Agent skills for Codex CLI

Elicit confident, ungrounded fabrications from an LLM application — invented facts, fake citations, non-existent policies — and show they…

Treat LLM output as untrusted and encode it for the specific sink that consumes it — HTML/JS context encoding, parameterized queries…

Pydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.

Detect direct and indirect prompt-injection attempts and successful policy breaks against an LLM application from prompt/response telemetry.

Elicit sensitive information an LLM application should not reveal — training data, other users' data, secrets pulled into context, or…

LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with…

Manages lightweight, folder-based Markdown knowledge bases with fast offline vector search, BM25 indexing, and automated AI note ingestion.

Routine maintenance and safe commits. Use when committing changes, rebuilding indexes, or checking overall vault health.

Creates slash commands from procedural doc sections.

Bootstraps projects to production-ready structure.

Generates .NET Clean Architecture backend structure from entity definitions.

Removes platform-specific artifacts from Replit, StackBlitz, CodeSandbox, Glitch.

Removes all Replit artifacts from exported projects (configs, packages, code comments)

Generates Docker and docker-compose configuration for multi-container development

Builds and launches Docker containers with health verification using best practices

Researches competitive benchmarks and generates optimization hypotheses for identified bottlenecks.

Upgrades npm/yarn/pnpm dependencies with breaking change handling.

Replaces custom modules with OSS packages using atomic keep/discard testing.

Agent skill for load-balancer - invoke with $agent-load-balancer

Loads all 22 DataHub connector golden standards into context.

Loads internal CausalPy example datasets.