jackwener

扮演方案的"反对方"，挑刺、找隐藏问题、戳过度自信的假设。/think 给出 plan 后强烈建议立刻跑一次 /challenge——让方案在落地前先经过一轮自我对抗。

把本次踩到的坑写进 .qoder/business-logic/gotchas.md，每条强制 4 段结构（现象 / 根因 / 正确做法 / 反例）。比 /update-context 更窄、更结构化——只管 gotcha 这一类。

session 结束时总结本次做了什么 / 没做完什么 / 关键决策 / 下一步从哪继续。用于写 commit body、更新 spec progress.md、交接给下一个 session。每个有产出的 session 结束前都该跑一次。

任务完成后的 diff 审查。完成代码改动后必须执行：看 git diff、对照原始目标、跑验证命令、输出审查报告。不允许"看起来 OK"就宣称完成。

Bug 系统化排查。给定问题描述后先复现 → 定位 → 提假设 → 验证 → 再决定怎么修。任何 bug、回归、线上异常、"为什么不 work" 类问题开始前必须执行。

最小改动模式。线上修复 / 小 bug / 老项目维护 / 跨多人协作的代码区域改动时强制启用：不重构无关代码、不格式化整文件、每处 diff 都解释必要性。

开工前澄清需求、列 Non-Goals、给候选方案。任何超过 30 分钟、跨多文件、或语义不完全清晰的任务，开始前必须执行；避免 Agent 抱着模糊的理解直接动手。

任务结束后沉淀团队记忆。把本次发现的边界 case、踩坑、隐性约束、有效技巧写入 .qoder/business-logic/gotchas.md（或更新对应业务文档），让下次会话不再踩同一个坑。

Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works…

Build or improve an OpenCLI JS adapter using observed site behavior, existing adapters and browser API evidence. For ad-hoc browser interaction, see opencli-browser.

Drive Chrome with OpenCLI to inspect pages, interact with logged-in sites, capture API evidence, and manage native tabs, groups and windows. For reusable adapters, see opencli-adapter-author.

Discover and invoke OpenCLI capabilities for websites and Chrome. Find commands, inspect schemas, interpret results and choose browser or adapter tools.

基于 opencli 命令的智能搜索路由器。当用户想要使用 OpenCLI、CLI 或 API 搜索、查询、查找或研究信息时，尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时，务必使用此 skill

Ingest source material into an LLM Wiki vault. Use whenever the user invokes `/ingest`, asks to turn documents, notes, chats, or URLs into durable wiki knowledge, or asks to create or update interconnected wiki pages from source material.

Audit and safely maintain an LLM Wiki vault. Use whenever the user invokes `/lint`, asks to check wiki quality or health, or asks to find and optionally repair broken links, missing frontmatter, stale pages, orphan pages, source drift, or duplicate topics.

Answer questions from an LLM Wiki vault. Use whenever the user invokes `/query`, asks what the wiki knows about a topic, or needs an evidence-grounded synthesis of existing wiki pages and their links.

Research a topic for an LLM Wiki vault. Use whenever the user invokes `/research`, asks for a sourced deep dive beyond the current wiki, or asks to discover external sources and integrate the resulting knowledge into the wiki.

通过多轮对话确认生成 Spec 上游文档（03-立项提案、04-PRD、05-用户故事、09-API规格），再批量生成下游规格文档。适用于研报助手等项目的完整规格文档集生成场景。

Grade a team's backend implementation against its spec on 9 weighted dimensions, producing a markdown report + JSON summary with evidence.

Grade a team's frontend implementation against its spec on 10 weighted dimensions, producing a markdown report + JSON summary with evidence.

Use xiaohongshu-cli for ALL Xiaohongshu (Little Red Book, 小红书) operations — searching notes, reading content, browsing users, liking, collecting, commenting, following, and posting. Invoke whenever the user requests any Xiaohongshu interaction.

Fetch WeChat Official Account (微信公众号) articles from mp.weixin.qq.com and convert to Markdown. 微信文章转 Markdown 工具。

Use boss-cli for ALL BOSS 直聘 operations — searching jobs, viewing recommendations, managing applications, chatting with recruiters, and batch greeting. Invoke whenever the user requests any job search or recruitment platform interaction on BOSS 直聘.

wx-cli — 从本地微信数据库查询聊天记录、联系人、会话、收藏等。用户提到微信聊天记录、联系人、消息历史、群成员、收藏内容时，使用此 skill 安装并调用 wx-cli。

Headless-browser-based CLI skill for Xiaohongshu (小红书, RedNote, XHS) to search notes, read posts, browse profiles, like, favorite, comment, and publish from the terminal

CLI skill for Telegram to sync chats, search messages, filter keywords, and monitor groups from the terminal

Discord CLI with YAML-first structured output for AI agents — fetch chat history, search messages, sync channels, and AI analysis

Save a web page as a Markdown file. Use when the user asks to save, clip, archive or export a page, or to read it as Markdown.