The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill is designed to manage and utilize sensitive authentication credentials, including the Scrapy Cloud API key stored in environment variables (SHUB_APIKEY) or the local configuration file (~/.scrapinghub.yml). Security is maintained through the use of a Python wrapper script (scripts/scrapy_cloud_api.py) that performs authentication internally and avoids printing secrets to standard output.
[COMMAND_EXECUTION]: The skill uses the Bash tool to perform project discovery and management. It executes commands such as ls and cat to locate configuration files, and uses uvx shub to deploy projects, schedule spiders, and manage jobs.
[EXTERNAL_DOWNLOADS]: The skill dynamically downloads and executes the official shub CLI tool from the Python Package Index (PyPI) via uvx. It also performs network requests to the Docker Hub API (hub.docker.com) to identify the latest compatible environment stacks for deployment.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it processes data from external sources that could be influenced by an attacker.
Ingestion points: Local project configuration files (scrapinghub.yml, scrapy.cfg, requirements.txt) and JSON responses from the Scrapy Cloud HTTP API.
Boundary markers: Absent; the skill does not utilize specific delimiters or instructions to ignore embedded commands when processing these files.
Capability inventory: Execution of shell commands via uvx shub and local file system access (Read, Write).
Sanitization: None; the skill does not perform explicit validation or sanitization of content ingested from project files or API responses before using them in its logic flow.

scrape-scrapy-cloud