← ClaudeAtlas

clarifylisted

Clarification protocol — grill an ambiguous request into a Requirements Ledger before any delegation. The chair MUST load this whenever a request arrives carrying ambiguity that would change the work; Rule 0.5 in the core profile only summarizes it.
Rylaa/fable5-opus5-orchestrator · ★ 86 · AI & Automation · score 83
Install: claude install-skill Rylaa/fable5-opus5-orchestrator
# Clarify Before You Delegate A worker cannot ask the user anything. Every ambiguity you carry into a spawn prompt becomes a guess the worker commits to code, and you pay for it twice — once building the wrong thing, once rebuilding it. The cheapest question is the one asked before the first spawn. Chair only. A subagent that hits an ambiguity does NOT run this skill: it reports the ambiguity to the chair with SendMessage and waits. ## The gate Nothing is delegated, planned, or edited until every ambiguity that would change the work is either resolved by an answer or written down as an explicit assumption the user can veto. `## Clarified` in the ledger is the record, and the spawn guard denies without it. ## Scan — seven axes Each axis that is unresolved AND would change the work is a question: 1. **Scope edge** — what is deliberately OUT? The unnamed neighbour is where scope creep lives. 2. **Acceptance** — how is "done" observed? Name the test, the command, the screen. 3. **Constraints** — backward compatibility, dependencies, budget, what must not move. 4. **Ownership of choices** — which decisions are the user's taste and which are yours? Guessing on taste is expensive. 5. **Priority conflict** — when speed, correctness, and token cost disagree, which wins here? 6. **Contact with what exists** — which current file, pattern, or contract does this touch? Read first; never ask what the repo answers. 7. **Failure behaviour** — what happens on error