geminiclaw

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Translate a web page while preserving its original DOM structure, CSS, and images. Generates a self-contained bilingual preview HTML with toggle controls. Use this skill whenever the user shares a URL and asks for translation, translated preview, bilingual view, or when the channel topic instructs to use translate-preview. Do NOT write your own translation scripts — always use this skill's reference files.

Job scheduling. Manage recurring tasks using MCP tools.

Generate a prioritized daily briefing with calendar, email, tasks, and yesterday's activity. Designed for cron execution. Trigger with "morning briefing", "daily brief", "start my day".

Self-management via geminiclaw_admin MCP tool. Config, skills, upgrade, sessions.

Proactively explore the web for topics matching the user's interests and share findings conversationally. Designed for cron execution with Flash model.

Read before planning, declare scope before implementing. Prohibit out-of-scope changes and full rewrites.

Conduct thorough research using multi-angle queries, reading multiple sources, and cross-referencing.

GitHub operations via gh CLI (PRs, Issues, CI checks, API queries). Not for local git operations.

Google Workspace MCP tools for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

Safe PDF reading via text extraction. Use this skill whenever you need to read, analyze, or extract content from PDF files. Gemini CLI's read_file sends PDFs as base64 inlineData which frequently causes API errors (400/500), garbled output, or empty responses. This skill avoids those failures by extracting text with pdftotext first. Triggers on any task involving PDF files — paper analysis, document review, data extraction from PDFs, or when a user shares a PDF URL.

Search and analyze past session logs. Use when the user says things like "in the previous conversation..." or "I did something before...", or when investigating cost and tool usage.

Persistent task management via TODO.md. Supports add, complete, list, delete, and heartbeat integration.

Create session working directories. Provision directories under runs/ when file output is needed.