MITupdated 7d ago
is notation. Replace it with a concrete absolute plugin root before every resource read or command:
Ollama で何ができる?
name: ollama description: "Delegates an explicit analysis, review, or second-opinion request after checking the configured Ollama endpoint and requiring consent for non-loopback destinations. Use only when the user asks for Ollama; do not start a server or download a model without consent." argument-hint: "" disable-model-invocation: true
Ollama
Plugin Resource Resolution
<PLUGIN_ROOT> is notation. Replace it with a concrete absolute plugin root
before every resource read or command:
- Codex: Start from the directory containing the absolute selected
SKILL.mdpath, then ascend two directories (skills/<name>to plugin root). - Claude Code: Bind it to the injected
${CLAUDE_PLUGIN_ROOT}value.
Read both files completely, then apply the adapter while following the command body:
<PLUGIN_ROOT>/lib/codex-command-adapter.md<PLUGIN_ROOT>/commands/ollama.md
インストール
Ollama をクライアントに追加します。お使いのものを選んでください。
npx skills add gopherguides/gopher-aiInstalls every skill in the repository, then prompts for which to keep.
/plugin marketplace add gopherguides/gopher-aiAdds the repository as a plugin marketplace; install individual plugins with `/plugin install`.
git clone https://github.com/gopherguides/gopher-ai
cp -r plugins/llm-tools/skills/ollama ~/.claude/skills/A skill is a plain directory. Copy it into `.claude/skills/` in a project or in your home directory.
スコア
65 / 100
良好