@pavp/storywright 1.6.2 → 1.6.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/package.json +1 -1
  2. package/skills/_components/clarification-questions/SKILL.md +1 -1
  3. package/skills/_components/jira-wiki-formatter/SKILL.md +1 -1
  4. package/skills/_components/storywright-base/SKILL.md +3 -1
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@pavp/storywright",
3
- "version": "1.6.2",
3
+ "version": "1.6.3",
4
4
  "description": "PM Skills pack for Claude Code — turn ambiguous inputs (prompts, screenshots, Figma links) into Jira-ready user stories.",
5
5
  "keywords": [
6
6
  "claude",
package/skills/_components/clarification-questions/SKILL.md CHANGED
@@ -43,7 +43,7 @@ Invoked by `story-generate`, `story-refine`, `story-split`, and `story-from-figm
43
43
  4. For `BLOCKING`, draft questions. Limit to **3 questions max per round**. Prefer multiple-choice or yes/no.
44
44
  5. Order by impact: scope > behavior > data > UX detail.
45
45
  6. Emit as a Markdown block titled `### Clarifying Questions` with numbered list.
46
- 7. If no questions remain, emit nothing.
46
+ 7. If no questions remain, emit nothing — no summary, no "Clarification resolved", no offer to save. Proceed directly to the next step.
47
47
 
48
48
  ## Examples
49
49
 
package/skills/_components/jira-wiki-formatter/SKILL.md CHANGED
@@ -63,7 +63,7 @@ Final step in `story-generate` and `story-refine`. Always last.
63
63
  15. Edge Cases
64
64
 
65
65
  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.
66
- 5. Emit both as fenced code blocks in the chat (so user can copy), and offer to save to disk when running from CLI.
66
+ 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.
67
67
 
68
68
  ## Examples
69
69
 
package/skills/_components/storywright-base/SKILL.md CHANGED
@@ -24,7 +24,7 @@ If you are reading this through a top-level skill, treat every rule below as non
24
24
 
25
25
  ## Hard rules (v2.2 — apply to all top-level storywright skills)
26
26
 
27
- 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.
27
+ 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.
28
28
 
29
29
  2. **Cohn + Gherkin canonical.** Every story (or child story) has:
30
30
  - ONE Use Case block (`As a / I want to / so that`).
@@ -246,6 +246,8 @@ Everything else is identical and lives in this base.
246
246
  ## Common Pitfalls (all skills)
247
247
 
248
248
  - Writing any sidecar question file (clarifications.md, questions.md, etc).
249
+ - Announcing "Clarification resolved" or "no clarifications.md needed" instead of proceeding silently.
250
+ - Offering to save a clarifications file to disk after resolving gaps.
249
251
  - Skipping rule 1 (terminal-only) "because the user is async".
250
252
  - Eyeballing outcome counts instead of running the mechanical table.
251
253
  - Renumbering ACs the team may already reference externally.