Run any Skill in Manus with one click

tds-ui-generator

Stars0

Forks0

UpdatedJuly 14, 2026 at 08:08

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).

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

sylvanus4

sylvanus4/github-to-notion-sync

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Web DevelopersComputer and Mathematical Occupations·SOC 15-1254

File Explorer

100 files

SKILL.md

readonly

name

tds-ui-generator

description

TDS UI Generator

일반 UX 표현은 보존하고 TDS realization만 강학습하는 데스크톱 콘솔 UI 생성기. 모델은 제한된 IR만 생성하고 코드·검증·집계는 결정론 하네스가 소유한다([[sonnet-format-determinism]]· [[thin-harness-fat-skills]]·[[docx-readability]] 동형). 포맷 결정론은 이 원칙을 따른다.

파이프라인

입력(text/sketch/screenshot) → UX-IR(디자인시스템 독립) → TDS-IR(registry-검증)
  → validate_ir.py(게이트) → compile_tds_ir.py(TSX) → 렌더/critic → repair 루프

산출물 (이 스킬이 소유)

파일	역할
`schema/ux-ir.schema.json`	의도 표현(화면목적/정보구조/액션/역할) + novelty/density 컨트롤
`schema/tds-ir.schema.json`	컴포넌트 realization 트리(enum은 registry가 런타임 검증)
`schema/registry.json`	TDS Component Registry — `@thaki/tds` 61 primitive의 props/slots/variant/enum + uxRoleToComponent
`scripts/validate_ir.py`	결정론 게이트: 컴포넌트 존재·prop enum·slot 호환·interaction-graph(dead touch, 중복 CTA)
`scripts/compile_tds_ir.py`	TDS-IR → React TSX(`@thaki/tds` import). 같은 IR → byte-identical
`scripts/grammar_gen.py`	확률 그래머 합성 화면 생성기(무작위 조합 금지)
`scripts/build_dataset.py`	게이트 통과 화면 → 다태스크 SFT + hard-negative preference pair

사용

PY=.venv/bin/python
# 1) 합성 화면 생성
$PY scripts/grammar_gen.py --n 100 --registry schema/registry.json --out-dir samples/raw
# 2) 게이트(수용 데이터만 학습에 사용)
$PY scripts/validate_ir.py --registry schema/registry.json --ir <tds-ir.json> --json
# 3) TSX 컴파일
$PY scripts/compile_tds_ir.py --ir <tds-ir.json> --out Screen.tsx
# 4) 학습 데이터셋(5 태스크 + DPO)
$PY scripts/build_dataset.py --in-dir samples/raw --registry schema/registry.json --out-dir samples/dataset --cap 100

불변식

모델은 JSX/코드를 직접 쓰지 않는다 — 검증된 TDS-IR만. 코드는 컴파일러 소유.
게이트 통과분만 학습 데이터(data engine > data volume). status=valid 아니면 drop 또는 repair.
registry는 retrieval 소스 — 현재 props를 weights에 암기시키지 않는다(TDS 버전 변동 대비).
학습: 일반 UX 추론은 LoRA/frozen 보존, TDS realization adapter만 강학습([[subagent-model-routing]]).
중국 teacher API는 비-TDS UX 추론에만(사내 IP 보호, 2026-07-14 결정).

데이터 태스크 (registry 통과 화면당 파생)

text→UX-IR · text→TDS-IR · screenshot→TDS-IR · edit→JSON Patch · invalid→repair · TDS-IR→NL설명 · DPO(good>corrupt).

Registry 재생성 (tds_ssot 갱신 시)

ThakiCloud/tds_ssot 클론 → props/slots/enum 재추출 → schema/registry.json 갱신 → uxRoleToComponent 재매핑. 데스크톱 콘솔 표면(Table/Drawer/Modal/CatalogCard/PageShell).

More from this repository

same repository

jarvis

sylvanus4/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.

2026-07-140

metis-finetune-eval

sylvanus4/github-to-notion-sync

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).

2026-07-140

qa-issue-dedup-poster

sylvanus4/github-to-notion-sync

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).

2026-07-140

kakao-emoticon-forge

sylvanus4/github-to-notion-sync

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).

2026-07-140

nunchi-map

sylvanus4/github-to-notion-sync

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.

2026-07-140

selfharness-evolve

sylvanus4/github-to-notion-sync

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).

2026-07-130

name

tds-ui-generator

description

TDS UI Generator

파이프라인

입력(text/sketch/screenshot) → UX-IR(디자인시스템 독립) → TDS-IR(registry-검증)
  → validate_ir.py(게이트) → compile_tds_ir.py(TSX) → 렌더/critic → repair 루프

산출물 (이 스킬이 소유)

파일	역할
`schema/ux-ir.schema.json`	의도 표현(화면목적/정보구조/액션/역할) + novelty/density 컨트롤
`schema/tds-ir.schema.json`	컴포넌트 realization 트리(enum은 registry가 런타임 검증)
`schema/registry.json`	TDS Component Registry — `@thaki/tds` 61 primitive의 props/slots/variant/enum + uxRoleToComponent
`scripts/validate_ir.py`	결정론 게이트: 컴포넌트 존재·prop enum·slot 호환·interaction-graph(dead touch, 중복 CTA)
`scripts/compile_tds_ir.py`	TDS-IR → React TSX(`@thaki/tds` import). 같은 IR → byte-identical
`scripts/grammar_gen.py`	확률 그래머 합성 화면 생성기(무작위 조합 금지)
`scripts/build_dataset.py`	게이트 통과 화면 → 다태스크 SFT + hard-negative preference pair

사용

PY=.venv/bin/python
# 1) 합성 화면 생성
$PY scripts/grammar_gen.py --n 100 --registry schema/registry.json --out-dir samples/raw
# 2) 게이트(수용 데이터만 학습에 사용)
$PY scripts/validate_ir.py --registry schema/registry.json --ir <tds-ir.json> --json
# 3) TSX 컴파일
$PY scripts/compile_tds_ir.py --ir <tds-ir.json> --out Screen.tsx
# 4) 학습 데이터셋(5 태스크 + DPO)
$PY scripts/build_dataset.py --in-dir samples/raw --registry schema/registry.json --out-dir samples/dataset --cap 100

불변식

모델은 JSX/코드를 직접 쓰지 않는다 — 검증된 TDS-IR만. 코드는 컴파일러 소유.
게이트 통과분만 학습 데이터(data engine > data volume). status=valid 아니면 drop 또는 repair.
registry는 retrieval 소스 — 현재 props를 weights에 암기시키지 않는다(TDS 버전 변동 대비).
학습: 일반 UX 추론은 LoRA/frozen 보존, TDS realization adapter만 강학습([[subagent-model-routing]]).
중국 teacher API는 비-TDS UX 추론에만(사내 IP 보호, 2026-07-14 결정).

데이터 태스크 (registry 통과 화면당 파생)

text→UX-IR · text→TDS-IR · screenshot→TDS-IR · edit→JSON Patch · invalid→repair · TDS-IR→NL설명 · DPO(good>corrupt).

Registry 재생성 (tds_ssot 갱신 시)

ThakiCloud/tds_ssot 클론 → props/slots/enum 재추출 → schema/registry.json 갱신 → uxRoleToComponent 재매핑. 데스크톱 콘솔 표면(Table/Drawer/Modal/CatalogCard/PageShell).