Regex Vs Llm Structured Text
affaan-m/everything-claude-codeWhen you need to pull information from structured text like quizzes or invoices, you have two main tools: regex and LLM. Regex is fast and predictable. An LLM is powerful but costs more. This skill gives you a clear way to choose.
The key idea is to start with regex first. It handles 95 to 98 percent of cases cheaply and reliably. Only when confidence is low do you call an LLM. This hybrid approach saves money and keeps accuracy high.
You get a simple decision tree and code to score confidence. You also get a pattern to add an LLM validator for tricky edge cases. This skill is for anyone who builds text extraction pipelines and wants to balance cost and quality.
Add Regex Vs Llm Structured Text skill to your workflow
Global
mkdir -p ~/.claude/skills/regex-vs-llm-structured-textProject
mkdir -p .claude/skills/regex-vs-llm-structured-textSource Repository
More Automation & Workflows Claude Code Skills
Lark Drivelarksuite/cli
Organize Lark cloud files import export manage permissions and versions
Lark Eventlarksuite/cli
Stream Lark events in real time with simple CLI commands
Lark Workflow Meeting Summarylarksuite/cli
Turn your Lark meeting notes into organized weekly summaries with ease
Lark Approvallarksuite/cli
Easily manage Lark approval instances and tasks from your command line
Implementmattpocock/skills
Implement PRD or issue tasks with TDD tests typechecking and review
Executing Plansobra/superpowers
Load a plan review critically then execute each task with verifications
Subagent Driven Developmentobra/superpowers
Execute plans with fresh subagents per task and thorough reviews for fast iteration
Churn Preventioncoreyhaines31/marketingskills
Reduce customer churn with smart cancel flows and failed payment recovery