@pavp/storywright 1.3.0 → 1.4.0

package/commands/story-refine.md

@@ -1,6 +1,6 @@
 ---
-description: Audit an existing user story and fill gaps in place
-argument-hint: <paste existing story>
+description: Audit an existing user story and fill gaps in place (supports text + optional image / Figma companion)
+argument-hint: <paste existing story> [+ attach image or paste Figma URL for cross-source check]
 ---
 
 Invoke the `story-refine` skill from the storywright pack to audit and improve this story:
@@ -9,6 +9,7 @@ $ARGUMENTS
 
 Follow the skill's procedure:
 
+0. Detect companion sources (image, figma-link). If present, run conflict detection between the story text and the design BEFORE filling sections. Surface conflicts as BLOCKING clarifications; never silently rewrite the story to match the design.
 1. Parse the existing story into the section taxonomy. Mark each section: present / missing / weak.
 2. Gap-check weak sections via `clarification-questions`. Ask only BLOCKING questions.
 3. Detect language and preserve it in output.

package/commands/story-split.md

@@ -1,6 +1,6 @@
 ---
 description: Split an oversize story into an epic + child stories using INVEST + Humanizing Work patterns
-argument-hint: <paste oversize story>
+argument-hint: <paste oversize story> [+ optional image / Figma URL for flow inventory]
 ---
 
 Invoke the `story-split` skill from the storywright pack to split this story:
@@ -9,6 +9,7 @@ $ARGUMENTS
 
 Follow the skill's procedure:
 
+0. Detect companion sources (image, figma-link). If present, use them to inventory candidate sub-flows (prototype links, frame structure). If Figma shows N flows but text mentions K (K < N), surface as BLOCKING clarification before drafting the split plan. Text is canonical for scope of the epic; design is canonical for flow structure.
 1. Run `invest-checklist` and apply the pre-split gates:
    - If Valuable FAILS → NOT A STORY. Don't split. Stop.
    - If Testable / Negotiable FAILS → fix in place, don't split. Stop.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pavp/storywright",
-  "version": "1.3.0",
+  "version": "1.4.0",
   "description": "PM Skills pack for Claude Code — turn ambiguous inputs (prompts, screenshots, Figma links) into Jira-ready user stories.",
   "keywords": [
     "claude",

package/skills/story-refine/SKILL.md

@@ -6,6 +6,8 @@ intent: Refinement skill for stories that already exist but are incomplete or we
 version: 1.0.0
 inputs:
   - text
+  - image
+  - figma-link
 outputs:
   - story.jira-wiki.md
   - story.standard.md
@@ -37,9 +39,19 @@ For oversized stories that fail `Independent / Estimable / Small`, hand off to `
 ## Inputs & interpretation
 
 - **text** — existing story. Detect which sections are present, which are missing, which are weak.
+- **image (optional)** — companion screenshot/mockup the story references. Use to validate UI claims and surface missing edge cases / states.
+- **figma-link (optional)** — companion design. Use to enrich Technical Considerations, Edge Cases (states shown but not in story), and to detect scope mismatches.
+
+### Mixed inputs
+
+When the user pastes a story plus an image / Figma link, apply the source-priority matrix from `[[story-generate]]` "Mixed inputs" section:
+- Story text remains canonical for `User Story / Scope / Business Goal`.
+- Image/Figma is canonical for `Components / States / Edge Cases / UX flow`.
+- Surface conflicts as BLOCKING clarifications (e.g., story says "single provider" but Figma shows multiple). Never silently rewrite the story to match the design without asking.
 
 ## Application (step-by-step)
 
+0. **Detect companion sources** (image, figma-link). If present, run conflict detection against the story text BEFORE filling sections. Add detected conflicts to the gap-check output.
 1. **Parse the existing story.** Map content into the 15-section taxonomy. Note: present / missing / weak.
 2. **Gap-check the weak sections** via `[[clarification-questions]]`. If gaps are inferrable, mark `⚠️ Assumed` and proceed. Only ask BLOCKING questions.
 3. **Detect language** of the existing story; preserve it in the output.

package/skills/story-split/SKILL.md

@@ -6,6 +6,8 @@ intent: Splitting skill that uses the INVEST failure reasons (from invest-checkl
 version: 1.0.0
 inputs:
   - text
+  - image
+  - figma-link
 outputs:
   - split-plan.md
   - epic.md
@@ -28,6 +30,16 @@ When a story is an epic in disguise, splitting badly is worse than not splitting
 ## Inputs & interpretation
 
 - **text** — the oversize story (or a one-line goal that's clearly epic-scoped).
+- **image (optional)** — companion mockup. Use to validate scope and reveal hidden sub-flows the text doesn't mention.
+- **figma-link (optional)** — companion design. Often makes splitting easier: prototype links and frame structure reveal natural flow boundaries that map to children.
+
+### Mixed inputs
+
+When the user provides text + image / Figma alongside the story:
+- **Text is canonical for User Story / Scope / Business Goal** of the epic.
+- **Figma / image is canonical for flow structure** — use prototype links to enumerate candidate sub-flows. Each flow is a candidate child story.
+- **Conflict handling:** if Figma shows N flows but text only mentions K (K < N), surface this in the gap-check via `[[clarification-questions]]` BEFORE drafting the split plan. Ask: "Figma includes flows for X, Y, Z — include in this epic, or scope out?" Never silently expand or shrink scope.
+- See `[[story-generate]]` "Mixed inputs" for the full source-priority matrix.
 
 ## Application (step-by-step)