Skip to main content
The public Anarlog skill teaches agents a single workflow across Cloud MCP and the local CLI:
  1. Call connected Cloud MCP tools first.
  2. Fill gaps with anarlog --json when Cloud has no snapshot.
  3. Resolve meeting IDs from search results.
  4. Fetch meeting detail before transcript text.
  5. Keep transcript reads bounded and never access SQLite directly.

​
Sources

The published file is self-contained. The repository package adds references for setup, CLI commands, MCP tools, and errors.

​
Install the plugin

The Anarlog plugin connects to hosted Cloud MCP and bundles the skill. Enable Settings → Developers → Cloud API & Connectors first. Install the Anarlog CLI when the skill needs to fill a meeting that is not in Cloud.
If you previously installed Anarlog Cloud, replace it with Anarlog.
For Claude Code:
For GitHub Copilot CLI:
For ChatGPT and Codex, add the repository source, restart the ChatGPT desktop app, then install Anarlog from the Fastrepl source in the Plugins Directory:
The first cloud tool use opens Anarlog’s OAuth sign-in and consent flow; no cloud API key is required for Cloud reads. Cursor Teams and Enterprise administrators can import https://github.com/fastrepl/anarlog as a team marketplace, then install Anarlog.

​
Install in an agent

Install it from the documentation site with the skills CLI:
For a filesystem-based agent, copy the complete skills/anarlog directory into that agent’s skills directory. Keep the directory name anarlog so relative reference links continue to work.
Agent skill locations and installer commands vary by client. Follow your agent’s skill installation instructions rather than copying only SKILL.md.
The contributor skills under .agents/skills are internal repository workflows. They are not part of the public Anarlog skill.