The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the weread-agent-cli package globally via NPM to enable its primary functions.\n- [COMMAND_EXECUTION]: The skill uses a local CLI tool, weread, to perform all operations including network requests to the WeRead API and writing exported notes to the local filesystem.\n- [CREDENTIALS_UNSAFE]: The skill manages a private WeRead API key (wrk-...) and informs the user that this credential is stored locally in ~/.weread-cli/config.json. It provides documentation on how to set and secure this key.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the WeRead platform that could be manipulated to influence agent behavior.\n
Ingestion points: Retrieves book metadata, chapter text, and public user reviews through commands like weread search and weread reviews list.\n
Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the retrieved book data.\n
Capability inventory: The skill has the ability to write files to the local system (weread notes export) and perform network communication via the CLI tool.\n
Sanitization: There is no explicit logic mentioned for sanitizing or escaping the content of book descriptions or reviews before they are processed by the agent.

weread