apify-ads-intelligence

What this skill does

# Ads Intelligence Cluster

Answer natural language questions about ads, ad libraries, and competitor advertising activity by routing to the right Apify Actor and delivering a synthesized answer.

**CLI rules:** Always pass `--user-agent apify-awesome-skills/apify-ads-intelligence`, `--json` (or the relevant `--format` flag on `datasets get-items`), and `2>/dev/null`. The `--user-agent` flag is critical for telemetry — never omit it.

## Note on platform coverage

- **Meta, Google, TikTok, LinkedIn**: real public ad libraries with rich data (creatives, targeting, dates, reach where disclosed).
- **X (Twitter)**: no public ad library exists. Coverage is a **best-effort workaround** that scrapes a brand's tweets and flags items with non-empty `card` field or `source` containing "Ads" as likely promoted. Always include the caveat in synthesis output.

## Note on overlap with `apify-ecommerce`

That skill has an `ads-intelligence` intent that routes to `apify/facebook-ads-scraper` for shallow Meta-ad lookups. This skill is the deep dive across all five platforms. If you only need Meta ads as a side detail of an ecommerce question, stay in `apify-ecommerce`. If ads are the main task, use this skill.

## Prerequisites

(No need to check it upfront)

- Apify CLI v1.5.0+ (`npm install -g apify-cli`)
- `jq` (recommended for response parsing and filtering; `brew install jq` on macOS, `apt install jq` on Linux)
- Authentication via one of:
  - `apify login` (OAuth, opens browser)
  - `APIFY_TOKEN` env variable (e.g. `export APIFY_TOKEN=...` or `.env` file)
  - Token from [Apify Console → Settings → Integrations](https://console.apify.com/settings/integrations)

Verify auth: `apify info --user-agent apify-awesome-skills/apify-ads-intelligence` — should show username and userId.

## Workflow

Copy this checklist and track progress:

```
Task Progress:
- [ ] Step 1: Detect intent and select Actor(s)
- [ ] Step 2: Fetch Actor schema
- [ ] Step 3: Ask user preferences (output format, result count, country)
- [ ] Step 4: Run the Actor (or Actors in parallel for cross-platform-audit) and fetch results
- [ ] Step 5: Synthesize a direct answer (not a data dump)
```

### Step 1: Detect Intent and Select Actor

Classify the user's message into an intent, then pick the right Actor.

**Intent signals:**

| Signals in user message | Intent |
|-------------------------|--------|
| "what ads is X running", "competitor [brand] ads", "[brand] FB/Google/TikTok/LinkedIn/X/Twitter ads", "show ads from [page]", "promoted tweets from [brand]" | `competitor-ads` |
| "ads about [topic]", "find [keyword] ads", "ads for [vertical]", "fitness/fintech/saas ads" | `keyword-ads` |
| "trending ads", "winning ads", "top ads", "best performing", "long-running ads", "creative inspiration" | `top-creatives` |
| "where do these ads go", "landing pages from ads", "click destinations", "ad funnels" | `landing-page-audit` |
| "compare X's ads across platforms", "all ads from [brand]", "cross-platform ad audit" | `cross-platform-audit` |

If multiple intents detected, ask: *"Do you want [intent A] or [intent B]?"*

**Actor routing — always try Primary first, switch to Fallback only if it fails or returns 0 results:**

| Intent | Platform | Primary Actor | Fallback Actor |
|--------|----------|---------------|----------------|
| `competitor-ads` | Meta (FB/IG) | `apify/facebook-ads-scraper` | `brilliant_gum/facebook-ads-library-scraper` |
| `competitor-ads` | Google | `dz_omar/google-ads-scraper` | `solidcode/ads-transparency-scraper` |
| `competitor-ads` | TikTok | `brilliant_gum/tiktok-ads-library-scraper` (`source: library`) | `silva95gustavo/tiktok-ads-scraper` |
| `competitor-ads` | LinkedIn | `silva95gustavo/linkedin-ad-library-scraper` | `dz_omar/linkedin-ads-scraper` |
| `competitor-ads` | X (workaround) | `apidojo/twitter-scraper-lite` (`twitterHandles: [<brand>]`) + heuristic filter | `apidojo/tweet-scraper` |
| `keyword-ads` | Meta | `brilliant_gum/facebook-ads-library-scraper` | `apify/facebook-ads-scraper` |
| `keyword-ads` | Google | `apify/google-search-scraper` (`focusOnPaidAds: true`) | — |
| `keyword-ads` | TikTok | `brilliant_gum/tiktok-ads-library-scraper` | — |
| `keyword-ads` | LinkedIn | `silva95gustavo/linkedin-ad-library-scraper` | — |
| `keyword-ads` | X (workaround) | `apidojo/twitter-scraper-lite` (`searchTerms: [<keyword>]`) + heuristic filter | `apidojo/tweet-scraper` |
| `top-creatives` | Meta | `brilliant_gum/facebook-ads-library-scraper` (rank by `daysRunning`) | — |
| `top-creatives` | TikTok | `burbn/tiktok-top-ads-spy` (sort by CTR / impressions / likes) | `brilliant_gum/tiktok-ads-library-scraper` (`source: creative_center`) |
| `top-creatives` | Google | n/a — fall back to `competitor-ads` route, filter to active ads | — |
| `top-creatives` | LinkedIn | n/a — fall back to `competitor-ads` route, rank by `impressionsPerCountry` reach | — |
| `top-creatives` | X | n/a in v1 — no reliable promoted-content signal across timelines | — |
| `landing-page-audit` | Meta | `brilliant_gum/facebook-ads-library-scraper` (`resolveSnapshotUrls: true`) | — |
| `landing-page-audit` | Google | `apify/google-search-scraper` (`focusOnPaidAds: true`, `directUrl`) | `dz_omar/google-ads-scraper` (`destinationUrl`) |
| `landing-page-audit` | X | n/a in v1 — heuristics not reliable enough for landing-page extraction | — |
| `cross-platform-audit` | All five | Run Meta + Google + TikTok + LinkedIn primaries in parallel; X workaround runs separately with caveat. Merge by advertiser. | — |

**X (Twitter) heuristic filter** — after scraping, flag a tweet as *likely promoted* if any of the following hold:

- `card` field is non-empty (website cards / CTAs are commonly attached to promoted tweets)
- `source` field contains "Ads" (e.g. "Twitter Ads")

Surface results with the explicit caveat: *"X has no public ad library; results below are tweets from the brand's own timeline that match promoted-content heuristics. They will miss promoted-only ads that appear in other users' feeds."*

### Step 2: Fetch Actor Schema

Fetch the Actor summary, input schema, and README:

```bash
# Summary (title, description, pricing, stats)
apify actors info "ACTOR_ID" --user-agent apify-awesome-skills/apify-ads-intelligence --json 2>/dev/null

# Input schema (required and optional parameters; schema lives in
# .taggedBuilds.latest.build.inputSchema as an escaped JSON string)
apify actors info "ACTOR_ID" --user-agent apify-awesome-skills/apify-ads-intelligence --input --json 2>/dev/null

# README (capabilities, examples, gotchas)
apify actors info "ACTOR_ID" --user-agent apify-awesome-skills/apify-ads-intelligence --readme 2>/dev/null
```

Replace `ACTOR_ID` with the selected Actor (e.g., `apify/facebook-ads-scraper`).

### Step 3: Ask User Preferences

Before running, ask:

1. **Output format**:
   - **Quick answer** (default) — synthesized answer in chat, no file saved
   - **CSV** — full export saved to disk
   - **JSON** — full export saved to disk
2. **Result count** — defaults by intent:

   | Intent | Default count |
   |--------|---------------|
   | `competitor-ads` | 30 |
   | `keyword-ads` | 30 |
   | `top-creatives` | 20 |
   | `landing-page-audit` | 50 |
   | `cross-platform-audit` | 15 per platform |

3. **Country** — default `US`. For TikTok library specifically, default `DE` (EU-only) and warn the user; for global TikTok use `source: creative_center`. X routes are global by handle/keyword, no country parameter.

**Cost safety**: Always set a sensible result limit in the Actor input (e.g., `maxResults`, `resultsLimit`, or the equivalent field per Actor schema). Warn the user before runs of 500+ ads — `apify/facebook-ads-scraper` charges per ad and X primaries charge per tweet.

### Step 4: Run the Actor and Fetch Results

Two steps: run the Actor (blocks until done), then fetch dataset items in the requested format.

**Run the Actor** — returns run metadata as JSON; extract `defaultDatasetId` for t