사용 방법
- 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
- 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
- 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/apidojo-io/apidojo-skills --skill discovering-viral-tiktok-content-trends시작 전 확인
- 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
- 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 Skill 문서
원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.
Discovering Viral TikTok Content Trends
Identifies what's going viral on TikTok in a niche by analyzing high-performing posts. Extracts repeatable content formats, hooks, and structural patterns — the inputs needed to create content that rides existing momentum.
Prerequisites
APIFY_TOKENenvironment variable set- Optional: Apify MCP server installed
Inputs
| Parameter | Type | Required | Default | Notes |
|---|---|---|---|---|
startUrls | array | Optional | [] | TikTok URLs — user profiles, hashtags, music pages, search, locations |
keywords | array | Optional | [] | Search keywords/terms to find posts |
sortType | string | Optional | RELEVANCE | Sort order for keyword results: RELEVANCE, MOST_LIKED, DATE_POSTED |
location | string | Optional | — | ISO 3166-1 alpha-2 country code for regional filtering (e.g. US, GB) |
maxItems | number | Optional | Unlimited | Maximum posts to return across the run |
includeSearchKeywords | boolean | Optional | false | Add the matched search keyword field to each post |
customMapFunction | string | Optional | — | JavaScript function to transform each output object |
Workflow
Progress:
- [ ] Step 1: Search niche hashtags
- [ ] Step 2: Filter for high-performing posts
- [ ] Step 3: Analyze content formats and hooks
- [ ] Step 4: Score trend viability for replication
- [ ] Step 5: Deliver trend briefStep 1: Search Hashtags
Recommended — run_actor.js (handles waiting, output, and file saving automatically):
bash
# Quick answer (prints table to chat)
node scripts/run_actor.js \
--actor "apidojo~tiktok-scraper" \
--input '{"param": "value"}'
# Save as CSV
node scripts/run_actor.js \
--actor "apidojo~tiktok-scraper" \
--input '{"param": "value"}' \
--output YYYY-MM-DD_results.csv --format csv
# Save as JSON
node scripts/run_actor.js \
--actor "apidojo~tiktok-scraper" \
--input '{"param": "value"}' \
--output YYYY-MM-DD_results.json --format jsonAPIFY_TOKENmust be set in environment or.envfile.
If Apify MCP is available:
Tool: apify:run-actor
Actor: "apidojo~tiktok-scraper"
Input:
{
"keywords": ["#[niche]", "#[niche]tiktok", "#[niche]foryou"],
"maxItems": 200
}REST API fallback:
bash
curl -X POST "https://api.apify.com/v2/acts/apidojo~tiktok-scraper/runs?token=$APIFY_TOKEN" -H "Content-Type: application/json" -d '{"keywords": ["#skincaretips", "#skincaretiktok"], "maxItems": 200}'Filter: playCount >= min_views
Step 2: Analyze Content Patterns
From caption and available metadata, classify:
hook_type:
QUESTION = caption starts with or contains "?", "have you", "do you", "did you know"
LIST = "X things", "here are the", "number [N]"
BEFORE_AFTER = "I did X for 30 days", "watch the transformation"
STORY = first-person narrative opener ("I was struggling with...")
CONTROVERSY = "unpopular opinion", "no one talks about", "this is controversial"
TUTORIAL = "how to", "step by step", "the only guide you need"
content_length_tier:
SHORT = video duration < 15 seconds
MEDIUM = 15-60 seconds
LONG = > 60 secondsStep 3: Score Trend Replicability
trend_score = (playCount / 1000000, max 1) * 0.30
+ (diggCount / playCount * 100 > 3 ? 1 : ratio/3) * 0.25
+ (commentCount / playCount * 100 > 0.5 ? 1 : ratio/0.5) * 0.25
+ (format_is_replicable: TUTORIAL/LIST/QUESTION = 1, BEFORE_AFTER = 0.8, STORY = 0.6) * 0.20Trend window: posts all from the same 7-day period = TRENDING NOW; spread over 30 days = ESTABLISHED FORMAT
Step 4: Edge Cases
- Trend driven by a single mega-creator: If top 3 posts are from same creator, it's a creator trend not a format trend — flag as
CREATOR_DRIVEN; harder to replicate without their audience - Trend requires specific audio: Note if posts share the same sound; audio trends are TikTok-specific and may expire quickly
- Niche too small (< 50 posts above threshold): Lower
min_viewsto 25K; or report the top posts available with a note on data volume - International content dominates: Filter by caption language; use English-language posts if targeting English-speaking audience
Output Format
# TikTok Viral Trend Report: [NICHE]
Period: [DATE_RANGE] | Posts analyzed: [N] | Viral posts (>[MIN_VIEWS] views): [N] | Date: [DATE]
## Top Performing Formats
| Format | # Posts | Avg Views | Avg Like Rate | Best Example |
|--------|---------|-----------|--------------|-------------|
| Tutorial | [N] | [N] | [X%] | @[handle]: "[caption excerpt]" |
| List | [N] | [N] | [X%] | |
## Top Viral Posts
| Creator | Views | Likes | Comments | Hook Type | Caption Preview |
|---------|-------|-------|----------|----------|----------------|
## Hook Patterns Worth Replicating
1. "[Hook structure]" — used in [N] viral posts, avg [N] views
Example: "[verbatim hook from top post]"
## Trend Window Assessment
- TRENDING NOW (< 7 days): [N] posts in format
- ESTABLISHED FORMAT (7-30 days): [N] posts
- FADING (> 30 days): [N] posts
## Recommended Content Angles for [NICHE]
1. [Format + hook recommendation with rationale]
2. [Format + hook recommendation]Troubleshooting
All viral posts are from mega-creators: Add filter follower_count < 500K to surface format trends from creators of all sizes. Format analysis is inconsistent: Caption text is the only metadata available without video analysis; use it as a proxy and note this limitation. Trend is already declining: TikTok trends typically peak and decline within 2-3 weeks; if freshness is low, recommend adapting the format with a new angle rather than copying directly.
