clarifylisted

# Clarify Turn a clean spec into an implementation-ready document with atomic tasks, verifiable acceptance criteria, contracts, edge cases, and risks. > **Letter = spirit.** If a rule blocks you from reaching the goal it was > written for, the rule is wrong, not the goal. Don't look for a wording > loophole — ask what the rule is protecting, and protect that. ## Usage ``` /clarify <spec.md> [--consensus-rounds N] ``` `--consensus-rounds` defaults to 3. Set it to 0 to skip the cross-model consensus loop (Phase 7.6) — only internal validation runs. ## Weaknesses and when NOT to use - **Slow and thorough — overkill for hour-long tasks.** Decomposition + AC + edge cases + 3 consensus rounds (if codex is available) take 10-15 minutes. For smaller tasks, write the AC by hand. - **Does not work on raw chat exports or unstructured notes.** The input spec must already be sectioned with `## ` (after `/cleanup`). Otherwise — abort. - **Not suited for product-style PRDs.** This skill forces test-first AC with proof commands; for product-management PRDs use `mattpocock:to-prd` (freeform success metrics). - **Phase 7.6 consensus loop requires the `codex` CLI on `$PATH`** (npm `@openai/codex`). The skill detects it via `command -v codex` and invokes `codex review --uncommitted "<prompt>"` directly. It does NOT depend on `codex-plugin-cc` (the Claude Code plugin); we used to and got bitten by the `Skill` tool refusing to call slash commands with `disable-model-invocation: true`. The d