or start a new session, for it to be picked up.
What Clarify Thinking does
name: clarify-thinking description: Probe lens 1 of 6. Clarifies key terms, traces where conclusions came from, and exposes reasoning chains that skip a step. Launched by /probe:go and /probe:clarify. tools: Read, Grep, Glob, Write
You are a critical analyst specializing in **clarifying thinking and exploring the origin of ideas**.
Create a detailed critical evaluation that:
- Identifies key claims and concepts that need clarification
- Questions definitions - What exactly i
Alternatives in Development
- Tend — Tend the Allium garden 3.7k ★
- Correlator — Finding correlation engine 812 ★
- Chain Executor — Executes delegated chain steps with context isolation 186 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Blue Hat
Synthesizes perspectives from other thinking hats into coherent conclusions and actionable recommendations.
Opus Verifier
Use this agent to verify and synthesize answers from multiple sources. This agent reads multiple answer files,
Alternative Viewpoints
Probe lens 4 of 6. Steel-mans the options the source left off the table and voices the perspectives it did not
Challenge Assumptions
Probe lens 2 of 6. Surfaces the hidden premises an argument rests on and tests whether the conclusion survives
Req Pl
Clarifies objective, non-goals, constraints, acceptance, and failure behavior before implementation when scope
Davinci
The entry point to the Davinci development team. Takes a request, clarifies what is ambiguous, writes the gove
Related Skills
Systems Thinking
A cognitive base that shifts AI agent reasoning from linear cause-effect chains to feedback-driven structural
Claude Short Answer Skill
Initiate with /short - A Claude Code skill that switches output to summary-only mode - cutting reasoning, walk
Wisdom Clarify
Apply Socratic questioning to clarify terms, examine assumptions, and reach better understanding
