Add apify-app-store-intelligence skill - #89
Open
donnywin85 wants to merge 1 commit into
Open
donnywin85 wants to merge 1 commit into
donnywin85 wants to merge 1 commit into
Conversation
Routes App Store requests by the split that actually costs money: metadata (one row per app) vs reviews (thousands). Includes the ASO/rank-tracking boundary so ranking questions do not get answered from metadata.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this adds
apify-app-store-intelligence— a routing skill for Apple App Store data.The problem it solves is a routing one, not a scraping one. "Get me App Store data" splits into
two requests with roughly a 1000× cost difference between them:
Most Actors in the category do reviews, so an agent asked "did our competitor drop their price"
tends to route to a reviews scraper and bill the user for a corpus they did not ask for. The
skill classifies the request first, then routes; it also carves out keyword-rank tracking, which
is a third thing that cannot be answered from either.
Contents
SKILL.md— classification workflow, 8-Actor routing table, example prompts + the boundaryreferences/actor-index.md— routing table with input field names read from each Actor'spublished input schema
references/gotchas.md— storefront/price-per-country, the four things users call "the app",why a first
changesOnlyrun correctly returns zero rows, and the ambiguity of an emptyresult under throttling
Disclosure
One row in the routing table —
praise-most-high/app-store-intelligence— is an Actor I builtand publish. It is there for the one job the others do not do (per-field change detection on app
metadata); the other seven rows all route to unaffiliated Actors, and the two boundary cases
route away from it entirely. No affiliate or referral parameters on any link.
Checks run locally
bash scripts/lint_telemetry.sh— passes; the 2 warnings shown are pre-existing--format csvnotices in
apify-ads-intelligenceandapify-ecommerce, not this skillpython scripts/lint_references.py— passespython scripts/generate_agents.py— runs clean, 14 plugins; the generatedmarketplace.json/AGENTS.md/ README table were reverted and are not in this PROne skill, one PR, nothing outside
skills/apify-app-store-intelligence/.