Individual skill
crestapps-core-ollama
Skill for running local and self-hosted Ollama models in CrestApps.Core 2.0. Covers AddOllama and AddCoreAIOllama registration, connections with the Ollama client name and a required Endpoint, configured chat and embedding deployments that declare model capabilities through Features instead of the removed Purpose or Type, declaring toolCalling only for models that support tools, deployment slots resolved with ResolveSlotAsync, Docker and model pulling, unsupported image, speech and realtime clients, and upgrading from 1.x. Use it for local development, offline or air-gapped hosts, and privacy-sensitive workloads, or when troubleshooting missing endpoints, skipped deployments, tool calls that never happen, or slow local responses.
src/CrestApps.AgentSkills/crestapps-core/crestapps-core-ollama/SKILL.md
Source commit d86d04f234b1b2bd8145368a2544490f9d557596
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 13
- Repository last updated
- Oct 21, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai Repository topic
- ai-agents-framework Repository topic
- dotnet Repository topic
- mcp Repository topic
- mcp-server Repository topic
- orchardcore Repository topic
- devops Derived category
- devops-containers Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Read excerpt
# CrestApps.Core Ollama
The `CrestApps.Core.AI.Ollama` package uses `OllamaApiClient` (OllamaSharp) to talk to a local or self-hosted Ollama server. No API key is involved; data stays on your infrastructure.
## Guidelines
- Use Ollama for local development, offline work, and privacy-sensitive scenarios.
- The connection's `Endpoint` is required. There is no built-in default; a connection without one fails when a client is created.
- Capabilities are model-dependent. Declare `toolCalling` only for models that support tools (for example `llama3.1`, `llama3.2`, `qwen2.5`, `mistral`), and `imageInput` only for multimodal models such as `llava`.
- Only chat and embeddings are supported. Image generation, speech-to-text, text-to-speech and realtime are not; put those on another provider and resolve them through their slots.
- Pull a model before configuring a deployment that names it.
## Registration
