@pavp/storywright 1.6.2 → 1.7.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pavp/storywright",
-  "version": "1.6.2",
+  "version": "1.7.0",
   "description": "PM Skills pack for Claude Code — turn ambiguous inputs (prompts, screenshots, Figma links) into Jira-ready user stories.",
   "keywords": [
     "claude",

package/skills/_components/clarification-questions/SKILL.md

@@ -43,7 +43,7 @@ Invoked by `story-generate`, `story-refine`, `story-split`, and `story-from-figm
 4. For `BLOCKING`, draft questions. Limit to **3 questions max per round**. Prefer multiple-choice or yes/no.
 5. Order by impact: scope > behavior > data > UX detail.
 6. Emit as a Markdown block titled `### Clarifying Questions` with numbered list.
-7. If no questions remain, emit nothing.
+7. If no questions remain, emit nothing — no summary, no "Clarification resolved", no offer to save. Proceed directly to the next step.
 
 ## Examples
 

package/skills/_components/jira-wiki-formatter/SKILL.md

@@ -63,7 +63,7 @@ Final step in `story-generate` and `story-refine`. Always last.
    15. Edge Cases
 
 4. **Drop any section with no real content.** An empty heading is noise. A story with only the 5 core sections is a valid output.
-5. Emit both as fenced code blocks in the chat (so user can copy), and offer to save to disk when running from CLI.
+5. Always write `story.standard.md` and `story.jira-wiki.md` to disk. Also emit both as fenced code blocks in the chat so the user can copy them. Never ask whether to save — always save.
 
 ## Examples
 

package/skills/_components/storywright-base/SKILL.md

@@ -24,7 +24,7 @@ If you are reading this through a top-level skill, treat every rule below as non
 
 ## Hard rules (v2.2 — apply to all top-level storywright skills)
 
-1. **Terminal-only clarifications.** Never write any sidecar question file (no `clarifications.md`, no `questions.md`, nothing). All gap questions go through `AskUserQuestion`, batched ≤4 per call. Non-blocking gaps → mark `⚠️ Assumed: <text>` inline in the story body — do not ask.
+1. **Terminal-only clarifications.** Never write any sidecar question file (no `clarifications.md`, no `questions.md`, nothing). All gap questions go through `AskUserQuestion`, batched ≤4 per call. Non-blocking gaps → mark `⚠️ Assumed: <text>` inline in the story body — do not ask. Do NOT announce the absence of a clarifications file ("Clarification resolved", "no clarifications.md needed", or any equivalent). Silence = no questions. Proceed directly.
 
 2. **Cohn + Gherkin canonical.** Every story (or child story) has:
    - ONE Use Case block (`As a / I want to / so that`).
@@ -246,6 +246,8 @@ Everything else is identical and lives in this base.
 ## Common Pitfalls (all skills)
 
 - Writing any sidecar question file (clarifications.md, questions.md, etc).
+- Announcing "Clarification resolved" or "no clarifications.md needed" instead of proceeding silently.
+- Offering to save a clarifications file to disk after resolving gaps.
 - Skipping rule 1 (terminal-only) "because the user is async".
 - Eyeballing outcome counts instead of running the mechanical table.
 - Renumbering ACs the team may already reference externally.

package/skills/story-generate/SKILL.md

@@ -47,8 +47,11 @@ Conflicts → BLOCKING `AskUserQuestion` per base rule 1.
 If the base **deterministic pre-split test** returns count ≥2:
 - **STOP drafting.**
 - Output a terminal message listing candidate children + per-pair dep notes (base rule 10) + V audit (base rule 11).
-- Recommend `/story-split` to the user.
-- Do NOT auto-split, do NOT produce a 15-section story.
+- Show candidate children + dep notes + V audit.
+- Ask via `AskUserQuestion`: "This story has [N] independent flows. Run split now?" with options "Yes, split" / "No, keep as-is".
+- If user approves → execute `[[story-split]]` inline (epic + children + .storywright-context.json).
+- If user declines → stop. No output written.
+- Do NOT silently auto-split without the AskUserQuestion confirmation.
 
 If count ≤1:
 - Proceed with the base step-by-step Application skeleton (read context → language → persona → passive-goal → gap-check → siblings → fill canonical block → INVEST → render).

package/skills/story-refine/SKILL.md

@@ -39,9 +39,11 @@ Bring an existing user story up to standard *without* turning it into a feature
 
 If the base **deterministic pre-split test** returns count ≥2:
 - **STOP refining.**
-- Output a terminal message listing candidate children + per-pair dep notes (base rule 10) + V audit (base rule 11).
-- Recommend `/story-split` to the user.
-- Do NOT produce an oversized refined story.
+- Show candidate children + per-pair dep notes (base rule 10) + V audit (base rule 11).
+- Ask via `AskUserQuestion`: "This story has [N] independent flows. Run split now?" with options "Yes, split" / "No, keep as-is".
+- If user approves → execute `[[story-split]]` inline (epic + children + .storywright-context.json).
+- If user declines → stop. No output written.
+- Do NOT silently auto-split without the AskUserQuestion confirmation.
 
 If count ≤1:
 - Proceed with the base step-by-step Application skeleton, applying the source-specific preservation rules above.