Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →browser-act/x-tweet-by-handle
Scrapes tweets from an X (Twitter) user profile timeline given a handle, with selectable mode: tweets, tweets+replies, or media-only. Returns normalized per-tweet data including text, author profile, engagement counts, media, hashtags, mentions, and cursor for pagination.
Passed 15 of 19 test cases with the skill, and 6 of 19 without it.
and 12 more in the full report
11 fixed6 passed either way4 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
When building a profile URL for the photos and videos section of an X account using `scripts/build-profile-url.py`, a developer suggests passing `--mode media_tweets`. What exact `--mode` flag value is required?
| Checked | Without skill | With skill |
|---|---|---|
| Passes --mode media to scripts/build-profile-url.py | Missed | Passed |
The instructions your model reads when the skill loads.
X handle + timeline mode → normalized list of that user's tweets (or replies / media-only) with author, engagement, media, cursor.
All process output to user (progress updates, process notifications) follows the user's language.
Collect tweets from one or more X user profile timelines, selectable between the default tweets tab, the tweets-and-replies tab, and the media-only tab, returning structured per-tweet data and pagination cursors.
If browser-act has been confirmed available in the current session → skip this step.
Invoke browser-act via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry.
If login status for X has been confirmed in the current session → skip this step.
Otherwise: open https://x.com and observe the left sidebar:
User refuses or cannot log in → terminate execution.
This Skill's operational boundary = what the user can manually do in their browser. It only reads tweet data already shown to the user, never bypassing authentication. The browser's own JS signs the GraphQL request; the Skill triggers it via URL navigation and reads the response from network traffic. Python scripts under
scripts/only build URLs and parse responses — they do not call X directly. Run them through the bash tool.
test cases passed, vs 6 / 19 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.