Fetch Content
SerhiiKorniienko/bullshit-detector
Fetch and normalize any content source into clean text with metadata — YouTube video transcripts, TikTok captions, web articles, PDFs, tweets/X posts, local files.
A skill your agent uses 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…
Install Browsing X
$ npx skills add browsing-skills/browsing-skills --skill browsing-x -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install browsing-skills/browsing-skills browsing-x --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/browsing-skills/browsing-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/x.com .claude/skills/browsing-x && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "browsing-x" agent skill from https://github.com/browsing-skills/browsing-skills/tree/main/skills/x.com into .claude/skills/browsing-x/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browsing-x", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/browsing-skills/browsing-skills/tree/main/skills/x.comType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add browsing-skills/browsing-skills --skill browsing-x -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install browsing-skills/browsing-skills browsing-x --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/browsing-skills/browsing-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/x.com .agents/skills/browsing-x && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "browsing-x" agent skill from https://github.com/browsing-skills/browsing-skills/tree/main/skills/x.com into .agents/skills/browsing-x/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browsing-x", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add browsing-skills/browsing-skills --skill browsing-x -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install browsing-skills/browsing-skills browsing-x --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/browsing-skills/browsing-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/x.com .cursor/skills/browsing-x && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "browsing-x" agent skill from https://github.com/browsing-skills/browsing-skills/tree/main/skills/x.com into .cursor/skills/browsing-x/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browsing-x", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/browsing-skills/browsing-skills.git --path skills/x.com--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add browsing-skills/browsing-skills --skill browsing-x -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install browsing-skills/browsing-skills browsing-x --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/browsing-skills/browsing-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/x.com .gemini/skills/browsing-x && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "browsing-x" agent skill from https://github.com/browsing-skills/browsing-skills/tree/main/skills/x.com into .gemini/skills/browsing-x/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browsing-x", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install browsing-skills/browsing-skills browsing-xInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add browsing-skills/browsing-skills --skill browsing-x -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/browsing-skills/browsing-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/x.com .github/skills/browsing-x && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "browsing-x" agent skill from https://github.com/browsing-skills/browsing-skills/tree/main/skills/x.com into .github/skills/browsing-x/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browsing-x", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add browsing-skills/browsing-skills --skill browsing-x -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install browsing-skills/browsing-skills browsing-x --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/browsing-skills/browsing-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/x.com .opencode/skills/browsing-x && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "browsing-x" agent skill from https://github.com/browsing-skills/browsing-skills/tree/main/skills/x.com into .opencode/skills/browsing-x/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browsing-x", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
browsing-x- GitHub stars
- 117
- Token cost
- ~623 tokens
- SKILL.md length
- 218 words
- Files
- 7 (incl. references)
- Skills in repo
- 24
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses 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…
- The user wants to interact with X (formerly Twitter) - search for posts
- SKILL.md covers Action Index and Benchmarks
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Extract a specific posts data (content + engagement + author)
What it does
Browsing X is an agent skill from browsing-skills/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 (authtoken cookie) and a real browser - X is a JS-rendered SPA.
Its SKILL.md is about 620 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/following-feed.md`, `references/post-data.md` and `references/profile-data.md`).
It sits in Research & Science, covering Fact-checking and source verification. It works with X (Twitter). The repository describes itself as: Open-source registry of browser-automation skills for AI agents. The licence is MIT.
When your agent uses it
- The user wants to interact with X (formerly Twitter) - search for posts
- Extract a specific posts data (content + engagement + author)
- Extract a users profile
- Extract visible posts from a users timeline
Example prompts
- “s data (content + engagement + author), extract a user”
- “/browsing-x”
What it can do on your machine
Read from SKILL.md and the folder at commit 07855b5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Browsing X loads about 623 tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 116 tokens; SKILL.md has 218 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from browsing-skills/browsing-skills at commit 07855b5, republished under its MIT licence (© browsing-skills). 218 words, ~623 tokens.
Download SKILL.mdSave it as
.claude/skills/browsing-x/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- browsing-x
- description
- 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_token cookie) and a real browser - X is a JS-rendered SPA.
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.
- post-data — Extract a specific post's content, author details, engagement metrics, timestamp, and media. Full spec: 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.
- user-timeline — Extract visible posts from a user's profile timeline. Full spec: 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.
- 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.
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.
| 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. |
© browsing-skills, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 6 other files (references) in skills/x.com of browsing-skills/browsing-skills.
- SKILL.md
- references/following-feed.md
- references/post-data.md
- references/profile-data.md
- references/search.md
- references/source-context.md
- references/user-timeline.md
Open the folder on GitHubat commit 07855b5
Compare with similar skills
Browsing X next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Browsing X this skillbrowsing-skills/browsing-skills | 117 | — | ~623 | Automated safety check: Pass | MIT | |
| Fetch ContentSerhiiKorniienko/bullshit-detector | 154 | — | ~976 | Automated safety check: Pass | MIT | |
| Gmgn NarrativeGMGNAI/gmgn-skills | 607 | — | ~5.8k | Automated safety check: Pass | MIT | |
| Perplexity Web Searchdavila7/claude-code-templates | 32k | 11 repos | ~3.5k | Automated safety check: Notes | MIT | |
| Citation Verification GuideGalaxy-Dawn/claude-scholar | 5.7k | 2 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Article Fact Checkerdigoal/blog | 8.6k | — | ~939 | Automated safety check: Pass | GPL-2.0 |
Similar skills
Gmgn Narrative
GMGNAI/gmgn-skills
Independently research and write an AI-narrative / due-diligence card for a crypto token — the kind of "叙事分析" card that covers what story a token is telling and what's independently verifiable about…
Perplexity Web Search
davila7/claude-code-templates
Runs web-grounded searches through Perplexity's Sonar models over OpenRouter for current events, recent literature and cited facts beyond the model's training cutoff.
Citation Verification Guide
Galaxy-Dawn/claude-scholar
Reference guidance for checking every citation in academic writing against canonical sources such as DOI, arXiv, CrossRef and Semantic Scholar, to catch fake or wrong references.
Article Fact Checker
digoal/blog
三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…
Deep Research Agent Team
Imbad0202/academic-research-skills
Runs a 13-agent pipeline for rigorous academic research, from forming the question through systematic search, synthesis, bias checks and an APA 7.0 report.
More from browsing-skills/browsing-skills
All 24 skills in this repoWebsite Browsing Skills Index
browsing-skills/browsing-skills
Umbrella skill for a library of website-specific browsing skills. Use when the user's request targets one of these specific websites: <!-- DOMAINS:START…
Browsing Airbnb
browsing-skills/browsing-skills
A skill your agent uses when the user wants to interact with Airbnb — search public stays, extract listing details, extract visible reviews, or read availability and price breakdowns.
Browsing Aliexpress
browsing-skills/browsing-skills
A skill your agent uses when the user wants to interact with AliExpress — search products, inspect product detail pages, read the shopping cart, or add explicitly requested items to cart.
Amazon.com Browsing Actions
browsing-skills/browsing-skills
Searches Amazon products and groceries, reads product pages and cart contents, and adds explicitly named items to cart, stopping short of checkout.
Capterra Data Extraction
browsing-skills/browsing-skills
Extracts software product ratings, pricing and written user reviews from Capterra pages with a real browser, since the site has no public API.
Facebook Marketplace Browsing
browsing-skills/browsing-skills
Use when the user wants to interact with Facebook Marketplace — search visible listings, extract listing details, and summarize seller/profile information…
Related
Works with
Categories
Questions about Browsing X
What does Browsing X do?
A skill your agent uses 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…. Browsing X is an agent skill from browsing-skills/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.
When should I use Browsing X?
Browsing X fits situations like: the user wants to interact with X (formerly Twitter) - search for posts; extract a specific posts data (content + engagement + author); extract a users profile; extract visible posts from a users timeline.
How do I install Browsing X in Claude Code?
Run `npx skills add browsing-skills/browsing-skills --skill browsing-x -a claude-code`. Or copy the skill folder (skills/x.com in browsing-skills/browsing-skills) into .claude/skills/browsing-x in your project. Claude Code loads it when a task matches its description.
How do I install Browsing X in Codex?
Run `npx skills add browsing-skills/browsing-skills --skill browsing-x -a codex`. Or copy the skill folder (skills/x.com in browsing-skills/browsing-skills) into .agents/skills/browsing-x in your project. Codex loads it when a task matches its description.
Can I use Browsing X in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add browsing-skills/browsing-skills --skill browsing-x -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/browsing-x, .gemini/skills/browsing-x, .github/skills/browsing-x and .opencode/skills/browsing-x in your project.
What does Browsing X need to run?
SKILL.md names no scripts, command-line tools or credentials: Browsing X is instructions for the agent only.
Does Browsing X access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Browsing X safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Browsing X use?
Browsing X is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Browsing X use?
About 623 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.9k tokens, read only when the agent opens those files.
What are the alternatives to Browsing X?
Skills that share tags, products or a category with Browsing X: Fetch Content (SerhiiKorniienko/bullshit-detector, 154 stars), Gmgn Narrative (GMGNAI/gmgn-skills, 607 stars), Perplexity Web Search (davila7/claude-code-templates, 32k stars) and Citation Verification Guide (Galaxy-Dawn/claude-scholar, 5.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Browsing X?
browsing-skills (a GitHub organization) maintains it in browsing-skills/browsing-skills, which has 117 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on June 10, 2026.
Source: browsing-skills/browsing-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.