The Agent Skills Directory

[SAFE]: The skill acts as a developer reference for optimizing Linear API interactions. It contains legitimate technical patterns for caching and GraphQL query optimization using established libraries.
[INDIRECT_PROMPT_INJECTION]: The skill describes methods for processing data retrieved from the Linear API, which is an external and untrusted data source.
- Ingestion points: Data is ingested via various Linear API calls (e.g., fetching issues, teams, and workflow states) across all provided files.
- Boundary markers: The reference code does not include specific boundary markers or instructions to ignore potential commands embedded in issue titles or descriptions.
- Capability inventory: The skill facilitates Read, Write, Edit, and Grep operations via the agent environment.
- Sanitization: Code examples show basic string escaping for GraphQL queries, which serves as a minimal mitigation against simple injection attempts.
[CREDENTIALS_UNSAFE]: The skill correctly demonstrates the use of environment variables (LINEAR_API_KEY, REDIS_URL) for credential management, avoiding hardcoded secrets in scripts or configuration.

linear-performance-tuning