Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Discover and track emerging trends across Google Trends, Instagram, Facebook, YouTube, and TikTok to inform content strategy.
.claude/skills/apify-trend-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✓ | ▲ Improved | — | — |
| case-11 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✗→✓ | ▲ Improved | — | — |
Discover and track emerging trends using Apify Actors to extract data from multiple platforms.
(No need to check it upfront)
.env file with APIFY_TOKEN--env-file support)mcpc CLI tool: npm install -g @apify/mcpcCopy this checklist and track progress:
Task Progress:
- [ ] Step 1: Identify trend type (select Actor)
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the analysis script
- [ ] Step 5: Summarize findingsSelect the appropriate Actor based on research needs:
| User Need | Actor ID | Best For | |-----------|----------|----------| | Search trends | apify/google-trends-scraper | Google Trends data | | Hashtag tracking | apify/instagram-hashtag-scraper | Hashtag content | | Hashtag metrics | apify/instagram-hashtag-stats | Performance stats | | Visual trends | apify/instagram-post-scraper | Post analysis | | Trending discovery | apify/instagram-search-scraper | Search trends | | Comprehensive tracking | apify/instagram-scraper | Full data | | API-based trends | apify/instagram-api-scraper | API access | | Engagement trends | apify/export-instagram-comments-posts | Comment tracking | | Product trends | apify/facebook-marketplace-scraper | Marketplace data | | Visual analysis | apify/facebook-photos-scraper | Photo trends | | Community trends | apify/facebook-groups-scraper | Group monitoring | | YouTube Shorts | streamers/youtube-shorts-scraper | Short-form trends | | YouTube hashtags | streamers/youtube-video-scraper-by-hashtag | Hashtag videos | | TikTok hashtags | clockworks/tiktok-hashtag-scraper | Hashtag content | | Trending sounds | clockworks/tiktok-sound-scraper | Audio trends | | TikTok ads | clockworks/tiktok-ads-scraper | Ad trends | | Discover page | clockworks/tiktok-discover-scraper | Discover trends | | Explore trends | clockworks/tiktok-explore-scraper | Explore content | | Trending content | clockworks/tiktok-trends-scraper | Viral content |
Fetch the Actor's input schema and details dynamically using mcpc:
bashexport $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"
Replace ACTOR_ID with the selected Actor (e.g., apify/google-trends-scraper).
This returns:
Before running, ask:
Quick answer (display in chat, no file):
bashnode --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \ --actor "ACTOR_ID" \ --input 'JSON_INPUT'
CSV:
bashnode --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \ --actor "ACTOR_ID" \ --input 'JSON_INPUT' \ --output YYYY-MM-DD_OUTPUT_FILE.csv \ --format csv
JSON:
bashnode --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \ --actor "ACTOR_ID" \ --input 'JSON_INPUT' \ --output YYYY-MM-DD_OUTPUT_FILE.json \ --format json
After completion, report:
APIFY_TOKEN not found - Ask user to create .env with APIFY_TOKEN=your_token mcpc not found - Ask user to install npm install -g @apify/mcpc Actor not found - Check Actor ID spelling Run FAILED - Ask user to check Apify console link in error output Timeout - Reduce input size or increase --timeout
Use this skill when tackling tasks related to its primary domain or functionality as described above.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +61 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.