Explorar skills

Audits SwiftData/Core Data model layer for field completeness, serialization gaps, relationship integrity, semantic ambiguity, dead fields, and migration safety. Finds model-layer bugs that manifest as workflow bugs. Triggers: "audit models", "model radar", "/data-model-radar".

Forms have three layers of guidance: helper text below the input explains what to enter, placeholder shows the expected format, and validation confirms correctness. Real-time validation for complex inputs. Submit enables only when the form is valid. Use when designing or reviewing any form, input field, or data entry UI.

Use Chanjing TTS API to convert text to speech (list voices, create tasks, poll, download from returned URLs).

Push a local .workflow.ts to n8n, verify remote state, and live-test (test URL by default; `--activate --prod` runs production test). Side-effecting — only invoked explicitly via `/deploy`.

在跨多文件批改、术语统一、整篇论文润色、章节重写等可能改动专业术语 / 缩写 / 人名 / 概念命名的操作之前， 必须先显式列出"保护术语清单"，让用户确认哪些词不得被同义替换或改写，再开始执行。 Use when 用户要求跨章节修改、批量替换、整篇润色、术语统一、规范化、 或对出现专业术语 / 缩写 / 模型名 / 算法名 / 自定义概念的段落做改写。

Review a pull request or analyze local changes before submitting. Checks the diff against what the ticket asked for, then for correctness bugs, and reports only findings that survive a concrete failure scenario and verification against the file. Findings post as inline suggestions, and silence is a valid result. Invoke when the user gives a PR number, asks for a code review, wants changes analyzed

Use when integrating, porting, configuring, or debugging Zephyr RTOS, west builds, devicetree overlays, Kconfig, drivers, threads, logging, networking, or board support

Automatically generate comprehensive QA test plans when user mentions testing requirements, QA needs, or asks what should be tested. Analyzes code changes and features to create structured test scenarios. Invoke when user mentions "test plan", "QA", "what to test", "testing requirements", or "test scenarios".

在把任何成果交付给用户（"改完了"、"已完成"、"可以发给导师"、"可以提交"）之前， 必须运行一份硬检查清单：术语一致性、引用完整性、数据正确性、图表编号、 内部交叉引用、字数 / 格式合规、未完成 todo 残留、AIGC pattern（涉及文段改写时跑 chinese-de-aigc 五维自评）、 论证一致性（涉及核心声明改动时跑 paper-logical-consistency 复核）、 改动概要——任意一项 fail 都不能宣告完成。 Use when 你即将说「改完了 / 完成了 / 可以提交了 / 可以发给导师了」、 或用户问「是不是可以了」「还有什么要检查的吗」。

Generate and save a complete SEO report to disk. Use when user says "SEO report", "generate report", "monthly report", "weekly report", "audit report", "competitor report", "save report", "export SEO data", "create SEO summary", "export my SEO data", "save Ahrefs report", "download SEO report". Requires report type: monthly | weekly | audit | competitor.

Close out a completed session with status updates, optional local commit, extraction, and final readiness checks. Trigger on /wrapup, wrap up, finish session, or close out.

Save the current Codex or shared ARIA session transcript snapshot to the knowledge intake for later audit. Trigger on /snapshot, snapshot the session, or save this conversation.