发现 AI Agent 技能

Run a standalone code review on lilnas changes — correctness, testing, maintainability, project standards — plus conditional reviewers (kieran- typescript, julik-frontend-races, security, performance, api-contract, reliability, equations-security, adversarial, code-simplicity, previous- comments). Writes a numbered, severity-sorted, emoji-rich report with code snippets, fix options, trade-offs, a selectable summary list, and a recommendation to `REVIEW.md` at the repo root (any prior `REVIEW.md` is deleted first); the chat shows only the picker and recommendation so you can reply with issue numbers inline. Use before pushing a lilnas PR or any time the user types /lilnas-code-review. Fully self-contained — no dependency on /ce-code-review or the compound-engineering plugin.

Perform a comprehensive multi-agent parallel code review on git changes, acting as a senior staff software engineer. Reviews staged files if any exist, otherwise reviews unstaged files. Reads project documentation (README, docs/, package.json) to understand the type of software being reviewed, then selects and launches specialized reviewer agents in parallel (Frontend, Backend, Architecture, Security, DevOps, Design/UX, Testing) tailored to the project context. Consolidates all findings into a structured report with a severity-sorted action items list. Use when the user types /review, asks for a code review, or wants to review git changes.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.