Coding & Development

Teaches, practices, and assesses skills through first principles, active retrieval, and evidence-based feedback. Use when the learner asks to learn, practice, be quizzed, build a curriculum, create or resume a course, or assess a capability.

How to use the hwip_* MCP tools — notify, ask, send files and clipboard text to the user's devices, pass a message to another agent session, and list or read the agent sessions on this machine. The Stop hook already pushes on completion.

Run work as an orchestrator. Split a goal into tickets, give each ticket to a helper agent in its own worktree, verify each result yourself, and coordinate with peer orchestrators. Use when the human asks you to orchestrate, to delegate or coordinate agents, names a peer orchestrator, gives one goal to several agents, asks which orchestrators a project has, asks for a new orchestrator, or asks you to resume as one.

解析完整的 51 单片机 C51 程序，生成适合高职课堂的中文代码解释与教学信息图，包含原样源码、关键语句、硬件效果和执行流程。适用于 LED、按键、蜂鸣器、数码管等 C51 教学可视化；也支持只做代码解析或生成制图提示词。不用于普通前端界面、通用编程教程或默认制作 PPTX。

人因小管家部落格文章撰寫技能。將原始內容轉換為符合 V8 主題風格的 clean HTML，包含 Noah 角色元件、JSON-LD Article Schema 與 AI SEO 優化。

Find queries where two or more of your own pages split Google impressions, from a Google Search Console query+page export, and rank them HIGH/MEDIUM/LOW. Use when the user asks about keyword cannibalization, competing pages, pages fighting for the same keyword, or uploads a GSC export with query and page columns. Offline, no API keys.

Group a keyword list into topic clusters with a pillar keyword, majority search intent and suggested page type, so one page targets each cluster. Use when the user pastes keywords or a keyword CSV and asks to cluster, group, organise or map keywords to pages, or plan a content hub. Offline, no API keys.

Compare two Google Search Console page exports (an earlier period and a recent one) and flag pages that are LOST, DECLINING, in STRIKING_DISTANCE, GROWING or STABLE, ranked by clicks lost. Use when the user asks which pages lost traffic, about content decay, what to refresh or update first, or uploads two GSC page exports. Offline, no API keys.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".

Ask which skill or flow fits your situation. A router over the skills in this repo.

Готовит публикацию готового ролика через Buffer MCP — текст поста под каждую площадку, черновик в Buffer; публикует или ставит в расписание только после явного «да» пользователя. Запускай на «опубликуй», «сделай пост», «закинь в Buffer».

Первичная настройка проекта под нового пользователя — проверка окружения и подробное интервью (кто ты; ~10 рилсов-референсов и разбор вкуса; расшифровка; подключение сервисов с проверкой доступа; палитра; шрифты; субтитры, графика, движение, звук), с показом вариантов готовыми кадрами; запись harness.config.json, brand-kit.md, editing-taste.md, exemplars.md. Запускай, когда в harness.config.json "configured" false, или когда пользователь просит перенастроить проект / сменить стиль / заново разобрать референсы.

This skill should be used when the user asks to "make this animation feel natural", "fix motion that feels stiff/floaty/cheap", "my animation looks robotic", "choose an easing curve", "how do I use the Graph Editor", "add overshoot or bounce", "Easy Ease isn't enough", "make snappy motion", "pick a duration for this transition", "stagger a list animation", "sync animation to a beat", or "review motion for good timing". It is the tech-agnostic foundation for deciding how something should move.

解读任意学科课程的语音识别字幕，在答疑、总结、教学或笔记任务中，结合课程资料、前后文和必要的公开检索辨认误识别的专业术语、缩写与符号。默认在阅读时校验，不生成整份校订稿；每门新课程询问是否建立项目独立术语表。适用于 TXT、SRT、VTT 及逐字稿，不负责录播网站提取或音视频批量转写。

Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".

Vet a creator before a sponsorship or partnership by pulling their public TikTok, Instagram and YouTube profiles, recent posts, and transcripts of what they actually said, then summarising audience size, posting rhythm, engagement, past sponsors and any brand-safety flags. Uses the Captapi API (MCP tools or REST with CAPTAPI_API_KEY). Shows a credit estimate first and cites the endpoint behind every claim. Use when someone asks to vet, audit, shortlist or background-check an influencer or creator.

Track what competitors are advertising across the Meta, Google, LinkedIn and TikTok public ad libraries and report what changed since last week — new ads, ads that stopped running, and new creative angles. Uses the Captapi API (MCP tools or REST with CAPTAPI_API_KEY). Shows a credit estimate before running, keeps a snapshot file between runs, and cites the endpoint behind every claim. Use when someone asks to monitor competitor ads, compare ad activity week over week, or audit a brand's paid creative.

Diagnose bugs and failures through reproduction, connected-flow evidence, and root-cause testing; recommend or apply the smallest authorized fix. Also handles explicit behavior-preserving refactoring and structural repair. Use for broken behavior, unexplained errors, or requested refactors; broad quality review and release verification belong to qa-tester.

Produce a weekly digest of what competitors published on TikTok, Instagram, YouTube, X, Threads, LinkedIn and Facebook — their latest posts, which ones outperformed, and the topics and formats they are leaning into. Uses the Captapi API (MCP tools or REST with CAPTAPI_API_KEY). Shows a credit estimate first and cites the endpoint behind every claim. Use when someone asks to monitor competitor social content, benchmark posting activity, or find what is working for rival brands.

Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems. Use when implementing auth systems, securing APIs, or debugging security issues.

Guide backend audit. Use when implementing or reviewing production readiness, security, reliability, testing, release configuration, and prioritized findings in backend applications.

从现有代码库生成或更新可追溯的项目逻辑地图，连接产品能力、页面、动作、流程、数据、规则和测试，并按需交付交互式 HTML。适用于项目全貌梳理、维护交接和改动影响分析；不用于凭空设计尚未实现的系统或通用思维导图。

Guide backend authentication. Use when implementing or reviewing sign-in, identity verification, session or token lifecycle, account recovery, and authorization boundaries in backend applications.

Searches, installs, updates, and lists skills from the Antigravity Skill Vault. Use when choosing or managing workspace or global skills through the npm CLI.