suphiozdedee

Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-CDP live-DOM auditing; falls back to a browser-MCP…

Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name>] to diff against a branch. Reports only new violations introduced, violations fixed, and pre-existing count. Use…

Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.

Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance.

Audit a component or page for accessibility issues and fix them

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.

Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot

Run protected AAS maintainer sweeps, PR merge batches, canonical sync, Core preview checks, and scripted releases. Use for repository maintenance, main alignment, CLI/MCP/Workbench changes, or release work; not ordinary contribution tasks.

把用户上传的 Logo、人物头像、个人形象、IP 角色、插画、产品照片或标志性物件，扩展成一套统一的视觉身份提示词。用户提到一张图做品牌全案、个人品牌视觉、头像延展、IP 设定、品牌主视觉、包装周边、社交媒体视觉，或要求保持参考图一致性生成多场景图片时使用。默认输出视觉 DNA 卡和一组可直接生图的完整提示词；有生图工具且用户明确要求时可继续生成图片。

Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK. ACTIVATE this skill when the user wants to create, configure, or orchestrate Google Antigravity agents.

Plan and generate a conversion-oriented image-ad set in two phases: approve a hero concept and copy direction, then fan it out into platform formats.

Generate on-brand social or advertising image candidates from a confirmed brand system and asset library, with explicit compliance checks.

Combine multiple authorized portraits into a coherent group scene while preserving each person's likeness, placement, and consent boundaries.

Edit or transform a supplied image while preserving the specific people, products, composition, or brand details the user marks as fixed.

Apply a bounded image-enhancement operation such as upscaling, background removal, extension, or cleanup while preserving the intended subject.