webtoon-harness: Skill for Claude Code

.claude/skills/webtoon-trend-research/SKILL.md

webtoon-trend-research is a skill for Claude Code from revfactory/webtoon-harness. It costs 169 tokens per session (2,803 once invoked), scanned A, original, MIT.

A method for researching current webtoon trends, including genres, platform rankings, episode structures, hooks, twists, and reader reactions.

In plain words
What is it for?
Use it to compare popular webtoons, study genre patterns and cliffhangers, inspect platform publishing formats, and summarize findings into planning advice.
Why use it?
It records sources and observation dates so creative decisions are based on current evidence rather than assumptions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is revfactory/webtoon-harness's own configuration. It tells Claude Code how to work on webtoon-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything webtoon-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to revfactory/webtoon-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/revfactory/webtoon-harness/main/.claude/skills/webtoon-trend-research/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/revfactory/webtoon-harness

Made for: Claude Code.

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 webtoon-trend-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/revfactory/webtoon-harness/webtoon-trend-research/github.svg)](https://agentmods.dev/skills/revfactory/webtoon-harness/webtoon-trend-research)
Your own site
<a href="https://agentmods.dev/skills/revfactory/webtoon-harness/webtoon-trend-research"><img src="https://agentmods.dev/badge/skills/revfactory/webtoon-harness/webtoon-trend-research/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 webtoon-trend-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/revfactory/webtoon-harness/webtoon-trend-research"><img src="https://agentmods.dev/badge/skills/revfactory/webtoon-harness/webtoon-trend-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 169 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,803 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00169 $0.02803
Opus 5 $0.00084 $0.01401
Sonnet 5 $0.00034 $0.00561
Haiku 4.5 $0.00017 $0.00280

Measured 12d ago against content hash 4905e60d403f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

webtoon-trend-research 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 12d 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.

.claude/skills/webtoon-trend-research/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

웹툰 트렌드 리서치 방법론

리서치팀(trend-scout, platform-ranker, audience-analyst, hook-analyst, trend-synthesizer)이 "지금 무엇을, 어떤 톤·구조로 만들면 인기 있을지"를 데이터로 답하기 위한 공통 방법론이다. 명령형으로 따른다.

조사 대상이 빠르게 변하므로, 결론보다 근거와 출처를 먼저 챙긴다. 모든 주장에는 출처와 관측 일자를 붙인다. 상충 정보는 양쪽을 적고 출처를 병기한다(임의로 한쪽을 지우지 않는다).

왜 이렇게 조사하는가 (Why-first)

  • 웹툰 흥행은 우연이 아니라 반복되는 패턴이다. 패턴을 찾아 이식하면 흥행 확률이 오른다. 그래서 한 작품이 아니라 "여러 작품에서 반복되는가"를 본다.
  • 트렌드는 시점 의존적이다. 6개월 전 핫했던 트로프가 지금은 식었을 수 있다. 그래서 관측 일자를 항상 기록하고 최근 신호를 우선한다.
  • 기획팀은 실행 가능한 결정을 원한다. "로판이 인기"가 아니라 "로판 × 회귀 × 차가운 복수극 톤 × 1화 끝 정체 반전"처럼 곧바로 쓸 수 있는 형태로 정리해야 가치가 있다.
  • 시나리오/비주얼 팀이 산출물을 소비하므로, 발견은 이야기로 전환 가능한 형태(트로프·기법·구조)로 남긴다.

무엇을 어디서 조사하는가

네 축으로 조사한다. 자신의 역할 축을 깊게 파되, 다른 축의 신호도 교차 확인한다.

1) 장르·트로프 (trend-scout)

  • 인기 장르: 회귀·빙의·환생(회빙환), 다크판타지, 로맨스판타지(로판), 헌터/게이트물, 사이다 서사, 먼치킨, 학원/직장 복수극, 아카데미물, 현대판타지, 무협, 일상/힐링 등.
  • 각 장르의 반복 트로프와 변주, 그리고 라이프사이클(상승 / 정점 / 하락)을 구분한다.
  • 장르 혼종(로판+회귀, 헌터물+복수극 등)과 신규 결합의 초기 신호를 잡는다.
  • 트로프 뒤의 독자 욕구(대리만족·통제감·공정함·설렘)를 한 줄로 해석한다.

2) 플랫폼·연재 구조 (platform-ranker)

  • 플랫폼: 네이버웹툰, 카카오페이지, 카카오웹툰, 레진코믹스(필요 시 리디·투믹스 등).
  • 랭킹을 종류별로 본다: 인기 / 유료 / 신작 / 완결. 플랫폼마다 랭킹 산정 방식이 다름을 전제한다.
  • 인기작의 연재 구조: 회차당 분량(컷·패널 수, 스크롤 길이), 회차 호흡, 에피소드 단위.
  • 클리프행어 위치: 회차 끝 컷의 긴장 처리, "다음화"를 누르게 하는 지점.
  • 결제 전환 구간: 무료→유료 분기 회차, 기다무/미리보기 컷오프, 유료 구간의 훅 밀도.

3) 독자·반응 (audience-analyst)

  • 인구통계: 장르별 주 독자층(연령·성별·플랫폼 성향). 대부분 추정이므로 근거를 적고 "추정"으로 라벨링한다.
  • 몰입 요소: 붙잡는 감정 동인(대리만족·사이다·설렘·통제감·정의 실현)과 그 트리거 장면.
  • 이탈(드롭) 지점: 떠나는 전형 구간(느린 도입부, 고구마 누적, 떡밥 방치, 전개 지연, 작화 붕괴, 결제 장벽)을 회차·전개 단계와 연결한다.
  • 댓글 반응 패턴: 베스트 댓글을 유형으로 코딩(사이다 환호 / 고구마 불만 / 떡밥 추리 / 캐릭터 호불호 / 결제 불만). 개별 폭언이 아닌 반복 패턴으로 집계한다.

4) 후킹·클리프행어·반전 (hook-analyst)

  • 1화 후킹 공식: 첫 컷~첫 회차의 낚는 장치(강렬한 의문, 즉시 위기, 비범한 주인공 선언, 충격 오프닝, 회귀/각성 트리거)와 배치 순서.
  • 클리프행어 메커니즘: 회차 끝 긴장을 끊는 위치와 방식.
  • 반전(트위스트) 역설계: 어떤 예측을 어떻게 뒤집는가(정체·배신·관계 역전·시점·진실 공개)와 충격 극대화 타이밍.
  • 복선 기법: "심기 → 숨기기(미스디렉션) → 터뜨리기"의 단서와 회수 간격. 공정한 반전은 앞에 단서가 있다.

역설계의 관찰 프레임(반전·클리프행어 분해 체크리스트)은 길어서 분리해 두었다. references/observation-frames.md를 참고한다.

Read the full file on GitHub · 110 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 110 lines · 169 tokens per session scan A 4905e60d403f

Subscribe to this mod's changes

webtoon-trend-research is a skill published in the GitHub repository revfactory/webtoon-harness (313 stars, last pushed 2mo ago), licensed MIT. It adds 169 tokens to every session and 2,803 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens