ideogram-prod-checklist
A production readiness checklist for launching Ideogram-powered features.
Install
mkdir -p .claude/skills/ideogram-prod-checklist && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4113" && unzip -o skill.zip -d .claude/skills/ideogram-prod-checklist && rm skill.zipInstalls to .claude/skills/ideogram-prod-checklist
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.
Execute Ideogram production deployment checklist and rollback procedures.Key capabilities
- →Verify production API key validity
- →Validate image download functionality
- →Configure circuit breakers for failure handling
- →Execute rollback procedures
How it works
The workflow performs a series of automated checks against the production API to verify connectivity, key validity, and image retrieval before deployment.
Inputs & outputs
When to use ideogram-prod-checklist
- →Configuring production API keys
- →Setting up image storage infrastructure
- →Validating request timeout settings
- →Implementing production retry logic
- →Planning rollback procedures
About this skill
Ideogram Production Readiness Gate
Overview
Produce a fail-closed release decision for an Ideogram integration. A visually successful test is only one signal; production readiness also requires owned billing, secure credentials, bounded capacity, moderation, durable assets, async reconciliation, telemetry, and a tested rollback.
Prerequisites
- Immutable release SHA, target environment, change owner, approver, and deployment window.
- Current architecture, endpoint inventory, tests, SLOs, budgets, retention, and incident runbook.
- Staging parity and a synthetic canary that contains no customer-derived content.
Current Contract
Live API calls require accepted terms, payment method, positive prepaid credit, and a valid Api-Key. Generation routes differ by endpoint and sync or async lifecycle. Safety is item-level, image URLs expire, and default capacity is documented as 10 in-flight requests.
Authentication
Confirm a target-environment secret reference, server-only injection, correct Api-Key header, scoped application authorization, and exercised revocation. Never place a real key in the release artifact or checklist evidence.
Instructions
- Freeze the SHA and compare implemented endpoints, multipart fields, and schemas to current first-party docs.
- Verify terms, positive credit, billing owner, alert thresholds, and a response to exhausted balance.
- Prove secret handling, tenant authorization, media validation, safety and copyright policy, and retention controls.
- Test sync and async success, unsafe output, every handled error class, webhook verification, polling fallback, duplicates, and terminal-state closure.
- Confirm account-level concurrency, queue bounds, deadlines, storage download, expiring-URL removal, and object deletion.
- Review dashboards, alerts, on-call ownership, support escalation, and content-free evidence.
- Run a staging canary, execute rollback rehearsal, obtain explicit approval, then deploy a bounded production canary.
- Reconcile final state and stop or roll back on any failed gate.
Tool Discipline
Use Read, Glob, and Grep to inspect release evidence. Use Write and Edit only for approved fixes or release documentation. Do not deploy, add credit, rotate keys, alter policy, or run production generation by invocation alone.
Approval Boundaries
The named approver owns live spend, production traffic, policy settings, and rollback acceptance. Missing evidence, unknown asset retention, unverified webhook signatures, or an untested rollback yields a no-go decision.
Error Handling
- Stop on schema drift, secret exposure, unsafe-publication paths, unbounded queueing, or inability to persist output.
- Never waive a failed gate because the canary image looks correct.
- Roll back traffic before debugging a release that creates duplicate paid work or loses async state.
Output
Return SHA, environment, gate-by-gate pass or fail, evidence identifiers, canary metrics, known risks, approver, deployment state, and rollback receipt. Exclude keys, prompts, images, and URLs.
Examples
- Mark no-go when generation succeeds but the application retains only expiring vendor URLs.
- Mark go after verified signatures, polling fallback, safety handling, storage deletion, and rollback all pass.
Validation
Rerun the exact release test set against the frozen SHA, verify evidence timestamps and owners, and compare deployed digest to approved digest. Confirm canary termination and rollback remain available after launch.
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
- →When production infrastructure is not ready
- →When monitoring stack is missing
Prerequisites
Limitations
- →Requires durable storage for images
- →API key must be separate from development keys
How it compares
This checklist formalizes the go-live process with specific health checks and rollback scripts rather than relying on manual verification.
Compared to similar skills
ideogram-prod-checklist side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ideogram-prod-checklist (this skill) | 1 | 2mo | Caution | Advanced |
| miniprogram-development | 37 | 3mo | No flags | Intermediate |
| azure-functions | 10 | 7mo | Review | Intermediate |
| workflow | 4 | 3mo | 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
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.
workflow
vercel
Creates durable, resumable workflows using Vercel's Workflow DevKit. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of "workflow", "durable functions", "resumable", "workflow devkit", or step-based orchestration.
azure-static-web-apps
github
Helps create, configure, and deploy Azure Static Web Apps using the SWA CLI. Use when deploying static sites to Azure, setting up SWA local development, configuring staticwebapp.config.json, adding Azure Functions APIs to SWA, or setting up GitHub Actions CI/CD for Static Web Apps.
aws-serverless
davila7
Specialized skill for building production-ready serverless applications on AWS. Covers Lambda functions, API Gateway, DynamoDB, SQS/SNS event-driven patterns, SAM/CDK deployment, and cold start optimization.
cloudrun-development
TencentCloudBase
CloudBase Run backend development rules (Function mode/Container mode). Use this skill when deploying backend services that require long connections, multi-language support, custom environments, or AI agent development.