AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Browsing X

skill-browsing-skills-browsing-skills-x-com · by browsing-skills

Use when the user wants to interact with X (formerly Twitter) - search for posts, extract a specific post's data (content + engagement + author), extract a user's profile, extract visible posts from a user's timeline or home feed, or assemble visible source context for review, research, fact-checking, reporting, or archiving. Works on x.com and twitter.com. Requires a logged-in session (auth_toke…

No reviews yet
0 installs
47 views
0.0% view→install

Install

$ agentstack add skill-browsing-skills-browsing-skills-x-com

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-browsing-skills-browsing-skills-x-com)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Browsing X? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

X (Twitter) — Browsing Skill

Use this index to choose the X action that matches the user request, then open the linked reference file for the complete navigation, requirements, code, and return shape.

Action Index

  • search — Search X for a query and extract visible post results. Full spec: [references/search.md](references/search.md).
  • post-data — Extract a specific post's content, author details, engagement metrics, timestamp, and media. Full spec: [references/post-data.md](references/post-data.md).
  • profile-data — Extract an X user profile, including bio, follower counts, avatar, website, and account metadata. Full spec: [references/profile-data.md](references/profile-data.md).
  • user-timeline — Extract visible posts from a user's profile timeline. Full spec: [references/user-timeline.md](references/user-timeline.md).
  • following-feed — Extract visible posts from the X home feed (For You or Following tab). Full spec: [references/following-feed.md](references/following-feed.md).
  • source-context - Assemble visible posts, links, media flags, metrics, and canonical URLs into a source packet for review, research, fact-checking, reporting, or archiving. Full spec: [references/source-context.md](references/source-context.md).

Benchmarks

Benchmarks compare the maintained skill action against a no-skill browser agent that inspects the live page DOM and derives selectors at runtime. Full notes live in [BENCHMARKS.md](../../BENCHMARKS.md).

| Action | With Skill | Without Skill | Notes | |---|---:|---:|---| | search | 1,699 / ~6.4s | 3,907 / ~15.8s | Skill valid; no-skill malformed partial result. | | post-data | 1,987 / ~4.3s | 14,333 / ~35.1s | Skill complete; no-skill partial result. | | profile-data | 1,865 / ~12.3s | 324 / failed | Skill complete; no-skill one-shot eval failed. | | user-timeline | TBD | TBD | Not yet benchmarked. | | following-feed | TBD | TBD | Not yet benchmarked. | | source-context | TBD | TBD | Planned. |

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.