CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when asked to "think bigger", "expand scope", "strategy review", "rethink this", or "is this ambitious enough".
Turn any installed skill (gstack, custom, third-party) into an ATO agent the user can summon into war-rooms. Reads a SKILL.md, extracts the persona, strips runtime boilerplate, and writes an agent file at `.claude/agents/<slug>.md` (project-scoped) or `~/.claude/agents/<slug>.md` (global). Prompts for a model roster (primary + 1-2 alts) so cross-family dispatch in war-rooms produces real disagreement. Companion to `ato-warroom` — that skill summons agents this skill creates. Use when asked "turn this skill into an agent", "register X as a war-room agent", or when scoping a new persona before a war-room runs.
Before any multi-step work with a stated goal — a feature, a bugfix spanning multiple files, a QA sweep, a doc draft + iterations, a multi-day investigation — create an ATO Mission instead of doing it via bare `ato dispatch` calls. A Mission persists the goal + the verifiable success criteria, lets the coordinator tick drive the work across days, captures every event in a structured audit trail (SQLite + markdown narrative), and integrates parallel agents' work via merge strategies. Complement to `ato-warroom` (the cross-family decision before you start) and `ato-review` (the post-code-diff review). Missions is where multi-step work LIVES; war-rooms are where decisions ABOUT it get made; reviews are where the resulting commits get vetted. Fires when: the work has more than one decision point, a verifiable end state, or runs across more than one session. Use it for any ATO development that doesn't fit in a single dispatch.
End-to-end pipeline that builds a new, playable Phaser 4 browser game from a natural-language idea (design, build, verify, iterate; Startup derives routing metadata). Trigger when the user asks to make, create, build, or generate a game, describes a game concept, or describes interactive mechanics, levels, or player actions, even without the word 'game'. Do NOT trigger for editing, debugging, or adding features to an existing game codebase, or for general questions about games.
Create or revise repository-aware social preview images for GitHub, package pages, launch posts, and link cards. Use when an agent needs to inspect a project, sharpen its short positioning, generate a branded 2:1 raster preview, explore color variants, adapt a supplied visual reference without copying it, or validate and save a social-card image non-destructively.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when: (1) creating a new SKILL.md, (2) initializing a skill directory, (3) packaging a .skill file, (4) improving or iterating on an existing skill, (5) understanding skill best practices and design patterns.
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Research 3–5 confirmed same-industry or cross-industry websites and translate their brand narrative, page architecture, art direction, and visual-system evidence into one reusable Visual Reference Brief. Use when strong references are scarce, a site needs brand-led or premium positioning, a page lacks a narrative spine, or a key module lacks a credible design precedent. Do not create page content, a Design System, UI directions, HTML, or a permanent brand gallery.
Create or audit a complete, concise, UI-ready website page content framework from verified business facts before visual design. Use to define page goals, customer decision flow, section order, realistic draft copy, content and evidence needs, CTAs, or page-family rules; do not use for visual design, HTML, SEO implementation, or platform code.
Create branded 试界TryWorld AI-knowledge videos in the fixed "Paper Algorithm" (纸上算法) style with HyperFrames. Input is a Chinese voiceover script and optional images; output is a 16:9 horizontal video with Azure YunxiNeural (真·云希) voiceover, word-synced captions, ink/paper animations and unified transitions, an always-visible anti-counterfeit red seal, plus horizontal (4:3) and vertical (3:4) cover images and platform-optimized titles for Bilibili/Douyin/Xiaohongshu. Brand values are theme-driven (themes/paper-algorithm.json by default; custom brand themes supported — see references/theme-guide.md). Use when the user provides an AI 科普/教程/内容解读/知识分享 script and wants a TryWorld/试界 branded video, asks for the 纸上算法/Paper Algorithm style, wants a consistent script-to-video pipeline with covers and titles, or wants this pipeline with their own brand theme.
Handles git workflow: creating branches, atomic commits with conventional prefixes, PR creation with structured summaries, keeping PR descriptions updated on follow-up pushes, and post-merge cleanup. Use when the user asks to commit, create or update a PR, push changes, address PR feedback, or says a PR was merged.
Install and verify the msmodeling development environment. Use when the user explicitly asks to install msmodeling dependencies, set up this repository, create `myenv` with `uv`, install this repository's `requirements.txt`, set project `PYTHONPATH`, or configure `HF_ENDPOINT`; if the user only says to install an environment, ask whether they mean msmodeling dependencies before proceeding.
kbo-cli 의 작업 브랜치에서 develop 으로 향하는 새 PR 을 만든다. 단순 push+gh pr create 가 아니라, /code-review 로 diff 검토 → biome check (format+lint) → tsc typecheck → bun build → bun test 5단계 검증을 통과시킨 뒤에 PR 을 올린다. PR 제목·본문은 모두 한국어 Angular 컨벤션 (CLAUDE.md 참조). 사용자가 "PR 올려줘", "pull request 만들어줘", "PR 생성해줘", "이거 PR 로 정리해줘", "리뷰 받게 올려줘" 같은 PR 생성 의도를 보이거나, 기능 작업이 끝나서 머지 흐름을 시작하려는 맥락이면 반드시 이 스킬을 쓴다. push 만 하고 끝나는 단순 push 요청과 다르다 — push 직전에 검증을 강제하는 게 핵심이다.
Slice a NowStack Mobile app's .agents/plan/PRD.md + .agents/plan/ARCHITECTURE.md into well-scoped, implementable task files under .agents/plan/tasks/, each an autonomous 1–3h vertical slice (Convex schema/function → Expo screen → wiring) with success criteria, dependencies, and verification commands. Use for "create tasks", "ns tasks", "break this into tickets", or as the third planning step after ns-prd and ns-architecture. Both docs must exist first.
Set up Cloudflare R2 image/file uploads for NowStack Mobile - create the bucket, get S3 credentials, set the R2_* env vars on the Convex deployment, and verify. Use for "set up image uploads", "configure R2", "Cloudflare storage", "enable file uploads", or "file uploads not working".