Tldr Router

This is a decision tree for mapping natural language questions to the right tldr command layer. Instead of guessing whether you need cfg, dfg, or context for a given task, it gives you the question-to-command shortcuts: "What does X call" maps to context, "Where does variable Y come from" goes to dfg, "What affects line Z" needs slice. The intent detection table is the useful bit, breaking down keywords by navigation, architecture, complexity, data flow, and impact analysis. It's meant to work with the tldr-read-enforcer and tldr-context-inject hooks that auto-route based on your messages, but you can override manually when the automation gets it wrong. Basically a cheat sheet to stop you from running the wrong analysis command.

skills.sh installs: 479
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill tldr-router --agent claude-code

Installs into .claude/skills of the current project.

Files

TLDR Smart Router

Maps questions to the optimal tldr command. Use this to pick the right layer.

Question → Command Mapping

"What files/functions exist?"

tldr tree . --ext .py          # File overview
tldr structure src/ --lang python  # Function/class overview

Use: Starting exploration, orientation

"What does X call / who calls X?"

tldr context <function> --project . --depth 2
tldr calls src/

Use: Understanding architecture, finding entry points

"How complex is X?"

tldr cfg <file> <function>

Use: Identifying refactoring candidates, understanding difficulty

"Where does variable Y come from?"

tldr dfg <file> <function>

Use: Debugging, understanding data flow

"What affects line Z?"

tldr slice <file> <function> <line>

Use: Impact analysis, safe refactoring

"Search for pattern P"

tldr search "pattern" src/

Use: Finding code, structural search

Decision Tree

SKILL.md on GitHub

Details

Repository: github.com/parcadei/continuous-claude-v3
First seen: Jun 3, 2026