Lean and reference-oriented throughout: executable commands, a flag table, API/input/output JSON samples, and a short numbered overview. It does not explain concepts Claude already knows, and the 'Date Filtering' section earns its place by conveying the non-obvious fact that the actor's date params are unreliable.

Fully executable, copy-paste-ready bash commands in Quick Start and Common Workflows, a complete CLI reference table with defaults, and concrete JSON examples for direct API input and tweet output schema.

This is a single-action skill (run search_twitter.py) and the invocation is unambiguous with multiple worked examples; the 'How the Script Works' section sequences the internal steps (build term, call actor, poll, fetch, dedup, filter, sort, output) with status checking on the actor run. The operation is read-only, so destructive/batch validation caps do not apply.

Well-organized single-file overview with clearly labeled sections, and the one external artifact (scripts/search_twitter.py, verified present) is referenced one level deep via the example commands — no nested reference chains.

Lists multiple concrete actions ('Search and scrape Twitter/X posts', 'find tweets, track brand mentions, monitor competitors', 'analyze Twitter discussions') which would warrant a 3, but the description uses second person voice ('Use when you need to find tweets'), which the rubric penalizes by reducing specificity by 1.

Explicitly answers both what ('Search and scrape Twitter/X posts using Apify') and when ('Use when you need to find tweets, track brand mentions...') with an explicit 'Use when' trigger clause.

Strong coverage of natural terms a user would say: 'find tweets', 'track brand mentions', 'monitor competitors on Twitter', 'analyze Twitter discussions', 'Twitter/X posts'.

Clear niche (Twitter/X mention tracking via Apify's apidojo/tweet-scraper) with distinct triggers unlikely to collide with other skills.