feat(fiction-assistance): register plugin with full bespoke command set

Snapshot of the fiction-assistance plugin in its original Universalis-
specific form before generalization. Adds the missing plugin.json
manifest (subdirectory command paths explicitly listed), moves the two
stray root-level review files into their proper homes (review-all.md
into the reviewing-fiction skill, review-final.md as a command with
frontmatter), and registers the plugin in the marketplace.

Preserved here so the original card-generation and vault-maintenance
commands remain recoverable when the plugin is reduced to a portable
guidance-and-analysis subset in the next commit.

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

fiction-assistance/commands/review/score-scenes.md

@@ -0,0 +1,39 @@
+Analyze and score all scenes in the manuscript on several quality dimensions (0.5-10 scale), updating the ratings.csv file.
+
+## Task Instructions
+
+1. **Compile chapters**: Run `python scripts/compile_manuscript.py --chapters-only` to ensure current content
+
+2. **For each compiled chapter** from `Compiled/Chapters/` directory, read it and perform the following steps.
+
+3. **Extract scenes**: Identify individual scenes (marked by `## Scene Name` headers) from each chapter
+
+4. **Score each scene** on these specific qualities (0.0-10.0 scale):
+   - **Plot Advancement**: How significantly the scene moves story forward
+   - **Pacing**: Flow, rhythm, tension building/release
+   - **Opening Hook**: How effectively the scene draws readers in immediately  
+   - **Closing Hook**: How well it creates anticipation or transitions
+   - **Narrative**: Prose quality, imagery, emotional resonance
+   - **Dialogue**: Character voice consistency, naturalness, purpose
+   - **Emotion**: How effectively the scene triggers emotions
+
+5. **Scoring criteria**:
+   - Use your literary analysis expertise
+   - Consider scene function within chapter/story context
+   - Rate relative to professional fiction standards
+   - 0.0-3.0: Major issues, needs substantial work
+   - 4.0-6.0: Functional but needs improvement
+   - 7.0-8.5: Good quality, minor polish needed
+   - 9.0-10.0: Exceptional, publication-ready
+
+6. **Update ratings.csv**: Create/update with new scores in format:
+   ```
+   Scene,Plot Advancement,Pacing,Opening Hook,Closing Hook,Narrative,Dialogue,Emotion
+   Chapter X: Scene Name,8.5,7.0,9.0,8.0,8.5,7.5,8.0
+   ```
+
+7. **Provide summary**: Total scenes analyzed, highest/lowest rated scenes, key patterns observed
+
+Focus on objective story craft assessment. Skip any placeholder scenes (marked "Scene content goes here" or similar).
+
+The user is seeking to publish this manuscript and requires an accurate assessment.