adobe-cost-tuning
Optimize Adobe API costs across Firefly Services (generative credits), PDF Services (document transactions), and Photoshop/Lightroom APIs. Use when analyzing Adobe billing, reducing API costs, or implementing usage monitoring and budget alerts. Trigger with phrases like "adobe cost", "adobe billing", "adobe credits", "reduce adobe costs", "adobe pricing", "adobe budget".
What this skill does
# Adobe Cost Tuning
## Overview
Optimize costs across Adobe's consumption-based APIs. Each API family has different pricing models: Firefly uses generative credits, PDF Services uses document transactions, and Photoshop/Lightroom use API call credits.
## Prerequisites
- Access to Adobe Admin Console billing (https://adminconsole.adobe.com)
- Understanding of current API usage patterns
- Monitoring infrastructure for usage tracking
## Instructions
### Step 1: Understand Adobe API Pricing Models
| API | Free Tier | Paid Unit | Key Limit |
|-----|-----------|-----------|-----------|
| **PDF Services** | 500 tx/month | Document Transaction | Per-page for extract, per-file for create |
| **Firefly API** | Trial credits | Generative Credit | 1 credit per image generated |
| **Photoshop API** | Trial credits | API Credit | 1 credit per operation (cutout, actions, etc.) |
| **Lightroom API** | Trial credits | API Credit | 1 credit per auto-edit |
| **I/O Events** | Included | Free with entitlement | 3,000 events/5sec rate limit |
| **Document Generation** | Part of PDF Services | Document Transaction | Per-document generated |
### Step 2: Track Usage per API
```typescript
// src/adobe/usage-tracker.ts
interface ApiUsageEntry {
api: 'firefly' | 'pdf-services' | 'photoshop' | 'lightroom';
operation: string;
timestamp: Date;
durationMs: number;
creditsUsed: number;
}
class AdobeUsageTracker {
private entries: ApiUsageEntry[] = [];
record(entry: Omit<ApiUsageEntry, 'timestamp'>): void {
this.entries.push({ ...entry, timestamp: new Date() });
}
getMonthlySummary(): Record<string, { calls: number; credits: number }> {
const now = new Date();
const monthStart = new Date(now.getFullYear(), now.getMonth(), 1);
const monthly = this.entries.filter(e => e.timestamp >= monthStart);
return monthly.reduce((acc, entry) => {
const key = entry.api;
if (!acc[key]) acc[key] = { calls: 0, credits: 0 };
acc[key].calls++;
acc[key].credits += entry.creditsUsed;
return acc;
}, {} as Record<string, { calls: number; credits: number }>);
}
checkBudget(api: string, monthlyLimit: number): { remaining: number; warning: boolean } {
const summary = this.getMonthlySummary();
const used = summary[api]?.credits || 0;
const remaining = monthlyLimit - used;
return { remaining, warning: remaining < monthlyLimit * 0.2 };
}
}
```
### Step 3: Cost Reduction Strategies
**Strategy 1: Cache Firefly outputs by prompt hash**
```typescript
import crypto from 'crypto';
function promptHash(prompt: string, size: { width: number; height: number }): string {
return crypto.createHash('sha256')
.update(`${prompt}:${size.width}x${size.height}`)
.digest('hex')
.slice(0, 16);
}
// Before generating, check if identical prompt was already run
const hash = promptHash(prompt, { width: 1024, height: 1024 });
const cached = await cache.get(`firefly:${hash}`);
if (cached) return cached; // Saves 1 generative credit
```
**Strategy 2: Minimize PDF Services transactions**
```typescript
// EXPENSIVE: Extract + Create + Merge = 3 transactions
await extractPdf(input);
await createPdf(html);
await mergePdfs([pdf1, pdf2]);
// CHEAPER: Combine operations where possible
// Use Document Generation API (1 transaction) instead of
// creating PDF then merging
await generateDocument(template, data); // 1 transaction
```
**Strategy 3: Right-size Firefly image dimensions**
```typescript
// Same credit cost but different use cases:
// - Thumbnails: 512x512 (same 1 credit, faster generation)
// - Social media: 1024x1024
// - Print: 2048x2048 (same 1 credit, slower generation)
// Generate at the size you actually need — don't upscale unnecessarily
```
**Strategy 4: Use Photoshop batch actions**
```typescript
// EXPENSIVE: 5 separate API calls = 5 credits
await removeBackground(image1);
await removeBackground(image2);
// ...
// CHEAPER: Photoshop Actions can chain operations
// Record an action that does: remove bg + resize + add watermark
// Run it once per image = 1 credit for all 3 operations
await runPhotoshopAction(image, actionFile);
```
### Step 4: Budget Alert System
```typescript
// Check PDF Services free tier monthly limit
const pdfTracker = new AdobeUsageTracker();
// Wrap PDF Services calls with tracking
async function trackedPdfExtract(pdfPath: string) {
const budget = pdfTracker.checkBudget('pdf-services', 500); // Free tier
if (budget.remaining <= 0) {
throw new Error('PDF Services monthly quota exhausted. Upgrade or wait for reset.');
}
if (budget.warning) {
console.warn(`PDF Services: only ${budget.remaining} transactions remaining this month`);
// Send alert to Slack/email
}
const result = await extractPdfContent(pdfPath);
pdfTracker.record({
api: 'pdf-services',
operation: 'extract',
durationMs: 0,
creditsUsed: 1,
});
return result;
}
```
### Step 5: Cost Dashboard Query
```sql
-- If tracking usage in your database
SELECT
api,
operation,
DATE_TRUNC('day', timestamp) as date,
COUNT(*) as calls,
SUM(credits_used) as credits,
AVG(duration_ms) as avg_latency_ms
FROM adobe_api_usage
WHERE timestamp >= DATE_TRUNC('month', CURRENT_DATE)
GROUP BY 1, 2, 3
ORDER BY credits DESC;
```
## Output
- Per-API usage tracking with credit consumption
- Budget alerts at 80% threshold
- Caching to prevent duplicate Firefly credit charges
- Operation batching for Photoshop workflows
- Monthly cost dashboard query
## Error Handling
| Issue | Cause | Solution |
|-------|-------|----------|
| Unexpected charges | Untracked batch jobs | Wrap all calls with usage tracker |
| Free tier exceeded | No budget alerts | Implement 80% warning threshold |
| High Firefly costs | Duplicate prompts | Cache by prompt hash |
| PDF overage | Unnecessary re-extractions | Cache extraction results |
## Resources
- [Adobe PDF Services Pricing](https://developer.adobe.com/document-services/pricing/main/)
- [Firefly Services Documentation](https://developer.adobe.com/firefly-services/docs/guides/)
- [Adobe Admin Console](https://adminconsole.adobe.com)
## Next Steps
For architecture patterns, see `adobe-reference-architecture`.
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.