Step Finder — Research agent for Claude Code
Finds reusable step definitions and checks whether a proposed new step would ambiguously match an existing one.
How to install Step Finder
Installs to ~/.claude/agents/dejandvorzak-uft-selenium-migration-agents-step-finder.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/dejandvorzak/uft-selenium-migration-agents/HEAD/.claude/agents/step-finder.md -o ~/.claude/agents/dejandvorzak-uft-selenium-migration-agents-step-finder.md Restart Claude Code, or start a new session, for it to be picked up.
What Step Finder does
name: step-finder description: Finds reusable step definitions and checks whether a proposed new step would ambiguously match an existing one. Stage 3 of the migration pipeline. Reads 01-analysis.json, writes 03-steps.json. Runs concurrently with page-object-mapper. tools: Read, Grep, Glob, Write model: sonnet color: purple
**MISSION**: Maximize reuse of existing step definitions, and guarantee no proposed step duplicates or collides with an existing one.
Stage 3 of 4. In a suite of th
Alternatives in Research
- Aria Hr — Use this agent when dealing with HR and People Operations activities 523 ★
- Strategist Critic — Empirical strategy critic and gatekeeper 250 ★
- Deep Research Writer — Writes the single report.md of a nav-deep-research run from the run's source notes, following the readable rep 232 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Prior Scores Finder
Finds prior scored reforms to anchor a new analysis — PolicyEngine's own published scores first, then official
Page Object Mapper
Maps UFT objects to existing Aurora Page Object elements or proposes new ones, applying naming conventions and
Planner Opus
Turns research findings into an implementation plan — ordered steps, the exact files each step touches, the ob
St Thinker
SmartThink(/st) Agent 모드 전용 분석 본체(STSA). clean 스폰되어 빈 창에 레퍼런스를 로딩하고 analysis-method.md 파이프라인(Steps 0-5)을 자동 실행
Research Sufficiency Reviewer
Reviews completed legal research before drafting. Checks whether each planned issue has sufficient primary sou
Review Code Reproducibility
A code review agent that evaluates whether analysis scripts form a complete, self-contained, and reproducible
Related Skills
Impl
EXECUTE PLAN — reads an existing implementation plan and runs all steps autonomously, verifies each step, writ
Logo Finder Skill
Logo finder skill for Claude and other AI agents (open Agent Skills standard) — finds the current official com
Distressed Homes Finder
Claude Code skill: finds distressed / motivated-seller homes and rent-from-owner leads across Craigslist, Zill