Stats
Actions
Tags
How this skill is triggered — by the user, by Claude, or both
Slash command
/core:alignmentThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill is the alignment gate. Its only job is to make the user's intent 100% explicit before any work begins, by asking the maximum set of genuinely useful clarifying questions through `AskUserQuestion`, then returning control. It writes nothing and never starts the task itself.
This skill is the alignment gate. Its only job is to make the user's intent 100% explicit before any work begins, by asking the maximum set of genuinely useful clarifying questions through AskUserQuestion, then returning control. It writes nothing and never starts the task itself.
Think Before Coding guideline from core:base applied as a gate.AskUserQuestion. Batch related questions into one AskUserQuestion call where the tool allows multiple questions; never silently pick when interpretations diverge. Each question carries canonical question text, 2-4 concrete options each with an implication string, and a recommended default pre-selected. Prefer concrete options over open-ended prompts.Maximum means maximally complete coverage of real ambiguity, not padding. Drop any question whose answer is already determined by the request or context.Aligned intent recap: the confirmed one-sentence goal plus a compact bullet list of each resolved decision (e.g. scope: X, output: Y, constraint: Z).AskUserQuestion is the only tool; never read or modify files.core:base SIMPLE principles and the destructive-operation safety rules by reference, not by restating them.npx claudepluginhub shoto290/shoto --plugin coreCreates bite-sized, testable implementation plans from specs or requirements, with file structure and task decomposition. Activates before coding multi-step tasks.