Organize engineering work carried out by AI agents with clear completion criteria, small verifiable tasks, and evaluations before and after implementation. Match model choice to task complexity and track tokens, retries, time, and outcomes to manage cost.
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.
This skill organizes development from planning through evaluation when AI agents handle most implementation. Before work begins, it defines completion criteria and evaluation methods. It records baseline results, repeats the evaluations after implementation, and compares the changes. Work is divided into roughly 15-minute units, each independently verifiable, with a clear main risk and completion condition.
Use it when handing development to an agent and wanting consistent task boundaries and quality checks. Reviews of generated code prioritize required conditions, edge cases, error handling, authentication assumptions, and the effects of changes. It also covers switching sessions at major milestones and summarizing conversations.
The model guidance assigns Haiku to narrow edits, Sonnet to implementation and refactoring, and Opus to design and root-cause analysis. Move to a higher model tier when the reason the lower tier failed is clear. People remain responsible for quality and risk management.
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 for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls.
Apply the 15-minute unit rule:
Prioritize:
Do not waste review cycles on style-only disagreements when automated format/lint already enforce style.
Track per task:
Escalate model tier only when lower tier fails with a clear reasoning gap.
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.