Soc Lite — Development skill for Claude Code
Lite mode. Clarify a vague request with exactly 0 or 1 high-leverage question, then return a tighter prompt.
How to install Soc Lite
Installs to ~/.claude/commands/ycedrick-socratic-soc-lite.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/ycedrick/socratic/HEAD/.claude/commands/soc-lite.md -o ~/.claude/commands/ycedrick-socratic-soc-lite.md Restart Claude Code, or start a new session, for it to be picked up.
What Soc Lite does
description: Lite mode. Clarify a vague request with exactly 0 or 1 high-leverage question, then return a tighter prompt. argument-hint: [mostly-complete request]
You are Socratic operating as a Claude Code slash command in lite mode.
Your job is to turn the user's incomplete request into a clear, executable prompt with minimal back-and-forth.
Use this shared core behavior as the source of truth:
@skills/socratic-core/SKILL.md
The user's request is:
$ARGUMENTS
Rules:
- This is `l
Alternatives in Development
- Pohuy — Переключить уровень мата (lite/full/ultra) 1.1k ★
- ExportProfile — Generate a complete personal profile summary of everything you know about me from our conversations 250 ★
- Ponytail Lite — Stop agents from over-engineering 154 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Soc
Default mode. Clarify a vague request by asking 0 to 3 high-leverage questions, then return a tighter prompt.
Socratic
Alias for /soc. Default mode with 0 to 3 high-leverage questions.
P
Prompt optimizer · clarify only if needed, rewrite your request into a sharper prompt, then carry it out. Pref
Yotta Prompt
元引 yotta-prompt — intent clarification & ecosystem entry Agent Skill: turns vague prompts into runnable tasks
Soc2 Evidence Plan
You are a SOC 2 Type II evidence collection planning assistant. Your job is to take an auditor's information r
Generation System
You generate small, safe repository changes. Return strict JSON with exactly two keys: summary and changes.
Related Agents
Decision Agent
You are a Tier 2 decision agent for Correctless Auto Mode. You receive a structured decision request and retur
Issue Subagents QA
QA agent for issue-subagents skill. Two distinct one-shot modes selected by spawn prompt — test-author mode wr
Persona Reviewer
Read-only dispatch target for team personas in review, analysis, or assessment mode. Structurally lacks Edit/W