agent-skills-mirror

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish, or hand off.

Manage persistent coding sessions across Claude Code, Codex, Gemini, Cursor, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, or exposing the orchestrator's 65 tools as an MCP server to Hermes Agent / Claude Desktop / Cursor / Cline / Continue / Zed / Windsurf / Goose. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "autoloop", "ultraapp", "Forge tab", "build a web app", "one-click app", "AppSpec", "autonomous iteration", "iterate until goal", "deep paper review", "auto research", "switch model", "multi-agent", "coding session", "session inbox", "cursor agent", "opencode", "mcp server", "clawo-mcp", "hermes mcp", "model context protocol

Use when starting a turn or checking Aegis skill routing.

Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when the user explicitly requests strict or test-first TDD, or when the current conversation already contains an explicit `TDD Route: strict` decision from another Aegis workflow.

Use when the user provides a plot summary, scene idea, character relationship, emotional beat, or short video concept and wants a cinematic AI video prompt. First diagnose the story, then rewrite it into a model-ready prompt for Kling, Seedance, Veo, Sora, Runway, Jimeng, or general AI video models.

Use before claiming CodeWhale release work is done: run the full gate sweep and list the manual QA targets.

Cluster a milestone of issues into coherent implementation workstreams with sequencing, dependencies, and a lead train.

Clarify a rough product or engineering idea into a BRD-lite brief (Why) with measurable business value.

Turn an approved PRD or implementation goal into SRS/FRS technical requirements (How), architecture, contracts, and verification decisions.

Plan a feature from BRD-lite brief or clear intent into PRD (What), decisions, implementation plan, and task slices.

Route a task to the next synced SDLC workflow based on current artifacts and repo state.

Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.

Create scientific conference posters as .pptx files using python-pptx. Handles A0/A1 layouts, section placement, figure insertion, and academic color schemes. Exports editable .pptx and PDF.

Verify BRD-lite, PRD, SRS/FRS, UX, and test prerequisites before implementation starts.

Systematic root-cause debugging: find the cause before writing any fix

Strategic product gate: challenge the brief, find the 10-star product hiding inside the request, before writing any code

Engineering architecture gate: lock architecture, diagrams, edge cases, and test matrix before writing implementation code

Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop

🛒 E-commerce & Retail skill suite derived from VoltAgent/awesome-agent-skills. Product catalogue optimisation, conversion rate, customer journey and retail analytics. Provides 10 specialised commands for ecommerce, retail, shopify workflows.

📈 SEO & Content Marketing skill suite derived from VoltAgent/awesome-agent-skills. Keyword research, content audits, SERP analysis, technical SEO and content strategy. Provides 10 specialised commands for seo, content, marketing workflows.

Captura sinais de aprendizado relevantes durante o fluxo do Superpowers para revisão futura

Orquestra acquire-codebase-knowledge para bootstrap ou redescoberta do conhecimento do codebase

Valida sinais do inbox e promove para docs/lorebase/*.md apenas com evidência verificável

Use this skill when asked to search public content platforms such as Bilibili or YouTube, pick the top relevant results for a topic, and summarize each item with links and brief overviews. Uses Runtime-aware routing — opencli first, fetch second, browser last.

Skill 创建向导 - 交互式引导按模块生成 Copilot 专家 Skill。 支持任意平台和应用层级，自动从 project-profile.json 读取技术栈配置。 分批深度研究 + 分批生成，确保代码入口精确。 触发关键词: 创建Skill, 新应用专家, 生成模块专家, app skill wizard, 新增应用, 为应用创建专家, 添加应用Skill, create app skills, 平台Skill, 再生专家, regenerate experts, 批量生成Skill, 项目接入, project setup, 新项目专家

Bug 辅助诊断专家 - 两种模式：批量分析历史 Bug 生成模式库，实时诊断定位嫌疑文件。 模式A: 读取 data/bug_analysis/ 的 JSON 数据，分析并生成 bug-patterns.md 到模块 Skill。 模式B: 接收 Bug ID 或描述，路由到对应模块专家，聚合诊断建议。 触发关键词: Bug诊断, 缺陷分析, 问题排查, bug diagnosis, 更新Bug模式库, Bug模式, 嫌疑文件, regression, 崩溃分析, 黑图排查, bug-patterns

设计驱动自动编码 - 读取圆桌会议设计文档，按任务拆解逐任务自动编码，直接写入项目文件。 触发关键词: 根据设计编码, 开始编码, 按设计实现, coding agent, 实现设计方案, 按圆桌会议编码, 从设计文档编码, 执行编码任务, start coding, implement design

购物车模块域专家。管理商品加购、数量修改、优惠计算和结算流程。 触发关键词: 购物车、cart、加购、结算、SKU、优惠券、coupon、下单、checkout

经验固化协议：将解决问题中发现的最佳实践自动提炼、分类、写入 Agent 规则或 Skill 知识库，并同步上传。 触发关键词: 固化经验, 总结教训, 升级规则, 经验沉淀, codify experience, harness learning, 提炼经验

专家索引 - 智能推荐合适的领域专家。 触发关键词: 推荐专家、不确定找谁、哪个专家、专家列表、帮我选专家、有哪些专家。 输入: 问题描述或功能关键词。 输出: 推荐的专家列表及调用方式。 **重要**: 这是唯一维护专家列表的地方，其他 skill 通过引用此索引获取专家信息。

代码追溯专家 - 查找代码修改者、关联PR、获取改动背景。 触发词: 谁改的, 谁写的, blame, 追溯, 找作者, 这行代码, 提交记录, 谁提交的, PR, 代码历史

MCP Server 开发指南 - 帮助创建高质量的 MCP (Model Context Protocol) 服务器。 当需要构建 MCP 服务器来集成外部 API 或服务时使用，支持 Python (FastMCP) 和 Node/TypeScript (MCP SDK)。 触发关键词: mcp开发, mcp服务器, model context protocol, 构建mcp, 创建mcp

需求返讲助手 - 帮助研发人员进行需求评审和返讲文档撰写。 触发关键词: 需求返讲、评审需求、返讲文档、检查需求、需求拆解、PBI评审、需求完整性。 输入: DevOps PBI链接、需求描述、或PBI内容。 输出: 需求返讲文档、检查清单结果、风险点、遗漏项。 适用场景: 收到PM需求后进行评审、检查需求完整性、撰写返讲文档。

项目接入辅助 Skill - 提供 ProjectSetup Agent 的 schema 定义、subAgent prompt 模板和质量标记规范。 触发关键词: project-onboarding, 项目接入辅助, 接入schema, component-map

圆桌会议 - 多子Agent协作生成高质量设计文档。触发关键词：圆桌会议、设计文档、生成设计、详细设计、架构设计、plus design、出设计、写设计、深度设计、给我出一份设计、设计评审、圆桌会议plus。输入：PBI需求、设计方案、技术选型。输出：可直接编码的设计文档。核心机制：必须使用runSubagent启动5个独立子Agent，分层执行（4并行+实施派依赖），主Agent组装设计评审文档，6个文件交付。

全局运维规则集 - 按需加载的对话管理、MCP工具、代码规范、质量检查等规则。 触发关键词: 运维规则, MCP工具, 代码规范, 质量自检, 对话管理, 版本检查, 阶段过渡

研发工作流入口 - 帮助用户快速进入正确的工作流阶段。 触发关键词: 工作流, 流程, 从哪开始, 帮我, 我该怎么做, 下一步, workflow, 不知道用什么, 新手引导, 怎么用