Design, implement, or review AI-generated software changes with explicit architecture boundaries, stable contracts, single sources of truth, visible failures, maintainable modules, migration safety, and preserved user changes. Use for feature implementation, bug fixes, refactoring, API or schema changes, frontend-backend coordination, or code review where fast generation risks duplication, drift, silent fallback, or brittle structure.
EnglishOrchestrate evidence-gated AI software delivery from an ambiguous request through product framing, implementation, verification, operational safety, and durable closeout. Use when a beginner or solo builder wants Codex to turn an idea into working, tested, releasable software with plain-language checkpoints, or for complex features, cross-module changes, risky fixes, project setup, modernization, migration, and release work that needs coordinated product, engineering, test, security, and operations perspectives.
EnglishGovern system ports, rewrites, framework or language upgrades, architecture refactors, production replacements, and open-source extractions without losing contracts, business truth, or completion criteria. Use when migrating between stacks, modernizing legacy software, preserving old behavior in a new implementation, deciding whether a replacement is cutover-ready, separating a private source from a writable target, or packaging a reviewable handoff.
EnglishDesign and execute risk-based software verification that produces trustworthy evidence rather than false-green checks. Use for test planning, regression selection, bug-fix verification, contract tests, integration tests, end-to-end tests, release acceptance, flaky-test diagnosis, assertion review, or any claim that a change is complete, safe, or production-ready.
EnglishIncludes Engineering Guardrails, Exocrew Delivery, System Modernization, and other workflows.
Supported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Engineering Guardrails
Design, implement, or review AI-generated software changes with explicit architecture boundaries, stable contracts, single sources of truth, visible failures, maintainable modules, migration safety, and preserved user changes. Use for feature implementation, bug fixes, refactoring, API or schema changes, frontend-backend coordination, or code review where fast generation risks duplication, drift, silent fallback, or brittle structure.
Exocrew Delivery
Orchestrate evidence-gated AI software delivery from an ambiguous request through product framing, implementation, verification, operational safety, and durable closeout. Use when a beginner or solo builder wants Codex to turn an idea into working, tested, releasable software with plain-language checkpoints, or for complex features, cross-module changes, risky fixes, project setup, modernization, migration, and release work that needs coordinated product, engineering, test, security, and operations perspectives.
System Modernization
Govern system ports, rewrites, framework or language upgrades, architecture refactors, production replacements, and open-source extractions without losing contracts, business truth, or completion criteria. Use when migrating between stacks, modernizing legacy software, preserving old behavior in a new implementation, deciding whether a replacement is cutover-ready, separating a private source from a writable target, or packaging a reviewable handoff.
Test Evidence
Design and execute risk-based software verification that produces trustworthy evidence rather than false-green checks. Use for test planning, regression selection, bug-fix verification, contract tests, integration tests, end-to-end tests, release acceptance, flaky-test diagnosis, assertion review, or any claim that a change is complete, safe, or production-ready.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Engineering Guardrails skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.