Loading...
Loading...
Found 425 Skills
Safegres is Constructive's security protocol for expressing authorization as Authz* policy nodes (types + JSON configs). This skill defines each Authz* type, its config shape, semantics, and when to use it. No SQL and no SDK/grant/RLS steps.
LLM-as-a-judge HTTP/HTTPS proxy that secures AI agents by intercepting and evaluating outbound requests against security policies before they reach external APIs.
Query the memory system for relevant learnings from past sessions
Debug production render failures in telecine. Inspect render state in the database, Valkey queues, and Cloud Run logs. Restart failed renders, trace the render pipeline flow, and diagnose fragment-level failures.
Use when reviewing or writing new SQL/SQLAlchemy queries, especially in `backend/app/services/`, `backend/app/models/`, or migration files. Catches missing tenant filters, N+1 queries, async-session misuse, and missing indexes before they reach production. Trigger when the user says "review this query", "check for N+1", "is this query safe", or modifies repo-layer code.