Coding & Development

マネージャー（このセッション）・作業者（team-worker）・レビュー役（team-reviewer）の3役でタスクを進める

Drill for a test or quiz instead of lecturing. Use when Srijan says "drill me", "quiz me", "study for", "test on", "help me review", or names a unit or chapter he has a test on. Builds a question bank from his notes, Canvas, or the textbook section, asks one question at a time, tracks misses, and loops back on them until they stick. Also use to make a one page cheat sheet after a drill.

問「我現在這個狀況該用哪個 skill 或流程？」：這個 skill 集合的總導覽，依你描述的狀況指出該用哪一個。

ทำคลิปเล่าประวัติศาสตร์บนแผนที่แนวตั้ง 9:16 ภาษาไทย ~1 นาที ด้วยโปรเจค motion-history-starter — วิจัย เขียนบทแบบเล่าเรื่อง ตรวจข้อเท็จจริงอิสระ สร้างแผนที่ ภาพ เสียง และเรนเดอร์ ใช้เมื่อผู้ใช้พูดว่า "ทำคลิปประวัติศาสตร์", "เล่าประวัติศาสตร์บนแผนที่", "motion history" หรือให้หัวข้อประวัติศาสตร์ที่มีสถานที่/เส้นทาง

Audits a skill folder for format, structure, static security, and supply-chain issues. Use when someone says “audit this skill”, “check my SKILL.md”, “is this skill safe to publish”, “lint skill”, or “prepare for marketplace”.

BPA competition prep for the 505 Sports Media Marketing Team event. Use when Srijan says "bpa", "judge me", "practice the pitch", "q and a practice", "mock judge", or asks for help with the BPA plan, slides, numbers, or team roles. Reads the official event guidelines first, then either builds the deliverable with him or runs a live mock judging round with hard follow up questions.

Skill for converting an installed Firebase Extension (or extension source) into a standalone Cloud Functions for Firebase codebase or publishable npm package, including V1 to V2 trigger upgrades, lifecycle hooks, and declarative security

Make per-episode podcast graphics from the show's Apple Motion templates (main title card, citation lower thirds) and place them in Final Cut Pro via FCPXML. Use when asked for a title card, citation/lower third, on-screen text, or anything involving .motn/.moti files or Motion.

>- Integrates Firebase AI Logic (formerly Vertex AI for Firebase) into mobile and web apps (Android, iOS, Web, and Flutter) to call Gemini models from client code. Use when provisioning or initializing Firebase AI Logic, or adding Gemini features to an app: text generation, multimodal input, chat, streaming, structured output, hybrid on-device inference, App Check protection, or switching models with Remote Config.

>- Deploys and manages full-stack web applications (Next.js, Angular) with Server-Side Rendering (SSR) using Firebase App Hosting. Use when deploying Next.js/Angular apps, configuring apphosting.yaml or firebase.json apphosting blocks, managing secrets, setting up GitHub CI/CD, or configuring Blaze billing requirements. Don't use for classic static web hosting, Auth, Firestore, Crashlytics, or Xcode.

Score the vibe coding practice behind the current Git branch

Разобрать одну воронку Bitrix24 через BI Connector и получить MD/PDF с максимум пятью основными местами ухода в провал, причинами и менеджерами. Используй для анализа потерь лидов или одной воронки сделок; не для объединения воронок, денежных KPI или рекомендаций по продажам.

Runs UptimeLens on-call and escalation operations through the UptimeLens MCP server — find who is currently on call, acknowledge or snooze active escalation pages, cover a shift by overriding an on-call rotation, and inspect escalation runs and policies. Use when the user mentions on-call, who is on call, acknowledging, resolving, closing, taking or silencing an alert or page, snoozing a page, escalation runs, covering or swapping a shift, or overriding a rotation.

>- Proactively structure substantial human-facing answers while composing them: explanations, comparisons, plans, and reports. First decide whether prose, a list, a table, or a visual best serves the reader's question and environment. Use when explaining a process, comparing options, showing relationships or trends, or preparing a document for people. Routine confirmations and brief progress updates stay concise; machine-facing files keep their required format.

Review or replace React useEffect calls, or enforce a no-direct-effect policy. Use for effect implementation, refactoring, or lint policy; excludes unrelated React work and non-React effect systems.

Adopt or check mandatory personal-project policy through explicit selection and native Claude/Codex instructions.

Mandatory current-solution and proportionate-engineering rules for explicitly adopted personal projects.

>- Names and rebrands an app clone so it is the user's own: name candidates with the trademark, domain, store and handle checks to run, a new palette checked for contrast, a logo brief, a voice guide, and a sweep tool that finds anything of the original left in the codebase. Use when the user says "name my app", "rebrand the clone", "make it mine", "pick a name and colours", "logo brief", "brand voice", "check for leftovers", or after /replica-entrepreneur. Always runs before /replica-launch.

Check what an MCP server declares before an agent connects to it — prompt-injection text in tool descriptions, invisible Unicode (including the tag block that encodes printable ASCII at zero width), look-alike and duplicate tool names, framework-name collisions and unconstrained shell sinks. Use when reviewing an MCP server, installing an MCP integration, vetting a third-party tool provider, or when someone asks "is this MCP server safe" or "audit these tool definitions".

Set up, modify, or troubleshoot reproducible development environments built with Nix flakes. Use this skill whenever a user mentions flake.nix, devShells, nix develop, shell.nix migration, nixpkgs unstable, devenv, direnv, reproducible project tooling, or wants to add development dependencies with Nix. It supports language-agnostic projects and requires explicit approval before edits and again before validation commands are run.

Use when lasting learnings from the current session should be recorded in agent instruction files - AGENTS.md, CLAUDE.md, or the user's global instructions - such as pitfalls hit, mistakes corrected, conventions found, or commands that finally worked, whatever the conversation language. Proposes minimal, deduplicated edits per file and applies only the approved ones. Not for general memory, a full audit of instruction files, or improvement requests for skills.

Показывает стили строки состояния на примере или включает один из них (full, compact, bars, minimal) в настройках пользователя или проекта.

Explain a file, directory, or function to someone new to this codebase.

Review code changes for correctness, readability, tests, and obvious security problems. Use when the user asks for a review of their changes, a diff, or a branch, or before they open a merge request.