How do I install the Linuxdo Topic Capture skill?

Run npx skillmds@latest add sammielisha425-design/linuxdo-topic-capture in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Linuxdo Topic Capture safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Linuxdo Topic Capture?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Linuxdo Topic Capture free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Linuxdo Topic Capture?

sammielisha425-design (@sammielisha425-design) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Linuxdo Topic Capture by sammielisha425-design

Name: Linuxdo Topic Capture
Rating: 4.666666666666667 (3 reviews)
Author: sammielisha425-design

Linuxdo Topic Capture

Capture Linux.do / L站 topic list titles, links, ids, categories/tags, reply/view/update snippets from the Codex in-app browser login session. Use when the user asks to 抓L站, linux.do帖子名, L站话题列表, 最近话题, or wants only titles to decide what to read. Default is list-only capture; do not open every topic or collect full replies unless explicitly requested. Do not use for Browser/iab repair, generic web research, Douyin/QQ/Discord capture, Cockpit/API, or full forum scraping; use the matching local skill.

File contents

Linux.do Topic Capture

Routing boundaries

Use this skill for:

Linux.do/L站 topic list capture from an existing in-app browser login session.
List-only title/link/id/category/reply-view-update snippets.

Do not use this skill for:

Browser/iab unavailable or login/control repair -> use codex-desktop-permission-browser-repair.
General internet research -> use agent-reach.
Douyin/QQ/Discord capture -> use the matching capture skill.

Default workflow

Use the Codex in-app Browser login session.
Confirm current tab is on https://linux.do/.
Capture list rows only by default: topic title, id, URL, and visible metadata.
Scroll gently, single-threaded, until the requested count is reached.
Save outputs under: <YOUR_CHAT_CAPTURE_WORKSPACE>\work\samples\linuxdo
Merge cumulative files only when requested or when continuing an existing capture set.

Reference map

Read references/original.md when you need:

exact Browser setup JavaScript;
DOM extraction pattern;
output filenames and merge rules;
detailed safety/reporting rules;
specific-topic follow-up behavior.

Safety rules

Do not post, reply, like, bookmark, edit settings, upload files, or access private messages.
Do not extract or print cookies/tokens.
Stop on CAPTCHA, rate limit, login errors, or unusual account warnings.
Do not use screenshot/OCR for normal capture.

---name: linuxdo-topic-capturedescription: Capture Linux.do / L站 topic list titles, links, ids, categories/tags, reply/view/update snippets from the Codex in-app browser login session. Use when the user asks to 抓L站, linux.do帖子名, L站话题列表, 最近话题, or wants only titles to decide what to read. Default is list-only capture; do not open every topic or collect full replies unless explicitly requested. Do not use for Browser/iab repair, generic web research, Douyin/QQ/Discord capture, Cockpit/API, or full forum scraping; use the matching local skill.---# Linux.do Topic Capture## Routing boundariesUse this skill for:- Linux.do/L站 topic list capture from an existing in-app browser login session.- List-only title/link/id/category/reply-view-update snippets.Do not use this skill for:- Browser/iab unavailable or login/control repair -> use `codex-desktop-permission-browser-repair`.- General internet research -> use `agent-reach`.- Douyin/QQ/Discord capture -> use the matching capture skill.## Default workflow1. Use the Codex in-app Browser login session.2. Confirm current tab is on `https://linux.do/`.3. Capture list rows only by default: topic title, id, URL, and visible metadata.4. Scroll gently, single-threaded, until the requested count is reached.5. Save outputs under: `<YOUR_CHAT_CAPTURE_WORKSPACE>\work\samples\linuxdo`6. Merge cumulative files only when requested or when continuing an existing capture set.## Reference mapRead `references/original.md` when you need:- exact Browser setup JavaScript;- DOM extraction pattern;- output filenames and merge rules;- detailed safety/reporting rules;- specific-topic follow-up behavior.## Safety rules- Do not post, reply, like, bookmark, edit settings, upload files, or access private messages.- Do not extract or print cookies/tokens.- Stop on CAPTCHA, rate limit, login errors, or unusual account warnings.- Do not use screenshot/OCR for normal capture.

Frequently asked questions