refactor(fiction-assistance)!: reduce to portable guidance and analysis (v2.0.0)

Strip the Universalis-specific vault layout and card-management
machinery. The plugin is now a general-purpose fiction toolkit:
nine commands that take a manuscript path/glob/selection via
\$ARGUMENTS and write their output to the conversation.

Surviving commands, flattened into commands/:
- analyze-story: structural and statistical analysis
- bechdel-test: representation tests (Bechdel + related)
- check-continuity: plot/character/world continuity
- check-voice: per-character voice consistency
- developmental-review: structural feedback on a scene/chapter
- extract-research: world-building and research inventory
- final-review: synthesis of prior-phase reviews
- generate-timeline: chronology with consistency checks
- strategic-review: craft-based critique with priority ranking

Removed (vault and card management): 10 update-*-cards commands,
cleanup-generated, update-changed, update-links,
update-chapter-summaries, validate-story, validate-pdf, score-scenes.
The original bespoke command set is preserved in 65c29d7 for recovery.

Agent (line-editor) and skill (reviewing-fiction) were already
portable and are unchanged. plugin.json no longer needs the
commands subdirectory paths since the layout is flat. Marketplace
description updated to reflect the general-purpose scope.

BREAKING CHANGE: All update-*-cards, cleanup-generated, update-changed,
update-links, update-chapter-summaries, validate-story, validate-pdf,
and score-scenes commands are removed. perform-bechdel-tests is renamed
to bechdel-test. review-final is renamed to final-review.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

fiction-assistance/commands/final-review.md

@@ -0,0 +1,39 @@
+---
+description: Synthesize prior phase reviews into a final manuscript assessment
+argument-hint: "[path to manuscript and/or prior review notes]"
+allowed-tools: [Read, Glob, Grep]
+---
+
+Using whatever prior-phase review notes the user provides (or that exist in the working directory under names like `review-*.md`, `notes/review/`, etc.), produce a final, integrated assessment of the manuscript at `$ARGUMENTS`.
+
+## Story architecture
+
+1. **Inciting incident** — clear, compelling, well-placed?
+2. **Plot points** — major turning points obvious and impactful?
+3. **Climax** — does it feel earned and satisfying?
+4. **Resolution** — does it resolve the key conflicts appropriately?
+
+## Integration analysis
+
+5. **Scene flow** — do scenes connect logically and maintain momentum?
+6. **Pacing rhythm** — variation between fast and slow?
+7. **Character arc completion** — do characters grow consistently?
+8. **Setting consistency** — locations and time periods coherent?
+9. **Theme reinforcement** — do plot, character, and setting support the central themes?
+
+## Structural recommendations
+
+- Scenes to add, remove, or combine
+- Pacing adjustments
+- Character development gaps
+- Setting opportunities
+- Overall readability improvements
+
+## Final assessment
+
+- The manuscript's greatest strengths
+- Top 3–5 areas needing improvement
+- Concrete action steps for revision
+- Overall readiness assessment for the writer's intended market
+
+Present the synthesis directly in the conversation. Quote specifically from prior reviews and from the manuscript to support each point — name the chapter/scene and the issue. The goal is a revision roadmap the writer can act on.