github-to-notion-sync

Meta-orchestrator that decomposes user goals into agent execution plans with model routing and dependency ordering, optionally pursuing them via Goal Mode with pursuing/paused/achieved/unmet/budget-limited lifecycle states. Maintains a persistent TODO backlog under state/todos/. Pipeline Mode auto-triggers for registered pipelines (report, persona, deep-research, research-report) and executes immediately. Use when: "jarvis", "자비스", "plan how to do X", "decompose this goal", "goal mode", "목표 모드", "pursue this until done", "jarvis goal", "jarvis plan", "자비스 계획", "자비스 목표", "long-running objective", "multi-turn goal", "멀티턴 목표", "장기 목표", "계획 세워줘", "jarvis todo", "자비스 TODO", "보고서 작성해줘", "리포트 만들어줘", "보고서 생성", "분석 보고서", "슬랙에 리포트 보고", "슬랙에 보고서 공유", "리서치해서 슬랙에 보고", "페르소나 분석", "관점 분석해줘", "관점 분석", "딥 리서치", "리서치해서 보고서로". Do NOT use for a single known skill (invoke directly), simple edits, or one-shot tasks. Do NOT use for daily pipeline (use today). Do NOT use for "딥 리서치" without "보고서" → use deep-research-pipeline.

End-to-end playbook to fine-tune and evaluate an LLM on ThakiCloud Metis (kubeflow-llm-training + vLLM serving on compute-h200). Covers served-model data generation, dataset→S3, TrainJob submission (with every admission gotcha), LoRA adapter serving for inference, and gate-based A/B eval. Use when "모델 학습시켜줘", "파인튜닝 돌려줘", "TrainJob 띄워줘", "학습 전후 평가/A/B", "데모 GPU로 학습", "fine-tune on the cluster", "train and evaluate", "serve the adapter and compare". General across models. Do NOT use for local/Colab training (use colab-unsloth-finetune) or serving-only ops (use demo-llm-inference-test).

Sync the #ai-platform-internal-qa Slack channel (demo.thakicloud.net QA reports) to a local corpus with full threads, filter out completion-tagged (완료/확인_완료) items, and dedup-check a new QA finding before posting it in the team's expert template. Use when "QA 이슈 올리기 전 중복 체크", "내부 QA 슬랙 싱크", "demo qa 중복 확인", "이 버그 이미 올라왔나", "internal-qa 채널", "check if this QA issue is a duplicate", "post QA finding". Do NOT use for GitHub issue dedup (use github-issue-dedupe), monitor/alert spam throttling (use slack-alert-dedup-cooldown), or general Slack posting (use scripts/slack_post_message.py).

Generate THAKI Design System (@thaki/tds) desktop-console UI from text / sketch / screenshot via a two-stage IR (UX-IR -> TDS-IR) with a deterministic compiler + validation gate + repair loop. Use when "TDS로 UI 생성", "화면 생성기", "디자인시스템 컴포넌트 트리 생성", "UI generator", "screenshot to TDS". Owns the TDS Component Registry (61 primitives) and the synthetic data engine for training a UI-gen model. Do NOT use for freehand React coding (use frontend-design) or Figma sync (use figma-to-tds).

Turn a known cartoon/comic character into a KakaoTalk-quality emoticon set (360x360 transparent, animated). Extracts a clean single-character reference, then generates held-cel sprite sheets with gpt-image-2 (body held, one part moves), splits/keys/stabilizes them, and compiles to KakaoTalk spec + GIF + PNG. Use when "이모티콘 만들어줘", "카카오 이모티콘", "캐릭터 이모티콘화", "움직이는 이모티콘", "emoticon set", "kakaotalk sticker set", "animate my character", "sprite emoticon". Do NOT use for one-off single stickers/messengers other than Kakao (use sticker-forge `stickerforge make`), plain image generation (use gpt-image-2), a pose sheet meant for dance/video (use pose-sheet-to-animation), or video (use video-producer).

Resume/continue development of 눈치맵 (nunchi-map) — a real-time local crowd/wait/on-site-photo app (대국민 눈치게임): enter a destination, see how crowded it is now, expected wait, and live '지금 뜨는 곳' ranking. Routes to the repos, explains architecture + how to run/verify, and lists the exact next gaps. Use when the user says "눈치맵", "누치맵", "nunchi-map", "대국민 눈치게임", "혼잡도 앱", "지금 뜨는 곳", or asks to continue/extend/deploy that app or its landing page. Do NOT use for ThakiCloud product repos (see [[thaki-platform-repos]]) or generic Go/React scaffolding unrelated to this app.

Evidence-grounded, leak-free skill-body evolution. Ports "Self-Harness" (arXiv:2606.09498) onto SKILL.md content: mines REAL execution-failure traces into clustered failure signatures (Weakness Mining), turns each cluster into a mechanism-targeted hermes mutation (Harness Proposal), and promotes variants through a leak-free non-regression gate with a sealed observe-only test split (Proposal Validation). Reuses hermes-skill-evolver as the variant engine — it does NOT replace it. Use when the user asks to "self-harness evolve", "evidence-grounded skill evolution", "evolve skill from real failures", "셀프하네스 진화", "실패 트레이스 기반 스킬 개선", "non-regression skill gate", "selfharness-evolve". Do NOT use for population/GEPA evolution on synthetic cases alone (use hermes-skill-evolver). Do NOT use for single-mutation quick fixes (use skill-autoimprove). Do NOT use for creating skills from scratch (use skill-creator). Do NOT use for the skill-ROUTER harness loop (use jarvis/runtime/SELF-HARNESS.md).

Translates ThakiCloud blog posts from Korean to English and Arabic and audits ko/en/ar parity so all three languages ship together in every batch. Use when adding or refreshing blog content that must ship in all three languages, translating a ko post to en/ar, or auditing language parity gaps. Korean+English triggers: 블로그 번역, 다국어 블로그, ko en ar 같이 배포, 트릴링구얼, 언어 패리티, blog translate, trilingual parity, i18n sync. Do NOT use for publish-cap/curation decisions (use tech-blog-manager), for build/push (use tech-blog-deploy), or for nightly quality scoring/rewriting (use tech-blog-evolve).

Nightly quality evaluation and systematic improvement of published ThakiCloud blog posts. Scores posts on measurable signals (length, images, sources, humanizer dashes, ko/en/ar parity), then improves the worst N with opus judgment (humanizer re-pass, gpt-image-2 images, source grounding, translation fill via blog-i18n-sync), commits and deploys. Use for the nightly blog-quality cron or when asked to evaluate, evolve, or improve published blog posts. Korean+English triggers: 블로그 평가, 블로그 진화, 블로그 품질 개선, 야간 블로그 진화, blog evolve, blog quality nightly, improve worst posts. Do NOT use for first-time content authoring/cap decisions (use tech-blog-manager), pure translation (use blog-i18n-sync), or build/push only (use tech-blog-deploy).

Curates the ThakiCloud tech blog content inventory: per-category policy, 250-posts/language publish cap, add-one/drop-one rule, and published-flag toggling. Use when managing blog categories, enforcing or inspecting the post cap, toggling published state, routing a twitter-selected topic to the blog. Korean+English triggers: 기술 블로그 관리, 블로그 카테고리 정리, 글 250개 상한, 배포 글 빼기, 블로그 발행 상태, blog cap, unpublish post, blog curation. Do NOT use for building/pushing the site (use tech-blog-deploy), translating posts to en/ar (use blog-i18n-sync), nightly quality scoring/rewriting (use tech-blog-evolve), or humanizing prose (use humanizer).

Download, load, explore, and benchmark The Well — Polymathic AI's 15TB collection of 16 diverse physics-simulation datasets (fluid dynamics, MHD, acoustic scattering, active matter, supernovae, reaction-diffusion) for training and evaluating spatiotemporal ML surrogate / physics-foundation models. Use when the user mentions "The Well", "polymathic", "the_well", "WellDataset", "물리 시뮬레이션 데이터셋", "PDE surrogate", "물리 서로게이트 모델", "물리 파운데이션 모델", "spatiotemporal simulation dataset", "neural PDE benchmark", "학습용 물리 시뮬레이션 데이터", or wants to pick/stream/download a Well dataset, wire it into a PyTorch DataLoader, visualize a simulation rollout, or benchmark a surrogate model. Do NOT use for generic HuggingFace dataset loading (use hf-datasets), non-physics ML data, or CFD solver authoring.

AI로 배너/썸네일 이미지를 생성한 뒤 Canva Magic Layers로 편집 가능한 레이어(배경·텍스트·오브젝트)로 분리하는 워크플로. 핵심은 "레이어가 깨끗하게 분리되도록" 이미지를 설계하는 프롬프트 엔지니어링. Use when "배너 만들어줘", "썸네일 편집 가능하게", "AI 이미지를 레이어로", "Canva Magic Layers", "editable layers", "flat 이미지 레이어 분리", "ChatGPT 배너 편집", "유튜브 썸네일 레이어", "banner to editable layers", "AI 이미지 재편집". 배너/썸네일/광고 크리에이티브를 만들고 나서 텍스트·오브젝트를 개별로 옮기거나 바꾸고 싶을 때. Do NOT use for 순수 이미지 생성만 (use gpt-image-2), PPT 슬라이드 번역 (use ppt-image-translator), 코드→UI 목업 (use image-to-code-skill), 배경만 제거 (imagemagick/rembg 직접).

영화/뮤직비디오급 스토리보드(分镜)를 이미지→영상 파이프라인으로 만드는 오케스트레이터. GPT Image 2로 시네마틱 스토리보드 그리드(또는 단일 프롬프트 풀-스토리)를 생성 → 샷별 프레임으로 분할 → 각 샷을 Seedance 2.0 image-to-video 프롬프트로 영상화 → 클립 합성. Use when "MV 스토리보드", "분경/分镜", "storyboard to video", "K-pop MV 생성", "영화 스토리보드 영상화", "GPT Image 2 스토리보드", "Seedance MV", "콜티 영상", "cinematic storyboard", "single-prompt film story". Do NOT use for 단일 이미지 생성만 (use gpt-image-2), Seedance 프롬프트 문법만 (use seedance2-skill / seedance-prompt-engineer), 소재 클립 편집만 (use video-producer).

Reads an uploaded photo with GPT Image 2 and produces a structured, multi-point annotated analysis image + text: face-feature/eyewear styling, or entertainment-only palm/face reading (관상/손금). Use when "얼굴 분석", "안경 추천", "관상", "손금", "손금 봐줘", "算命", "face feature analysis", "eyewear recommendation", "glasses guide", "palm reading", "physiognomy reading". Do NOT use for plain image generation/editing with no reading structure (use gpt-image-2), or PPT slide translation (use ppt-image-translator).

Remove signs of AI-generated writing from text and rewrite it to sound natural and human. Instructions are in English; OUTPUT stays in the input language (Korean by default for this repo). Based on Wikipedia's "Signs of AI writing" (33 patterns) plus a Korean-specific AI-tell layer (번역투, 과잉 의미부여, 3단 나열, 이중피동, AI 빈출 어휘, 쉼표 남용, 한국어 상투어). Use when editing/reviewing generated copy before publishing — reports, threads, Notion articles, decks, emails. Triggers: "AI 흔적 제거", "사람 글처럼", "휴머나이즈", "AI 티 빼줘", "humanize", "de-slop", "remove AI writing". Do NOT use for Chinese text (use humanizer-zh) or for honorific/格式 tone fixes alone (use korean-tone-reviewer — chain after this).

Turns a natural-language character description into a game-ready 3D asset via a 3-stage pipeline: reference/turnaround image generation, image-to-3D mesh conversion, and game-engine import prep. Use when "이미지를 3D로", "3D 게임 에셋", "캐릭터 3D 모델", "image to 3D", "game asset", "3D character", "turnaround sheet", "게임 캐릭터 모델링", "3D 모델 생성". Do NOT use for pure 2D image generation (use gpt-image-2), 3D icon retexture (use gpt-image-2 retexture workflow), or video generation (use cinematic-storyboard-to-video).

Generate an NxM (default 4x4) character pose/movement reference sheet with GPT-Image-2, slice it into per-pose frames, and write a Seedance 2.0 prompt that animates the pose sequence into a dance/character animation. Use when "포즈 시트", "무브먼트 시트", "포즈 레퍼런스 시트", "댄스 애니메이션", "캐릭터 애니메이션", "4x4 포즈", "pose sheet", "movement sheet", "dance animation", "character animation from poses", "pose grid to video". Do NOT use for multi-shot film/cinematic storyboards (use cinematic-storyboard-to-video), plain image generation with no animation goal (use gpt-image-2 directly), or general Seedance prompt syntax unrelated to pose sheets (use seedance2-skill / seedance-prompt-engineer).

Reverse-engineers the structure (shots, timing, hook, on-screen text, pacing) of a short-form video URL and rebuilds an original equivalent with generated subject images and Hyperframes. Use when "릴스 재현", "숏폼 영상 재제작", "릴스 URL 분석", "reel remake", "short-form recreate", "instagram reel to video", "Hyperframes 영상". Do NOT use for raw clip trimming/editing (use video-producer), pure image generation with no video output (use gpt-image-2), or building a video from a storyboard you already wrote with no source reel (use cinematic-storyboard-to-video).

단일 이미지를 세계관(피사체·배경·분위기·암시된 서사·개연성 있는 모션)으로 해석한 뒤 그 해석에서 Seedance 2.0 image-to-video 프롬프트를 자동 생성한다. Use when "이미지로 영상 프롬프트 자동 생성", "세계관 해석", "이미지 해석 Seedance", "사진 한 장으로 브이로그 영상", "image to video prompt", "worldview interpretation", "Gemini 이미지 해석 영상". Do NOT use for 손으로 직접 쓴 다중 샷 스토리보드(use cinematic-storyboard-to-video), Seedance @ 참조 문법·프롬프트 골격 자체(use seedance2-skill / seedance-prompt-engineer).

Use when setting up this repo on a new or freshly wiped macOS machine, rebuilding the Python 한국어 트리거: 새 맥북 세팅, 환경 재구축, venv 재생성, 서브모듈 초기화, 심링크 복구, 헤드리스 인증, 부트스트랩. .venv, fixing broken external skill symlinks, re-running scripts/env_bootstrap.sh, restoring headless claude auth (setup-token / headless.env), initializing git submodules, recreating the isolated TTS/STT venvs, or registering a new machine in machine_registry.json. Korean triggers: 새 맥북 세팅, 환경 구축, 환경 재구축, venv 재생성, 서브모듈 초기화, 심링크 복구, 헤드리스 인증, 환경 패리티, 부트스트랩. English triggers: new machine setup, environment rebuild, bootstrap, env parity, venv rebuild, submodule init, headless auth, CLI install. Do NOT use for day-2 fleet operation, launchd lifecycle, or runner anatomy (use aps-run-and-operate); do NOT use for config axes like model policy, hooks wiring, or plists (use aps-config-and-flags); do NOT use for diagnosing why a job fails (use aps-debugging-playbook).

Analyze recent git commits, group them into work units, create GitHub issues with full ThakiCloud Project #5 metadata (Status, Priority, Size, Estimate, Sprint, Start/End date), and verify the result. Use when the user asks to "이슈로 등록", "commit-to-issue", "이번주 작업 이슈 만들어줘", "이번 작업을 이슈로 남겨줘", "회고용 이슈 생성", "커밋을 이슈로", "작업 이슈 등록", "깃허브 이슈로 남겨줘", "project #5에 등록", "오늘 작업 이슈 만들어", or any retrospective issue creation from commits. Do NOT use for creating PRs (use release-ship), single ad-hoc issue creation without Project #5 linking (use `gh issue create` directly), or modifying existing issues.

N-repo bidirectional sync of agent assets (commands, skills, rules, agents) under BOTH .cursor/ and .claude/ across all 7 managed repositories via research hub. (Name is historical — it syncs .claude/ too.)

End-of-day shipping pipeline — claude-sync, domain-split commits, push, ISSUE creation linked to ThakiCloud Project #5, daily skill digest, and Slack summary across all managed repos. Use when the user types "EOD ship", "퇴근 정리", "EOD 정리", "오늘 작업 마무리", or runs `/eod`. Do NOT use for morning-only sync (use sod-ship), single-repo ship (use release-ship), or WIP commits without push (use domain-commit).

Diagnose git divergence across the 7 managed ~/thaki repos and emit a SAFE reconciliation plan (read-only, never force-pushes). Use when sod-ship/eod-ship reports push rejected, repos are ahead/behind/diverged, "359/359 발산", history rewrite suspected, "리포 동기화 깨졌어", fleet sync broken. Do NOT use for normal commit/push (use sod-ship) or asset propagation (use claude-sync/cursor-sync).

Grilling session that challenges your plan against the existing domain model. Sharpens terminology and updates CONTEXT.md and ADRs inline. Use when user says "grill with docs", "challenge my plan", "domain review", or wants to refine a plan against existing documentation.

Summarize the current conversation into a compact handoff document for another agent or a future session. Use when the user says "handoff", "summarize for another agent", "write a handoff doc", "pass this to another agent", or when a conversation has reached a natural break point and needs to be resumed later.

Every morning (08:00 KST, launchd) scrape HuggingNews (huggingnews.com) for the latest day's top AI news, Korean-localize it, dedup across mornings, and post to Slack #deep-research-trending as a ranked main message + one thread reply per story (핵심 + ThakiCloud 관점, Notion-style). Use when "허깅페이스 아침 뉴스", "HuggingNews 다이제스트", "deep-research-trending 뉴스 자동", HF morning news to Slack. Do NOT use for HF trending papers/models radar (use hf-trending-intelligence), Gmail-sourced Bespin news (use bespin-news-digest), or Twitter timeline (use twitter-timeline-to-slack).

Author, inspect, transform, and validate an OpenCut (classic) project as DATA — the TProject timeline JSON (scenes → tracks → elements, integer-tick MediaTime, canvas/fps settings). Use when the task is "build an OpenCut project/timeline programmatically", "generate an .opencut timeline", "edit OpenCut project JSON", "OpenCut timeline schema", "convert a shot list into an OpenCut timeline", "validate an OpenCut project file", "오픈컷 프로젝트/타임라인 JSON 만들어/편집/검증", "타임라인을 데이터로 생성". This is the gap the video fleet does not cover — it manipulates OpenCut's own project graph, it does not render video. Do NOT use to render/encode/export actual video files (use ffmpeg-toolkit / hyperframes / video-producer), to develop the OpenCut rewrite repo (use opencut-dev), or for non-OpenCut editors (Premiere/FCPXML/CapCut).

Lightweight shipping pipeline: domain-split commits, git push, and PR creation/update in one flow. Use when the user asks to "release-ship", "commit and push", "commit and PR", "push and create PR", "커밋하고 PR", "커밋하고 푸시", "ship without review", or wants to go from uncommitted changes to an open PR without code review. Do NOT use for review-included shipping (use ship), full release validation pipeline (use release-commander), domain-split commits only without push/PR (use domain-commit), or single-file trivial commits.

Start-of-day git sync — commit, push, pull all 5 projects, update submodules, then claude-sync.

Routes a video-generation request to the right LOCAL video skill and chains them end-to-end (decompose -> route -> chain -> render -> verify). Use when the user asks to "make a video", "create a video", "영상 만들어줘", "영상 제작", "비디오 생성", motion graphics, explainer/demo video, math animation, multi-scene video, or to edit raw footage into a finished clip. Picks among hyperframes / remotion-motion-forge / manim-video / video-use / openmontage / ffmpeg-toolkit by intent, offloads heavy renders to subagents, and verifies the output MP4. Do NOT use when the user names a single tool ("manim으로", "remotion으로" -> call that skill directly), for TTS/STT only (use [[tts-generation]]/[[stt-generation]]), or for image generation (use gpt-image-2/muapi).

When the user wants to write, generate, iterate, or scale ad COPY — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative testing,' 'ad performance optimization,' 'write me some ads,' 'Facebook ad copy,' 'Google ad headlines,' 'LinkedIn ad text,' 'static ads,' 'static ad concepts,' 'ad templates,' 'iMessage ad,' 'chat reveal ad,' 'text message ad,' 'fake DM ad,' 'ChatGPT ad,' 'Apple Notes ad,' 'creative strategy,' 'creative roadmap,' 'creative retro,' 'hook writing,' 'motion video ad,' 'faceless video ad,' 'animated explainer ad,' 'motion collage ad,' or 'I need more ad variations.' Use this whenever someone needs to produce ad copy at scale or iterate on existing ads. For campaign strategy and targeting, see ads. For landing page copy, see copywriting. For ad IMAGE/visual generation (gpt-image-2 render pipeline), see

Develop or contribute to the OpenCut ground-up rewrite monorepo (github.com/OpenCut-app/OpenCut) — a moon + proto + bun workspace with a TanStack Start web app, an Elysia/Cloudflare Worker API, and a Rust/GPUI desktop app, plus a shared rust/ core. Use when the task is "run/build/dev OpenCut", "add a route/component/API endpoint to OpenCut", "OpenCut monorepo setup", "moon run web:dev", "proto use", "why won't OpenCut build", "OpenCut 개발/기여", "오픈컷 빌드/실행", "오픈컷 모노레포". Do NOT use for the OpenCut classic editor's project/timeline data format (use opencut-project), for generic video editing or rendering (use video-producer / ffmpeg-toolkit / hyperframes), or for generic codebase spelunking (use codebase-archaeologist).

Generates spring-physics UI motion — micro-interactions with weight — and ships each effect three ways: CSS, React, and a copy-paste AI-prompt, with a live stiffness/damping readout. Owns a deterministic spring→cubic-bezier engine + a library of ~19 verified recipes (card resize, magnetic button, status pill, stagger, marquee, count-up, scramble…). Use when the user wants "spring animation", "bouncy/weighted UI motion", "micro-interaction", "reproduce a Kinetics-style effect", CSS/React motion from stiffness/damping, 스프링 모션, 물리 기반 인터랙션, 마이크로 인터랙션, 통통 튀는 UI 애니메이션. Do NOT use for timeline choreography or scroll-scrubbing (use gsap), pure decorative keyframes with no spring feel (use css-animations), 3D/WebGL (use three), Lottie playback (use lottie), or video-render motion (use hyperframes).

Scaffold a new 100% client-side static web tool from the agent-webtool-template skeleton, implement its pure testable core + independent audit + tests, verify the gates locally, then create the GitHub repo, push, and enable Pages. Use when the user wants a free browser-based diagnostic / calculator / analyzer shipped as its own repo ("정적 웹 도구 만들어줘", "GitHub Pages 도구", "클라이언트 사이드 계산기/분석기", "이 아이디어로 새 웹 도구 repo", "템플릿으로 새 도구"). Do NOT use for features inside an existing app, server-backed tools, or non-web deliverables.

Analyze the VIDEO inside an X/Twitter post — fetch it, transcribe the speech locally (Qwen3-ASR), and produce a chapter-anchored content summary / script. Use when the user shares a tweet/X video and asks "이 영상 분석/스크립트 뽑아줘", "무슨 내용인지 정리", "transcribe this tweet video", "summarize the video in this X post", or drops an x.com/twitter.com/status link pointing at a video. Handles long videos (1h+) by transcribing a window at each tweet-parsed chapter instead of the whole runtime. Do NOT use for: text-only tweets or articles (use x-to-slack / x-to-notion), non-tweet video files or YouTube (use video-to-text / transcribee), or timeline scraping (use twitter-timeline-to-slack).

Each night, turns today's collected tweets (a signal of what tech people care about now) into 3 STANDALONE PUBLIC-GOOD TOOL project ideas for a tech audience valuable to ThakiCloud — each buildable by composing our skills/harness, the way branded-deck became the public kr-brand-decks repo — and reports them to Slack #효정-할일. Use when "공익 도구 아이디어", "트윗에서 도구 아이디어", "daily tool ideas", or the scheduled com.thaki.tool-ideas fire. NOT product promotion — no ThakiCloud ads. Do NOT use to collect tweets (twitter-timeline-to-slack) or to actually build a chosen tool (that is a per-project repo scaffold, e.g. llm-selfhost-calculator).

Measures and enforces this repo's progress toward the "AI-Native Product Factory" vision — turning the operator harness into an org product factory. Scores the harness against the 5-principle / 5-org vision (0-5, deterministic), runs the Specification-First gate (Spec §→acceptance-criteria→test coverage), maintains the standing spec-registry convention, and renders the gap-analysis + conversion roadmap. Use when "AI-Native 성숙도", "AI-Native factory", "조직 제품공장 갭", "제품공장 전환", "spec 게이트", "executable spec", "성숙도 측정/스코어카드", "maturity scorecard", "advisory를 gating으로 전환". Do NOT use for harness fleet reliability/cost measurement (use aps-diagnostics-and-tooling), running one feature through the build chain (use feature-factory), or general spec authoring (use spec-driven-development / to-prd).

Reverse-lookup glossary that turns a vague description of a web animation/motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…" or describes a motion effect without knowing its name and wants the right word to prompt an AI/designer (모션 용어 찾기, 이 효과 이름이 뭐야, 애니메이션 용어). Do NOT use for designing or building an animation (use emil-design-eng / apple-design) or reviewing motion code (use review-animations).

Apple's approach to interface design and fluid, physical motion, translated for the web (CSS, Pointer Events, rAF, spring libraries). Use when building or refining gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials/depth, typography (optical sizing, tracking, leading), reduced-motion (애플 스타일 UI, 스프링 모션, 제스처, 유동적 인터페이스). Do NOT use for naming an effect (use animation-vocabulary), reviewing motion code (use review-animations), or general layout/WCAG (use make-interfaces-feel-better / fixing-accessibility).