Explorar skills

Rewrite a support response in a different tone - formal, casual, technical, empathetic, or concise.

Zustand + TanStack Query 상태 관리 패턴. store 생성, devtools, 서버 상태 연동, 디렉토리 구조.

Redux Toolkit(RTK) 상태 관리 패턴. createSlice, configureStore, RTK Query(createApi), slices 디렉토리 구조.

Search the vault using QMD semantic search. Use PROACTIVELY before reading files directly — whenever the user asks about past decisions, incidents, people, meetings, architecture, patterns, or any vault content. Always prefer QMD over Grep/Glob for vault queries. Also use after creating/editing notes to check for duplicates and related content.

Transform raw OKR data (metrics, percentages, notes) from files or pasted text into a readable narrative progress update for stakeholders. Use when preparing weekly or quarterly OKR reports, board updates, or team syncs. Triggers: 'okr update', 'narrate okr progress', 'stakeholder okr update', 'generate okr report', 'okr status update', 'окр апдейт', 'нарратив по OKR', 'прогресс-апдейт для стейкхо

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

Turn dashboard numbers into a ready-to-send weekly narrative for stakeholders. Paste metrics + context → polished email or Slack post in minutes. Use when writing weekly updates for leadership or team. Triggers: 'weekly metrics story', 'write metrics narrative', 'metrics to email', 'turn numbers into story', 'недельный нарратив по метрикам', 'метрики в email', 'напиши обновление по метрикам'.

Interpret A/B test results in plain language and get a ship/rollback/extend recommendation with a stakeholder summary. Use when you have experiment results from any analytics tool and need a clear go/no-go decision. Triggers: 'interpret experiment results', 'read my A/B test results', 'should I ship this experiment', 'интерпретируй результаты эксперимента', 'помоги прочитать результаты A/B теста'.

跨子 agent 协议/数据结构/流程对齐 skill。当一个项目的契约（API/事件协议/数据结构/接口/流程）需要由两个子 agent 各自代表实现方立场来回审稿时使用。用户作为人类中间人，在两个子 agent 之间传递文档与反馈。 典型场景：项目 A 的子 agent 写了一份 contract 文档，项目 B 的子 agent 要从实现方角度审稿、提反馈、敲细节，多轮迭代到双方都站得住脚。 触发关键词："和另一个子 agent 对齐协议"、"跨团队 contract review"、"让另一个子 agent 给意见"、"多子 agent 讨论"、"另一个工程师设计的协议你看看"、"我把反馈传过去了，对方改了"、"x-multi-llm-align"、"multi-agent 流程"，或用户描述的场景里同时出现"另一个子 agent/工程师/项目"+"协议/契约/数据结构/接口"+"

작업 산출물 정리. design-refs, test-results, temp 파일 등.

Django 기반 Python 백엔드 컨벤션

Bug 修复执行 skill。分三种入口： 1. 用户直接报告 Bug → 定位根因 → 修复 → 产出 fix-report-*.md 或 fix-note-*.md（无需 CR 报告） 2. 有 x-cr 的 CR 报告 → 按报告逐条修复 → 回写同一份 `reports/cr/cr-report-*.md` 主档并产出修复记录 3. 有 x-verify / x-qa-gate fail 报告 → 按发现清单一次批量修复，产出逐条处置表，交回 gate 增量复审 触发方式："x-fix"、"修一下这个 bug"、"这个功能坏了"、 "按 CR 报告修复"、"把 CR 问题修了"。