Financial Times Deep Reader (ft-reader) for Openclaw

Automate the extraction, synthesis, and bilingual reporting of Financial Times articles for professional and academic research.

zhouziyue233
v1.0.0
Feb 15, 2026
0
1.5k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install ft-reader

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install ft-reader using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Financial Times Deep Reader (ft-reader)?

The Financial Times Deep Reader is a specialized tool designed to bridge the gap between financial news and actionable intelligence. By leveraging Openclaw Skills for browser automation, this skill bypasses manual navigation, logs directly into FT.com, and extracts clean article data for high-fidelity analysis. It is specifically engineered for professionals and researchers who require deep reading capabilities and cross-lingual summaries.

This skill transforms raw article text into structured, academic-grade reports. Whether you are tracking market trends or performing sector-specific research, it ensures that technical terms and core arguments are accurately captured in both English and Chinese, providing a rigorous framework for global financial understanding.

Financial Times Deep Reader (ft-reader) Use Cases

  • Automated tracking of the Most Read section on Financial Times to stay current with market sentiment.
  • Academic research requiring structured extraction of core arguments and supporting data from paywalled financial content.
  • Professional market analysis where bilingual reporting is necessary for international teams.
  • Deep dives into specific financial sectors such as AI productivity or macroeconomic policy.

How Financial Times Deep Reader (ft-reader) Works

  1. Authenticates with FT.com using the browser profile to maintain session persistence and handle paywall access.
  2. Navigates to the homepage or specific sections to identify top-priority articles using DOM selection logic.
  3. Executes custom JavaScript to scrape titles, standfirsts, and body text without extraneous web clutter.
  4. Generates a structured analysis following a professional schema, translating core insights into English and Chinese.

Financial Times Deep Reader (ft-reader) Setup

To get started with this member of the Openclaw Skills library, ensure your browser profile is configured.

  1. Open your configuration file and add your credentials:
# FT credentials setup
FT_USER="[email protected]"
FT_PASS="your_password"
  1. Ensure the openclaw browser profile is initialized to allow for session persistence.
  2. Call the skill using your agent: "Lulu, use ft-reader to analyze the top 3 articles."

Financial Times Deep Reader (ft-reader) Data Schema & Taxonomy

The skill organizes article data into a structured format for easy parsing and archival:

Field Description Type
title The bilingual headline of the article String
core_opinion The primary thesis or argument String (Bilingual)
arguments Supporting evidence and data points List (Bilingual)
conclusion Final synthesis and takeaways String (Bilingual)
metadata Includes original URL and extraction timestamp Object

Financial Times Deep Reader (ft-reader) Advanced Features

  • Multi-article batch processing with automated token management to prevent data truncation during long reports.
  • High-fidelity English-Chinese translation of complex technical financial terminology.
  • Persistent session management using the openclaw profile to avoid repeated login challenges.
  • Custom extraction hooks via JavaScript evaluation for specific article components like charts and quotes.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*