ideogram-multi-env-setup
Configure and isolate Ideogram API settings and keys across different software development environments.
Install
mkdir -p .claude/skills/ideogram-multi-env-setup && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5433" && unzip -o skill.zip -d .claude/skills/ideogram-multi-env-setup && rm skill.zipInstalls to .claude/skills/ideogram-multi-env-setup
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Configure Ideogram across development, staging, and production environments.Key capabilities
- →Isolate API keys per environment
- →Configure environment-specific model and speed settings
- →Implement secure secret management
How it works
The workflow detects the current environment and retrieves the corresponding API key and configuration settings, ensuring isolation between development, staging, and production.
Inputs & outputs
When to use ideogram-multi-env-setup
- →Isolating dev and prod API keys
- →Configuring environment-specific caches
- →Setting up CI/CD secret management
- →Defining per-environment timeouts
- →Managing model/speed settings
About this skill
Ideogram Environment Isolation
Overview
Prevent development and staging activity from consuming production authority or contaminating production media. Separate keys, application identities, budgets, routes, queues, state, storage, telemetry, and cleanup while recognizing that keys in the same Ideogram team share credits.
Prerequisites
- Environment inventory, Ideogram team model, billing owner, and promotion owner.
- Secret, queue, webhook, storage, observability, data, and retention maps.
- A synthetic test-data policy and production-access exception process.
Current Contract
Ideogram supports multiple revocable keys, but keys within one team share credit and billing. Team roles are Owner, Admin, and Member. Environment separation therefore needs application-owned budgets and controls even when separate vendor keys use one shared team.
Authentication
Create distinct secret references per environment and inject each server-side as Api-Key to https://api.ideogram.ai. Never copy a production key into developer machines, pull-request jobs, staging configuration, or shared examples.
Instructions
- Inventory each environment's key reference, team, role owner, budget, route, queue, webhook URL, storage prefix, telemetry, and data class.
- Assign distinct keys where supported and document the shared-credit boundary of any common Ideogram team.
- Enforce application-side environment and tenant budgets, concurrency, and destination allowlists.
- Use environment-specific webhook hosts and bind every delivery to a known generation, tenant, and environment.
- Isolate object stores or prefixes, signing keys, retention jobs, and publication targets.
- Promote immutable code and schema evidence, not prompts, images, URLs, credentials, or in-flight state.
- Test wrong-key, wrong-webhook, wrong-bucket, and cross-environment access denial plus independent rollback.
Tool Discipline
Use Read, Glob, and Grep to inspect configuration and infrastructure. Use Write and Edit for approved environment definitions or tests. Do not create keys, copy secrets, add credit, or mutate deployments without the relevant owner.
Approval Boundaries
Require approval for production access, shared team or balance use, role changes, secret creation or revocation, data copying, external publication, and deployment. Treat emergency production access as time-bounded and auditable.
Error Handling
- A distinct key does not imply a distinct vendor balance.
- Reject callbacks and objects whose recorded environment differs from the receiver or storage boundary.
- Revoke a key copied across environments and verify all consumers before restoration.
Output
Return an environment matrix of key references, shared billing, budgets, routes, queues, webhook hosts, stores, data classes, promotion gates, owners, test results, and rollback state. Exclude actual secrets and content.
Examples
- Keep development offline by default, staging on synthetic paid canaries, and production behind protected deployment approval.
- Report
prod_key_in_nonprod=false; webhook_cross_env=denied; storage_cross_env=denied.
Validation
Scan for reused secret values or references, test network and object-store separation, deliver signed wrong-environment fixtures, and rehearse independent rollback. Confirm test assets are absent from production.
Resources
- Current first-party evidence map — use the dated endpoint, webhook, billing, team, and training links as the contract index for this workflow.
- Recheck the endpoint-specific page and current OpenAPI description before relying on an enum, limit, beta feature, or lifecycle claim.
- Record live observations as environment-specific evidence, not as universal vendor guarantees.
When not to use it
- →Using shared API keys across environments
- →Storing production secrets in .env files
Prerequisites
Limitations
- →Requires distinct API keys for each environment
- →Startup validation fails if configuration is incomplete
How it compares
This approach prevents cross-environment pollution by enforcing strict secret management and environment-specific configuration schemas.
Compared to similar skills
ideogram-multi-env-setup side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ideogram-multi-env-setup (this skill) | 1 | 2mo | Review | Intermediate |
| swarm-act | 0 | 3mo | Review | Advanced |
| miniprogram-development | 37 | 3mo | No flags | Intermediate |
| azure-functions | 10 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
swarm-act
ethersphere
Guide to Swarm ACT encryption and access control: create grantees, upload protected data, grant/revoke access, and troubleshoot not-found/history issues.
miniprogram-development
TencentCloudBase
WeChat Mini Program development rules. Use this skill when developing WeChat mini programs, integrating CloudBase capabilities, and deploying mini program projects.
azure-functions
aj-geddes
Create serverless functions on Azure with triggers, bindings, authentication, and monitoring. Use for event-driven computing without managing infrastructure.
firebase
davila7
Firebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they're often wrong. Firestore queries are limited, and you learn this after you've designed your data model. This skill covers Firebase Authentication, Firestore, Realtime Database, Cloud Functions, Cloud Storage, and Firebase Hosting. Key insight: Firebase is optimized for read-heavy, denormalized data. I
blockchain-developer
sickn33
Build production-ready Web3 applications, smart contracts, and decentralized systems. Implements DeFi protocols, NFT platforms, DAOs, and enterprise blockchain integrations. Use PROACTIVELY for smart contracts, Web3 apps, DeFi protocols, or blockchain infrastructure.
file-uploads
davila7
Expert at handling file uploads and cloud storage. Covers S3, Cloudflare R2, presigned URLs, multipart uploads, and image optimization. Knows how to handle large files without blocking. Use when: file upload, S3, R2, presigned URL, multipart.