<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Collaboration on Top AI Skills</title><link>https://topaiskills.com/tags/collaboration/</link><description>Recent content in Collaboration on Top AI Skills</description><generator>Hugo</generator><language>en</language><lastBuildDate>Thu, 02 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://topaiskills.com/tags/collaboration/index.xml" rel="self" type="application/rss+xml"/><item><title>Agentspace</title><link>https://topaiskills.com/skills/general/agentspace/</link><pubDate>Thu, 02 Jul 2026 00:00:00 +0000</pubDate><guid>https://topaiskills.com/skills/general/agentspace/</guid><description>&lt;h2 id="what-it-is"&gt;What It Is&lt;/h2&gt;
&lt;p&gt;Agentspace is a file-sharing skill for AI coding agents. Instead of copy-pasting output or describing what your agent generated, you say &amp;ldquo;share this folder&amp;rdquo; and it returns a URL. Anyone with the link can view or edit the shared workspace — no sign-up, no API key, no cloud account required.&lt;/p&gt;
&lt;p&gt;The skill is published by agentspace-so and lives alongside Find Skills in the same &lt;a href="https://github.com/agentspace-so/skills" rel="nofollow" target="_blank"&gt;agentspace-so/skills&lt;/a&gt; repo. It works with Claude Code, Cursor, Codex, and Windsurf. Install it globally with &lt;code&gt;npx skills add&lt;/code&gt;, then invoke it by telling your agent to share the current folder or specific files.&lt;/p&gt;</description></item><item><title>Lark Base</title><link>https://topaiskills.com/skills/automation/lark-base/</link><pubDate>Sun, 21 Jun 2026 00:00:00 +0000</pubDate><guid>https://topaiskills.com/skills/automation/lark-base/</guid><description>&lt;h2 id="what-it-is"&gt;What It Is&lt;/h2&gt;
&lt;p&gt;A skill inside the larksuite CLI that gives your AI agent structured access to Lark Base — the spreadsheet-database hybrid in Lark&amp;rsquo;s productivity suite. Your assistant can query records, create and update rows, list tables, and search across bases, all through natural language instead of clicking through the web UI or writing raw API calls.&lt;/p&gt;
&lt;h2 id="whats-actually-different"&gt;What&amp;rsquo;s Actually Different&lt;/h2&gt;
&lt;p&gt;Most database queries from an AI agent require either a SQL connection string in your environment or a custom API wrapper that breaks every time the schema changes. Lark Base uses the same shared authentication as the other 25 skills in the larksuite CLI — the same login that reads documents, manages wikis, and creates calendar events also handles Base operations. Compared to setting up a direct database connection, you get row-level access control through Lark&amp;rsquo;s permission model, schema-aware queries that respect field types, and no credential sprawl across your tooling.&lt;/p&gt;</description></item><item><title>Lark Wiki</title><link>https://topaiskills.com/skills/automation/lark-wiki/</link><pubDate>Sat, 20 Jun 2026 00:00:00 +0000</pubDate><guid>https://topaiskills.com/skills/automation/lark-wiki/</guid><description>&lt;h2 id="what-it-is"&gt;What It Is&lt;/h2&gt;
&lt;p&gt;Lark Wiki is the knowledge base skill from larksuite&amp;rsquo;s CLI ecosystem — it lets your AI coding assistant search wiki pages, fetch content, create new pages, and manage Lark/Feishu wikis without leaving the terminal. Think of it as having a permanent read-write connection to your team&amp;rsquo;s internal documentation, accessible from any prompt.&lt;/p&gt;
&lt;h2 id="whats-actually-different"&gt;What&amp;rsquo;s Actually Different&lt;/h2&gt;
&lt;p&gt;The Lark suite spreads across five separate products — Docs, Wiki, Base, Sheets, and Calendar — each a different skill under the same CLI. Lark Wiki specifically handles the tree-structured knowledge base: search across wikis, read page trees, create new pages with markdown content, and list recent updates. What sets it apart from a generic browser-based wiki approach is that your AI agent can search and retrieve wiki content mid-conversation, then reference it in code or decisions without you tabbing out. Compared to exporting wikis as PDFs or copy-pasting, the feedback loop collapses to zero.&lt;/p&gt;</description></item><item><title>LarkDoc</title><link>https://topaiskills.com/skills/automation/lark-doc/</link><pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate><guid>https://topaiskills.com/skills/automation/lark-doc/</guid><description>&lt;h2 id="what-it-is"&gt;What It Is&lt;/h2&gt;
&lt;p&gt;A skill inside the larksuite CLI that gives your AI agent direct access to Lark (Feishu) documents. Your assistant can fetch document content, create new docs, append or update blocks, insert images, and generate whiteboards — all through natural language commands instead of clicking through the web UI.&lt;/p&gt;
&lt;h2 id="whats-actually-different"&gt;What&amp;rsquo;s Actually Different&lt;/h2&gt;
&lt;p&gt;Most document automation tools require custom API wrappers or Zapier-style integrations that break on the first auth refresh. This skill is part of a purpose-built CLI with 200+ commands and 26 agent skills, all sharing a single authentication session. The same login that lets your agent read a document also lets it create Base records, manage calendar events, and send chat messages. Compared to building bespoke API calls, you get a tested, maintained integration that stays in sync with Lark&amp;rsquo;s platform updates.&lt;/p&gt;</description></item></channel></rss>