agent-skills

Simplify recently written or modified code for clarity, consistency, reuse, and maintainability without changing behavior. Apply three review lenses: reuse, quality, and efficiency. Use when the user asks to simplify, clean up, refine, polish, or make code clearer; after a feature, bug fix, or refactor leaves code working but harder to read; or when changed code feels too nested, repetitive, clever, or inconsistent with the surrounding project style.

Forge a coding or agentic prompt optimized for Claude Opus 4.7 or GPT-5.5 (Codex CLI) by interviewing the user with structured multiple-choice questions, then writing a precise XML-tagged prompt and optional SPEC.md handoff. Use whenever the user asks to write a prompt, scope a coding task, design a system prompt for a coding agent, brainstorm requirements before implementation, or build a SPEC.md for spec-driven development. Invoke even if the user does not say "interview me": if they want help crafting a prompt for Claude Opus 4.7, GPT-5.5, Codex, or any long-horizon coding or agentic task, this is the skill.

Write or refine prompts specifically for GPT-5.5, including Codex CLI runs and Responses API agentic workflows. Use when Claude or another harness needs a high-performance OpenAI-style GPT-5.5 prompt with reasoning.effort, text.verbosity, XML block contracts, persistence, decision rules, completeness contracts, verification loops, tool-use parallelism, and outcome-first acceptance criteria.

Write or refine prompts specifically for Claude Opus 4.7, especially for long-horizon coding, repo implementation, debugging, migrations, tool use, and validation-heavy execution. Use when Codex needs a high-performance Anthropic-style Opus 4.7 prompt with adaptive-thinking, effort, tool-use, XML structure, persistence, concrete acceptance criteria, and local verification guidance.