The Agent Skills Directory

[SAFE]: The skill provides documentation and implementation guidance for integrating with the protocols.io API. All operations, including protocol management, file uploads, and workspace organization, are consistent with the stated purpose of scientific data management.
[EXTERNAL_DOWNLOADS]: The skill references the well-known and trusted Python 'requests' library in its code examples for performing HTTP operations. No suspicious or unverified third-party dependencies are introduced.
[CREDENTIALS_SAFE]: The documentation follows best practices for authentication by using placeholders like 'YOUR_TOKEN' and advising users to store access tokens securely, avoiding hardcoded secrets.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from the protocols.io platform, such as protocol descriptions and user comments, which could theoretically contain malicious instructions.
Ingestion points: Data is ingested via 'GET' requests to protocols, comments, and workspace files (e.g., in protocols_api.md and discussions.md).
Boundary markers: No specific boundary markers or instructions to ignore embedded content are provided in the documentation.
Capability inventory: The skill has the capability to write data back to the service (e.g., POST /protocols, POST /workspaces/{id}/files/upload) and perform network operations via the API.
Sanitization: No explicit sanitization of the platform-provided content is mentioned before it is processed by the agent.

protocolsio-integration