A GraphQL-based skill for AI agents to query and manage personal reading libraries and book metadata from Hardcover.app.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install hardcover
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install hardcover 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 Hardcover?
The Hardcover skill empowers AI agents to interact directly with the Hardcover.app platform, providing a seamless bridge between your reading habits and your digital workspace. By utilizing this integration within the Openclaw Skills ecosystem, developers can enable agents to retrieve library statuses, search vast book catalogs, and monitor reading progress without manual intervention.
This skill is designed for technical users who want to synthesize their reading data into broader workflows. Whether you are building a personal dashboard or an automated research tool, this skill provides the necessary GraphQL interface to access books, authors, and series data efficiently while maintaining high performance and data integrity.
Hardcover Use Cases
- Syncing Hardcover reading data to personal knowledge bases like Obsidian or Notion.
- Building automated reading goal trackers that update based on real-time library data.
- Enhancing AI research agents with book metadata, author details, and series information.
- Retrieving Currently Reading lists for social media automation or personal dashboards.
- Tracking reading progress and page counts for specialized productivity reporting.
How Hardcover Works
- The AI agent initiates a connection using the provided HARDCOVER_API_TOKEN to authenticate with the GraphQL endpoint.
- The agent first retrieves the unique User ID via the me query to scope subsequent requests and identify the account holder.
- Users can then query specific reading statuses such as Want to Read, Currently Reading, or Read using pre-defined status IDs.
- The skill fetches detailed metadata including book titles, page counts, cover images, and author contributions.
- For large libraries, the agent utilizes pagination with limit and offset parameters to efficiently navigate and process data.
Hardcover Setup
To get started with this skill, you must obtain a token from your Hardcover account settings. This token is used for all authenticated requests.
# Set your environment variable
export HARDCOVER_API_TOKEN="your_token_here"
# Test connectivity using curl to verify the token
curl -X POST https://api.hardcover.app/v1/graphql \
-H "Authorization: Bearer $HARDCOVER_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"query": "query { me { id username } }"}'
Hardcover Data Schema & Taxonomy
The skill organizes data through a GraphQL schema focused on the following entities which are easily accessible via Openclaw Skills:
| Entity | Description |
|---|---|
| user_books | Contains library status (e.g., Want to Read, Paused) and specific reading progress. |
| book | Core data including title, total pages, slugs, and cover image URLs. |
| contributions | Maps authors and their specific roles to book titles. |
| editions | Specific publication details including ISBN-13, format, and publisher info. |
| search | Multi-type search interface for Books, Authors, Series, Characters, and Lists. |
All results are returned in structured JSON format with a maximum query depth of 3 to ensure optimal response times.
Hardcover Advanced Features
- Full GraphQL support for complex relational queries across personal libraries and the global Hardcover catalog.
- Distinct querying capabilities using distinct_on: book_id to avoid duplicates when fetching multiple editions.
- Multi-type search functionality allowing agents to discover and filter content by publisher, character, or user-created lists.
- High-performance rate limiting of 60 requests per minute, optimized for real-time AI agent interactions.
- Deep integration potential for syncing reading progress with external goals and productivity systems.
SKILL.md
Loading
Related Openclaw Skills
QMD Memory Skill
A local, high-performance hybrid search and memory engine designed to eliminate API embedding costs for AI agents.
qmd
A high-performance local search engine designed for indexing and retrieving Markdown notes and documents using keyword, vector, and hybrid search methods.
Clawdbot (Snibet Edition)
A high-performance tweet engine for builders that generates sharp, human-sounding X content without the AI fluff.
Weave
A powerful CLI tool for creating crypto invoices, generating cross-chain payment quotes, and monitoring settlement status.
FFmpeg CLI
A comprehensive media processing toolset for automated video transcoding, editing, and manipulation via the command line.
maasv Memory
A self-hosted long-term memory and cognition layer for OpenClaw agents utilizing 3-signal retrieval and knowledge graphs.
Featured*
