Borrowing it
Nothing to install: this file belongs to fivetaku/idea-lab. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fivetaku/idea-lab/main/.claude/skills/fashion-trend/SKILL.mdgit clone --depth 1 https://github.com/fivetaku/idea-labWrote 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.
[](https://agentmods.dev/skills/fivetaku/idea-lab/fashion-trend)<a href="https://agentmods.dev/skills/fivetaku/idea-lab/fashion-trend"><img src="https://agentmods.dev/badge/skills/fivetaku/idea-lab/fashion-trend/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.
<a href="https://agentmods.dev/skills/fivetaku/idea-lab/fashion-trend"><img src="https://agentmods.dev/badge/skills/fivetaku/idea-lab/fashion-trend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00230 | $0.01869 |
| Opus 5 | $0.00115 | $0.00934 |
| Sonnet 5 | $0.00046 | $0.00374 |
| Haiku 4.5 | $0.00023 | $0.00187 |
Grade A, and why
fashion-trend 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fashion Trend — KREAM 인기 트렌드 리포트
키워드의 남/여 인기순 상품을 긁어 이미지가 들어간 트렌드 리포트를 만들고, 주간으로 쌓아 순위 변화를 추적한다.
매주 KREAM을 직접 둘러보며 "요즘 뭐가 뜨나" 확인하던 일을 자동화한다. 인기순(노출 순위)을 인기 신호로 삼고, 거래량은 스테디셀러 편향이 있어 보조로만 쓴다. 같은 키워드를 매주 쌓으면 순위 변화(Δ)가 진짜 트렌드를 드러낸다.
이 워크스페이스의 리서치 트랙(①)의 특화 도구다: 원자료는 30-research/에, 리포트는 60-output/에 남아 다음 아이데이션·기획의 근거가 된다.
⚠️ 크롤링 주의 — robots.txt·이용약관 확인, 과도한 요청 자제, 수집 데이터는 본인 분석용으로만.
워크플로우
Step 1: 입력 확인 + URL 조립
타입: prompt
키워드와 성별 범위를 AskUserQuestion으로 확인한다. 키워드 기본값은 반팔티이며, 사용자가 다른 키워드(후드티·맨투맨 등)를 말하면 그 키워드로 바꾼다.
- 키워드(기본 반팔티) · 성별(남/여/둘 다, 기본 둘 다)
- 날짜는 오늘(YYYY-MM-DD)로 잡는다.
키워드를 URL 인코딩해 정렬별 URL 2개를 만든다:
남성: https://kream.co.kr/search?keyword={키워드}&tab=products&sort=male_popularity
여성: https://kream.co.kr/search?keyword={키워드}&tab=products&sort=female_popularity
Step 2: 수집 (insane-search)
타입: api_mcp
각 URL을 insane-search engine으로 스크래핑해 응답 HTML을 30-research/_raw/에 저장한다. KREAM은 봇 차단 + Nuxt SPA라 일반 fetch로는 안 되므로 insane-search가 필요하다.
mkdir -p 30-research/_raw
cd <insane-search engine 디렉토리> # ~/.claude/plugins/cache/.../insane-search/.../skills/insane-search
python3 -m engine "<URL>" > <workspace>/30-research/_raw/_raw-{성별}.html 2>/dev/null
insane-search 플러그인이 없으면 설치를 안내한다:
/plugin marketplace add https://github.com/fivetaku/gptaku_plugins.git → /plugin install insane-search
Step 3: 파싱 → 상품 표 저장
타입: script
scripts/parse.py로 __NUXT_DATA__를 파싱해 상품 표(마크다운)를 30-research/에 저장한다. 관심/리뷰/거래의 "만·천" 단위 축약은 반드시 실수치로 환산한다(parse.py가 처리) — 누락하면 거래가 최대 1만배 축소되는 버그가 생긴다. 이미지 URL도 상품 카드에서 추출해 함께 저장한다.
python3 .claude/skills/fashion-trend/scripts/parse.py \
30-research/_raw/_raw-남성.html 남성 {키워드} {날짜} 30-research
python3 .claude/skills/fashion-trend/scripts/parse.py \
30-research/_raw/_raw-여성.html 여성 {키워드} {날짜} 30-research
→ 30-research/kream-{키워드}-{성별}-{날짜}.md (이미지URL 컬럼 포함). 날짜 파일명 규칙은 주간 추적의 핵심이므로 고정한다. 파일 상단에 출처(KREAM 검색 URL)·수집일이 기록되는지 확인한다 (리서치 원자료 규칙).
Step 4: 분석
타입: prompt
What ships with it
2 files 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.
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.
- 10d ago First seen · 97 lines · 230 tokens per session scan A 88155283edc2
fashion-trend is a skill published in the GitHub repository fivetaku/idea-lab (2 stars, last pushed 7d ago), licensed MIT. It adds 230 tokens to every session and 1,869 once invoked, about $0.0011 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.
Other skills, from other repositories
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
co-marketing
When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marketing,' 'cross-promotion,' 'collaborate with another company,' 'partnership…
analytics
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this,"…
launch-monitor
Use when the user asks to "monitor my launch", "track our Product Hunt / Hacker News ranking", or "watch the launch window"; runs the T-0 to T+30 window watch — pre-launch instrumentation verification (UTM/event checks, the upstream of RAMP P1), HN rank/points/comments polling with a comments-over-points flamewar…
narrative-drift-monitor
Use when the user asks to "check if our surfaces have drifted from the canon", "watch for competitor repositioning", or "define when we should reposition"; produces a drift report — self-drift per flagship surface vs the narrative-registry canon over time (via wayback.py, change history Measured with as-of dates)…