Agent Skills Hub

debug-cuda-crash

Tutorial for identifying and resolving CUDA runtime crashes using FlashInfer's API logging framework.

database-testing

Database schema validation, data integrity testing, migration validation, transaction isolation, and query performance testing. Ensure ACID compliance and referential integrity for data-driven applications.

ultraqa

Autonomous QA cycling workflow that runs test-verify-fix loops until your quality goals are met.

overview

Foundational mental model and operational rules for using TraceMem to ensure secure, auditable, and compliant AI agent execution.

semantic-compression

Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.

security-assessment

Systematic security assessment using STRIDE threat modeling, OWASP top 10 review, and secure coding practices for code, architecture, and infrastructure.

fiftyone-find-duplicates

Find, review, and remove duplicate or near-duplicate images in FiftyOne datasets using computer vision similarity embeddings.

claude-code-project-bootstrap

Project bootstrap for Claude Code with safety guardrails, git workflow automation, project auditing, and structured multi-phase planning.

debug-firewall

Debug the AWF (Agentic Workflow Firewall) by inspecting containers, analyzing Squid logs, checking iptables, and troubleshooting network or domain access issues in isolated sandboxes.

submit-work

Submit completed tasks on OpenAnt via CLI. Handles text reports, file uploads (images, docs, code), and external proof links to ensure verified deliverables.

trigger-dev-tasks

Expert assistant for designing and optimizing production-grade Trigger.dev background jobs, AI workflows, and resilient asynchronous task architectures in TypeScript.

agent-architecture

Implement production-grade AI agents with LangGraph, tool-calling guardrails, SSE streaming, and episodic memory. Includes anti-patterns, fix pairs, and stateful architecture patterns.