zhihu-plus-plus

Release the LaTeX fork used by Zhihu++. Use when merging the latest huarangmeng/latex release into zly2006/latex, preserving approved fork deltas, publishing Maven Central artifacts, updating Zhihu's vendored third_party/markdown and direct LaTeX dependencies, and verifying the app.

Build, install, and launch the Zhihu++ Android app on a connected device using ADB. Includes comprehensive troubleshooting for common issues like missing devices, installation failures, signature mismatches, and app crashes. Use when deploying debug builds to physical devices or emulators.

Manage screenshots and other visual assets for GitHub pull requests. Use when a PR body needs real screenshots, when local /tmp paths must be replaced with durable links, when deciding whether GitHub web drag-and-drop uploads can be reproduced with gh api, or when updating a PR without disturbing the user's browser tabs.

Use for Zhihu++ maintenance work that scans Kotlin main sources for low-call functions, structurally similar function bodies, dead code, pure forwarding wrappers, pointless abstractions, repeated helpers, and cross-platform duplicate glue before refactoring or PR cleanup. Trigger when the user asks to clean AI slop, remove low-call wrappers, find similar or duplicated code, review duplicated helper functions, or audit functions with call count at most 2 in /Users/zhaoliyan/IdeaProjects/Zhihu.

Coordinate Zhihu++ issue and PR implementation through subagents with isolated git worktrees, off-host Android AVD validation, real screenshots, Chinese PR creation, and main-agent-only review/coordination. Use when the user asks to fan out issues, maximize parallel subagent work, implement multiple Zhihu++ features or fixes, validate on `$off-android-avd-ci-debug`, or automatically open PRs from worker branches.

Zhihu++ LLM 自动化 UI 测试。使用 testTag 系统精准定位 Compose 元素并交互，替代硬编码坐标的 adb tap。提供已知 tag 列表、文字内容点击、截图验证等能力。适用于：功能验证、UI 回归测试、自动化交互流程。

当用户要求复刻知乎网页版的功能、交互、接口行为或视觉细节时，使用此技能采集真实网页证据、分析 API 与 UI 结构，并落地到 Zhihu++ Android 代码。

以 subagent 启动的 UI 挑剔用户评审。Use when the user, AGENTS, or the current task requires “挑剔的用户”. 该 skill 会分别扮演新用户与老用户，对界面的 self explain、明确性、直觉性、效率、布局和操作习惯提出高标准意见；默认给出 5-10 条有效建议，必要时结合 ui-test 与截图检查，并把意见记入 .memory/YYYY-MM-DD/picky-user。

以 subagent 启动的 UI 漫游与异常发现技能。Use when the user, AGENTS, or the current task requires “UI漫游者”. 该 skill 负责系统性地把目标页面能点的都点一遍、把上下左右能滑的都滑一遍，重点发现空白页、越界、裁切、错位、布局失衡、状态切换异常等问题；必要时结合 ui-test 与截图检查，并把意见记入 .memory/YYYY-MM-DD/ui-volayor。