Imported from jeremylongshore/tons-of-skills-marketplace (skills/.curated/anima-cost-tuning/SKILL.md). Install upstream with npx skills add jeremylongshore/tons-of-skills-marketplace --skill anima-cost-tuning. Copyright stays with the author (MIT).

Anima Cost Tuning

Overview

Optimize design-to-code generation by measuring approved usage, avoiding duplicate work, and retaining only reusable outputs. Treat cost projections as planning inputs until the account owner confirms current contractual terms.

Pricing Context

Anima uses partner-based pricing (not self-service). API access is currently granted to partners with custom agreements. Costs are typically per-generation or per-seat.

Prerequisites

• A current agreement or account report from the authorized Anima owner; do not infer consumption limits from the illustrative optimization table.
• Aggregate generation telemetry that records file/node identifiers, generation version, cache state, and duration without exposing design tokens or content.
• An explicit cache freshness and invalidation policy agreed by design and code owners so cached output cannot silently lag an approved design change.

Cost Optimization Strategies

Instructions

Step 1: Usage Tracker

// src/cost/usage-tracker.ts
interface GenerationRecord {
  timestamp: string;
  fileKey: string;
  nodeId: string;
  cached: boolean;
  durationMs: number;
}

class AnimaUsageTracker {
  private records: GenerationRecord[] = [];

  record(entry: GenerationRecord): void { this.records.push(entry); }

  getReport(): { total: number; cached: number; savings: string } {
    const total = this.records.length;
    const cached = this.records.filter(r => r.cached).length;
    return {
      total,
      cached,
      savings: total > 0 ? `${((cached / total) * 100).toFixed(0)}% saved by caching` : 'No data',
    };
  }
}

Step 2: Smart Generation Policy

// Only generate when:
// 1. Figma file version changed (check via Figma API)
// 2. Cache is expired (>1 hour for active dev, >24h for CI)
// 3. Settings changed (new framework/styling)
// 4. Force flag passed (manual override)

async function shouldGenerate(
  fileKey: string,
  nodeId: string,
  cache: any,
): Promise<boolean> {
  // Check cache first
  const cached = cache.get(fileKey, nodeId);
  if (cached && Date.now() - new Date(cached.generatedAt).getTime() < 3600000) {
    console.log('Using cached generation (< 1 hour old)');
    return false;
  }
  return true;
}

Output

• Usage tracking with cache hit rate reporting
• Smart generation policy reducing unnecessary API calls
• Cost savings through caching and incremental updates

Examples

For a weekly design-system sync, record aggregate generation counts for the approved component registry, then compare an uncached baseline with the smart generation policy. Regenerate only components whose Figma version or generation settings changed, and attach the source-version and cache decision to the PR. If the current usage report is incomplete, a cache cannot identify its source version, or a design owner requests an immediate change, bypass the cache only with an explicit force record and regenerate the affected component—not the entire design file by default.

Error Handling

Resources

• Anima Pricing
• Anima API

Next Steps

For architecture design, see anima-reference-architecture.