Browse Skills

BindCraft designs protein binders using end-to-end optimization with built-in AF2 validation. Use it for production-quality binder campaigns with joint backbone and sequence optimization.

Binder Design helps choose between BoltzGen, BindCraft, RFdiffusion, and Germinal for de novo protein binder design, then guides target preparation, hotspot selection, generation, and filtering with validation metrics.

AI Pentest provides an offensive AI/LLM security checklist covering prompt injection, jailbreaking, model extraction, training data poisoning, adversarial inputs, and AI reconnaissance. Use it when assessing AI/ML systems, red-teaming LLMs, or researching AI attack vectors.

Compute Ladder organizes model selection by provider health, using Tier 0 local models for most tasks and paid models only as break-glass. It triggers fallback on 429, timeout, or stream death—never on perceived task difficulty.

Create Agent creates and configures agent.yaml files, writes SOUL.md personality definitions, and sets up agent directory structures with skills, tools, and knowledge. Use it when you need to configure an agent, set up its skills and knowledge, or customize agent settings.

Export & Import Agents converts agent definitions between frameworks such as Claude Code, OpenAI, CrewAI, Lyzr, and GitHub Models, and imports from Claude, Cursor, and CrewAI projects.

Get Started with GitAgent guides installation of gitagent and creation of a first agent using scaffolding, configuration, and validation. Use when new to gitagent or setting up an initial agent.

Knowledge Retrieval performs semantic search over ingested documents using RAG (LlamaIndex/ChromaDB or Foundational RAG). Use it to find information in PDFs, whitepapers, or technical documentation when domain-specific knowledge is not available on the open web.

Manage Skills searches the SkillsMP registry, installs skills locally or globally, creates custom skills with SKILL.md frontmatter, and manages the skill lifecycle. Use it when you need to find, install, create, or inspect agent skills.

Narco-Check audits an agent's memory for hallucinations, circular confirmations, and state poisoning when triggered by repeated failures or the nightly deep dive. It grounds checks in real system state and flags poisoned memory entries before proceeding.

Run Agent configures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Use it to run an agent locally, from a remote git repository, or with a one-shot prompt while switching LLM providers or configuring adapter settings.

Azure AI Agents Persistent .NET is a low-level .NET SDK for creating and managing persistent AI agents with threads, messages, runs, and tools. Use it for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter.