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 monitoring-instagram-brand-mentions시작 전 확인
- 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
- 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.
Monitoring Instagram Brand Mentions
Tracks all public Instagram posts mentioning a brand — via branded hashtags, @mentions, or product name keywords. Classifies mentions by sentiment and type (UGC, complaint, press coverage, competitor comparison).
Prerequisites
APIFY_TOKENenvironment variable set- Optional: Apify MCP server installed
Inputs
| Parameter | Type | Required | Default | Notes |
|---|---|---|---|---|
startUrls | array | ✅ | [] | Instagram URLs — profiles, hashtags, locations, audio pages, reels |
until | string | Optional | — | Scrape posts until this date (YYYY-MM-DD) |
maxItems | number | Optional | Unlimited | Maximum posts to return |
customMapFunction | string | Optional | — | JavaScript function to transform each output object |
Workflow
Progress:
- [ ] Step 1: Build hashtag and keyword list
- [ ] Step 2: Run instagram-scraper for each hashtag
- [ ] Step 3: Classify mention type and sentiment
- [ ] Step 4: Identify top advocates and critics
- [ ] Step 5: Deliver brand health reportStep 1 & 2: Run instagram-scraper
Recommended — run_actor.js (handles waiting, output, and file saving automatically):
# Quick answer (prints table to chat)
node scripts/run_actor.js \
--actor "apidojo~instagram-scraper" \
--input '{"param": "value"}'
# Save as CSV
node scripts/run_actor.js \
--actor "apidojo~instagram-scraper" \
--input '{"param": "value"}' \
--output YYYY-MM-DD_results.csv --format csv
# Save as JSON
node scripts/run_actor.js \
--actor "apidojo~instagram-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~instagram-scraper"
Input:
{
"keywords": ["#[BRAND]", "#[BRAND]review", "#[BRAND]community"],
"maxItems": 100
}REST API fallback:
curl -X POST "https://api.apify.com/v2/acts/apidojo~instagram-scraper/runs?token=$APIFY_TOKEN" -H "Content-Type: application/json" -d '{"keywords": ["#[brand]", "#[brand]review"], "maxItems": 100}'Run for each hashtag cluster. Merge results and deduplicate by postUrl.
Step 2: Classify Mentions
Mention type:
UGC = post contains product photo + brand mention; author is not verified
COMPLAINT = caption contains negative indicators: "broken", "disappointed", "scam", "refund", "terrible", "never again"
POSITIVE_REVIEW = caption contains: "love", "amazing", "best", "recommend", "obsessed"
PRESS/EDITORIAL = author is verified OR follower_count > 100K
COMPETITOR_COMPARISON = caption mentions competitor brand alongside this brandSentiment: Apply same lexical classification as Twitter sentiment skill (positive/negative/neutral indicators).
Step 3: Score Reach
mention_reach = likes + comments * 5 + (followers_of_author / 100)Step 4: Edge Cases
- Official brand account's own posts in results: Drop posts where
ownerUsername= brand's own handle - Hashtag is overloaded (> 1M posts): Use long-tail branded hashtags instead; or filter by date
- Sentiment misclassified for complex posts: Flag posts with both positive and negative indicators as
MIXED; report count - Foreign language mentions dominant: Report language distribution; flag non-English mentions separately
Output Format
# Instagram Brand Mention Monitor: [BRAND]
Posts collected: [N] | Period: [DATE_RANGE] | Date: [DATE]
## Mention Type Distribution
UGC: [N] | Positive Reviews: [N] | Complaints: [N] | Press: [N] | Comparisons: [N]
## Sentiment Summary
Positive: [X%] | Negative: [X%] | Neutral: [X%]
Weighted by reach: Positive [X%] | Negative [X%]
## Top UGC Posts (Most Liked)
| Creator | @Handle | Likes | Type | Caption Excerpt | Post URL |
|---------|---------|-------|------|----------------|---------|
## Complaints to Address
| Creator | Likes | Complaint Summary | Post URL |
|---------|-------|------------------|---------|
## Top Brand Advocates (Most Frequent Positive Posters)
1. @[handle] — [N] positive posts | [N] avg likesTroubleshooting
Hashtag returns generic posts: The brand hashtag may be ambiguous (e.g. "#apple"). Use #[brand]official or #[brand][product] for precision. Mostly competitor posts: This may indicate your brand is being used in comparison posts — analyze COMPETITOR_COMPARISON category for positioning insights. Sentiment skewed by a single viral negative post: Check weighted sentiment vs. raw sentiment; one viral post can shift the raw numbers.
