discussion

discussion is a skill for Claude Code from naver/design-to-ui. It costs 152 tokens per session (3,126 once invoked), scanned A, original, Apache-2.0.

A skill for saving design-to-code lessons and problems as GitHub Discussions. GitHub Discussions are public, organized conversations attached to a repository.

In plain words
What is it for?
Recording solved implementation gotchas, design mismatches, ideas, questions, and adoption examples in the repository’s matching discussion category.
Why use it?
It preserves fixes for recurring problems instead of leaving them only in a work session. It also requires a draft and user approval before publishing.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the design-to-ui plugin — 6 skills, 3 commands, 1 MCP server shipped together

Good fit Recording solved implementation gotchas, design mismatches, ideas, questions, and adoption examples in the repository’s matching discussion category.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/naver/design-to-ui/discussion
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add naver/design-to-ui --skill discussion
Clone the repo
git clone --depth 1 https://github.com/naver/design-to-ui

Made for: Claude Code.

Or install design-to-ui, the plugin that ships this one along with the rest of its 6 skills, 3 commands, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for discussion

README.md
[![agentmods](https://agentmods.dev/badge/skills/naver/design-to-ui/discussion/github.svg)](https://agentmods.dev/skills/naver/design-to-ui/discussion)
Your own site
<a href="https://agentmods.dev/skills/naver/design-to-ui/discussion"><img src="https://agentmods.dev/badge/skills/naver/design-to-ui/discussion/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for discussion

Your own site · 80×15
<a href="https://agentmods.dev/skills/naver/design-to-ui/discussion"><img src="https://agentmods.dev/badge/skills/naver/design-to-ui/discussion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,126 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00152 $0.03126
Opus 5 $0.00076 $0.01563
Sonnet 5 $0.00030 $0.00625
Haiku 4.5 $0.00015 $0.00313

Measured 10d ago against content hash a907a7bd5bf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

discussion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/design-to-ui/skills/discussion/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

discussion — 사용 경험을 Discussions로 축적

design-to-ui·design-qa로 작업하다 세션 중 나온 것(막힘→해결 gotcha · design-qa 오차 · 아이디어 · 문의 · 도입 사례)을 naver/design-to-uiGitHub Discussions에 등록한다.

진입은 사용자가 /discussion을 호출한다. 자동 트리거(skill description)는 구조적으로 약하므로 명시 호출이 실질 진입점이다.

핵심 목적은 gotcha 축적의 선순환이다 — "이 화면이 처음엔 안 맞았는데, 이런 추가 프롬프트로 해결했다"는 경험이 쌓일수록 스킬이 점점 정확해진다. 그래서 이 스킬은 단순 코멘트가 아니라 세션에서 UI 일치도를 올린 과정을 자동으로 캡처한다.

Discussions 등록은 외부에 보이는 행위다. 반드시 초안을 보여주고 사용자 확인을 받은 뒤에만 등록한다(Step 4). 임의 등록 금지.

카테고리 (등록 대상)

런타임에 discussionCategories를 조회해 이름으로 매칭한다(ID 하드코딩 금지 — 바뀔 수 있음).

이 레포는 카테고리별 폼(.github/DISCUSSION_TEMPLATE/*.yml)을 쓴다. 폼이 있는 카테고리는 반드시 그 폼 필드에 맞춰 본문을 구성한다 — 그래야 웹 폼으로 등록된 글과 구조가 일치한다(Step 3·4). 폼은 API(createDiscussion)에서 강제되지 않으므로, 스킬이 직접 폼을 읽어 따라야 한다.

카테고리 폼 파일 언제
Gotcha gotcha.yml (개선 시도한 경우만) 상황+문제+시도해본 것+반영 희망. 추가 프롬프트/SKILL 수정으로 막힌 걸 푼 경험의 기본 목적지.
Ideas ideas.yml 기능 제안·개선 아이디어
Q&A q-a.yml 사용·확장 문의
Show & Tell show-tell.yml 자유 공유 — 이런 점이 좋았다/아쉬웠다
플러그인/선디자인검수 워크플로우 도입 (폼 없음 · 자유형식) 도입 사례 공유

공지 카테고리는 maintainer 전용이므로 여기로 등록하지 않는다. 폼 슬러그는 카테고리명을 소문자화 + 공백→- + &제거 (Q&A→q-a, Show & Tell→show-tell). 폼 유무·필드는 하드코딩하지 말고 런타임 조회로 확정한다(위 표는 참고용, 폼이 추가/변경될 수 있음).

Steps

Step 1: 의도·코멘트 파악

/discussion <코멘트>면 코멘트를 그대로 쓴다. 코멘트가 없으면 묻는다:

"어떤 걸 공유/제보할까요? (막혔다 해결한 경험, 아이디어, 문의, 도입 사례 등)"

Step 2: 정보 수집 (이 스킬의 핵심 — 3개 출처, 날조 금지)

컨텍스트만 믿지 말 것. 제보만 하러 온 얕은 세션, 길어서 compaction된 세션, 작업이 다른 세션·서브에이전트에서 이뤄진 경우엔 대화 컨텍스트에 정보가 거의 없다. 그래서 아래 3개 출처를 순서대로 써서 채운다:

  1. 대화 컨텍스트 — 이번 세션에서 한 변환/검증 내역.
  2. 디스크 근거 (컨텍스트가 얕으면 반드시) — 최근 작업을 실제 파일에서 복원:
    • git status / git diff 로 최근 수정된 UI 파일(Compose/XML/Swift/res/)과 변경 내용
    • design-qa 산출물이 있으면 읽는다: OVERLAY-REPORT.md · metrics.json · ledger.json · blend50.png/cmp_*
    • 대상 화면 소스 파일 직접 확인
  3. 사용자 인터뷰 (그래도 부족하면) — 근거로 못 채우는 항목, 특히 폼 필수 필드(상황·문제·시도해본 것)는 추측하지 말고 구체적으로 질문해서 채운다.

    예: "어떤 화면/컴포넌트였나요? 처음엔 뭐가 안 맞았죠? 어떤 추가 프롬프트나 수정으로 해결하셨어요?"

Read the full file on GitHub · 159 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 159 lines · 152 tokens per session scan A a907a7bd5bf6

Subscribe to this mod's changes

discussion is a skill published in the GitHub repository naver/design-to-ui (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 152 tokens to every session and 3,126 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

release-retrospective

Produce a structured look-back after a major release or deprecation — capturing what the plan got right, what it missed, and what to do differently. Trigger when someone says: release retrospective, post-release review, what went wrong with the release, how did the deprecation go, release post-mortem, retro on the…

murphytrueman/design-system-ops · 89 tokens

version-bump-advisor

Recommend the correct semver bump with reasoning and a generated changelog entry. Trigger when someone says: what version bump, is this a breaking change, semver recommendation, should this be major or minor, version this release, changelog entry, what kind of release is this, or anything about versioning a design…

murphytrueman/design-system-ops · 72 tokens

mobile-checkpoint

Checkpoint workflow for mobile development safety. Save/restore Android project state at critical points.

TalissonVitorino/kmp-ios-skills · 21 tokens

shipping-and-archiving

Use when the user says "done", "ship it", "finish", "complete", "archive", or otherwise indicates the current design is ready to be shipped. Runs final verification (Gate B), archives the CSpec, updates history, extracts a recipe when eligible, and cleans up temp files.

noemuch/bridge · 66 tokens

release-process

Step-by-step release checklist for Squad — prevents v0.8.22-style disasters.

dotnet/maui-labs · 20 tokens

app-store-compliance

Run an enterprise pre submission compliance audit on a mobile app project before uploading to the Apple App Store or Google Play. Use when the user is about to submit, ship, or release an iOS or Android app, when an app was rejected and needs a fix plan, when reviewing App Store Review Guidelines or Google Play policy…

mjmirza/app-store-compliance · 108 tokens