Skip to content
mcp/skillhub

Agent Skill

Add Ollama Tool skill

add-ollama-toolnanocoai/nanoclaw.claude/skills/add-ollama-tool/SKILL.md

Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.

31kMIT

always on

28 tokname + description

once used

3,033 tokSKILL.md body

bundled files

54 scripts

repo stars

31kGitHub

Install the Add Ollama Tool skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/nanocoai/nanoclaw --skill add-ollama-tool

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/nanocoai/nanoclaw.git /tmp/nanoclaw
mkdir -p ~/.claude/skills
cp -R /tmp/nanoclaw/.claude/skills/add-ollama-tool ~/.claude/skills/add-ollama-tool

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description28 tok
When the agent uses itThe SKILL.md instructions3,033 tok
Only if opened5 bundled files (21 KB)varies

Until it is used, add-ollama-tool costs about 49× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 64 skills from nanocoai/nanoclaw would load 3,369 tokens of descriptions. Skills vs MCP study

Checks

  • Ships scripts the agent can run. Read them before installing.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Add Ollama Integration
  • Phase 1: Pre-flight
  • Check if already applied
  • Check prerequisites
  • Phase 2: Apply Code Changes
  • Copy the skill's source and tests into both trees
  • Register the MCP server in the agent-runner
  • Forward host env vars into the container
  • Surface [OLLAMA] log lines at info level
  • Add env-var stubs to .env.example
  • Validate code changes
  • Phase 3: Configure
  • Enable library-management tools (optional)
  • Set Ollama host (optional)
  • Restart the service
  • Phase 4: Verify
  • Test inference
  • Test model management (if enabled)
  • Check logs if needed
  • Troubleshooting
  • Agent says "Ollama is not installed" or tries to run a CLI
  • "Failed to connect to Ollama"
  • model not found / 404 on generate
  • ollamapullmodel times out on large models

More skills from nanocoai/nanoclaw

All skills in this repo
  1. add-anydocnanocoai/nanoclaw

    Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.

    31k164 tok idle · 1,758 in use
  2. add-atomic-chat-toolnanocoai/nanoclaw

    Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.

    31k433 tok idle · 2,544 in use
  3. add-clidashnanocoai/nanoclaw

    Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.

    31k2287 tok idle · 1,726 in use
  4. add-codexnanocoai/nanoclaw

    Use Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, vault-only via the selected gateway. Per-group via `ncl groups config update --provider codex`. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

    31k1992 tok idle · 2,392 in use
  5. add-cursornanocoai/nanoclaw

    Use Cursor (local Agent SDK) as a full agent provider — planning, tool orchestration, MCP tools, session resume — alongside or instead of Claude. Cursor-account sign-in or API key, held by the credential gateway. Per-group via `ncl groups config update --provider cursor`. Distinct from using Cursor as a cloud agent (those run on Cursor VMs and are not this provider).

    31k1984 tok idle · 2,979 in use
  6. add-dashboardnanocoai/nanoclaw

    Add a monitoring dashboard to NanoClaw. Installs @nanoco/nanoclaw-dashboard and a pusher that sends periodic JSON snapshots.

    31k332 tok idle · 1,317 in use
  7. add-deltachatnanocoai/nanoclaw

    Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.

    31k38 tok idle · 2,646 in use
  8. add-dialnanocoai/nanoclaw

    Add Dial channel integration — a real phone number for SMS and AI voice calls via the Dial platform (getdial.ai). Native adapter — no Chat SDK bridge.

    31k curl|sh36 tok idle · 5,544 in use