Agent skills for OpenAI Agents SDK

Generates Xiaohongshu (Little Red Book) infographic series with 9 visual styles and 6 layouts.

Fix responsive layout issues, missing mobile behavior, touch targets, and viewport handling.

Rewrite confusing UX copy so interfaces explain themselves: labels, buttons, errors, empty states, tooltips.

Simplify code for clarity without changing behavior.

Evaluate interfaces with two-pass design review: scoring, persona tests, AI slop detection, Nielsen heuristics, and 25 anti-patterns.

Debug systematically using root-cause analysis.

Add micro-interactions, transitions, hover states, and feedback animations.

Review every non-trivial decision with a fresh-context adversarial review.

Fix critical and high-severity accessibility, input, and state issues deterministically.

Extract what the user actually wants through one-question-at-a-time interviewing.

Fix performance issues: bundle size, animations, reflows, lazy loading, image optimization, render blocking.

Optimize application performance beyond the frontend: Core Web Vitals, load times, server response, database queries, caching, profiling.

Improve existing codebases systematically: scan the UI, diagnose issues across 8 categories, fix in priority order.

Harden code against vulnerabilities: OWASP prevention, input validation, authentication, data storage, and third-party safety.

Analyze failing eval cases and propose improvements.

Ground every implementation decision in official documentation before writing code.

Write tests first with RED-GREEN-REFACTOR cycle.

Fix typography and reading rhythm issues: typeface, weight, size, line-height, spacing, type ramp.

Use when deciding which jue-* sub-skill to invoke next, or when sequencing manuscript work from topic through rebuttal for a Journal of…

Use when tagging a Julia package version, updating the loulouJL registry, or computing artifact hashes for Artifacts.toml.

Generate hierarchical AGENTS.md structures for codebases.