From bl1nk-visual-mcp
Deep structural analysis of story graphs for Visual Story Planner projects. Use this skill whenever the user says "audit", "check structure", "analyze story structure", "is my story balanced", "review my plot", "structural report", or asks for feedback on three-act balance, pacing health, character arc completeness, or conflict escalation. Also activate when the user runs `validate_story_structure` and wants an explanation of results, or when story export output is present and they want a critique. IMPORTANT: Any export action (export_mermaid, export_canvas, export_dashboard, etc.) must be preceded by `validate_story_structure`. If validation reports any issues, surface them with severity levels (error / warning) and require explicit user acknowledgment before continuing to export. Block exports when blocking (error-level) issues exist unless the user explicitly confirms they accept the risk. This skill provides a four-phase audit (Structure → Characters → Conflicts → Pacing) with a scored health report and prioritized action list — always activate it, even for seemingly simple structure questions.
npx claudepluginhub billlzzz26/visual-story-extensionThis skill uses the workspace's default tool permissions.
**Before any export tool is called**, this skill must:
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Analyzes BMad project state from catalog CSV, configs, artifacts, and query to recommend next skills or answer questions. Useful for help requests, 'what next', or starting BMad.
Before any export tool is called, this skill must:
validate_story_structure on the current grapherror (blocking): exports are refused until resolved or user explicitly accepts riskwarning (non-blocking): exports proceed only after user acknowledges each warning⚠️ Validation required before export
Errors (blocking): [N] Warnings: [N]
[error] MISSING_CLIMAX — Story structure is incomplete: Missing a Climax
[warning] NO_MIDPOINT — Story should have a midpoint event
Resolve blocking errors before exporting, or type ACCEPT RISK to override.
If the user types ACCEPT RISK, proceed with the export and prepend a notice to the output that the exported content has unresolved validation errors.
Check each act against the 25%-50%-25% target:
| Act | Target % | Warning Threshold | Events Desired |
|---|---|---|---|
| Act 1 | 25% | < 15% or > 35% | 3–5 |
| Act 2 | 50% | < 40% or > 65% | 5–8 |
| Act 3 | 25% | < 15% or > 35% | 3–5 |
Check for presence and quality of:
inciting)midpoint)climax) ← error if missingresolution)Status: good | needs_work | critical
For each character with role protagonist or antagonist:
arc.start, arc.midpoint, arc.end non-empty)arc.transformation non-empty)motivations array non-empty)actAppearances covers acts they should be in)Flag any character missing 2+ of these as needs_work.
For each conflict:
escalations.length >= 2)resolution non-empty)slow (< 5 events) | balanced (5–15) | fast (> 15)Always output in this exact structure:
## Story Audit: [Title]
**Overall Health: [score]/100**
### ✅ Act Structure — [status]
[findings + act counts + %]
### ✅ Characters — [status]
[per-character findings]
### ✅ Conflicts — [status]
[per-conflict findings]
### ✅ Pacing — [status]
[pacing verdict + climax position]
---
### 🎯 Priority Actions (fix in this order)
1. [Critical] ...
2. [Warning] ...
3. [Suggestion] ...
Health score formula: