Define team processes for codebases largely implemented by AI agents. Covers planning, ownership rules, architecture, review criteria, and testing requirements, helping teams assess generated code through measurable acceptance criteria, system behavior, and regression checks.
Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.
Helps teams define their development process when AI agents handle much of the implementation. It organizes standards for planning, ownership, reviews, and testing, with an emphasis on measurable acceptance criteria and evaluations. Reviews cover system behavior, data integrity, failure handling, and safe releases, alongside code formatting.
Use it when setting team rules for generated code or agreeing on what reviewers should check. It also addresses designs that help agents work effectively: clear boundaries, stable contracts, typed interfaces, and tests that reproduce results under the same conditions. For hiring and performance evaluation, it covers the ability to break down ambiguous work and create prompts and evaluations.
The testing policy requires regression coverage for changed areas, explicit checks for unexpected inputs and boundary conditions, and integration checks where interfaces meet. These requirements form part of the standards used to assess generated code.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 19, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Use this skill when designing process, reviews, and architecture for teams shipping with AI-assisted code generation.
Prefer architectures that are agent-friendly:
Avoid implicit behavior spread across hidden conventions.
Review for:
Minimize time spent on style issues already covered by automation.
Strong AI-first engineers:
Raise testing bar for generated code:
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Design and audit interfaces for Web, iOS, and Android using WCAG 2.2 accessibility guidance. Check screen-reader labels, keyboard navigation, contrast, and control sizes to identify barriers and guide implementation for people using assistive technology.
Investigate unreliable AI agents across 12 layers, including instructions, memory, tool execution, and display. Use code and logs to trace failures, rank findings by severity, and produce an ordered repair plan that prioritizes code changes.
Compare coding agents on tasks from your own codebase. Define success checks, run agents in separate Git working directories, and report pass rates, available API costs, completion time, and consistency across repeated trials.
Design and refine an AI agent’s available actions, tool inputs, and result formats. Define recovery steps for errors, manage the information kept in context, and evaluate changes through completion rates, retries, and cost per successful task.
Diagnose AI agent runs that fail repeatedly, loop through tools, or lose track of the task. Capture errors and environment details, test a focused recovery action, and produce a report explaining the evidence and outcome.
Diagnose failed AI agent runs by capturing errors, checking likely causes, and choosing small, reversible recovery actions. The workflow produces a structured report of the failure, recovery steps, and evidence, helping explain repeated retries or stalled progress.