docs: add openai-preset.md and align skill tables (#690)

Create docs/openai-preset.md mirroring opencode-go-preset.md so every shipped
preset has its own doc with a Skill Reference section. Add a Source column to
the README skill table and a clarifying note to opencode-go-preset.md (which
defines no skills).

README.md

@@ -168,10 +168,10 @@ The default generated configuration includes both `openai` and `opencode-go` pre
 
 ## Skill Reference
 
-| Skill | Description |
-| --- | --- |
-| `*` | All installed skills (wildcard) |
-| `simplify` | Code simplification |
+| Skill | Description | Source |
+| --- | --- | --- |
+| `*` | All installed skills (wildcard) | public |
+| `simplify` | Code simplification | public |
 
 ### For Alternative Providers
 

docs/openai-preset.md

@@ -0,0 +1,108 @@
+# OpenAI Preset
+
+`openai` is the bundled default generated preset. The installer generates both
+`openai` and `opencode-go` presets; OpenAI is active by default.
+
+## Install with OpenAI Active
+
+```bash
+bunx oh-my-opencode-slim@latest install
+```
+
+Then authenticate and refresh models:
+
+```bash
+opencode auth login
+opencode models --refresh
+```
+
+## Switch at Runtime
+
+If both presets are already in your config, switch from inside OpenCode:
+
+```text
+/preset openai
+```
+
+See [Preset Switching](preset-switching.md) for the full runtime switching
+workflow.
+
+## Bundled Model Mapping
+
+The generated `openai` preset maps each specialist to an OpenAI model tuned for
+its role:
+
+| Agent | Model |
+|-------|-------|
+| Orchestrator | `openai/gpt-5.5` (`medium`) |
+| Oracle | `openai/gpt-5.5` (`high`) |
+| Librarian | `openai/gpt-5.4-mini` (`low`) |
+| Explorer | `openai/gpt-5.4-mini` (`low`) |
+| Designer | `openai/gpt-5.4-mini` (`medium`) |
+| Fixer | `openai/gpt-5.5` (`low`) |
+
+## Generated Config Shape
+
+Your generated config includes `openai` under `presets` and activates it by
+setting the top-level `preset` field:
+
+```jsonc
+{
+  "preset": "openai",
+  "presets": {
+    "openai": {
+      "orchestrator": {
+        "model": "openai/gpt-5.5",
+        "variant": "medium",
+        "skills": ["*"],
+        "mcps": ["*", "!context7"]
+      },
+      "oracle": {
+        "model": "openai/gpt-5.5",
+        "variant": "high",
+        "skills": ["simplify"],
+        "mcps": []
+      },
+      "librarian": {
+        "model": "openai/gpt-5.4-mini",
+        "variant": "low",
+        "skills": [],
+        "mcps": ["websearch", "context7", "gh_grep"]
+      },
+      "explorer": {
+        "model": "openai/gpt-5.4-mini",
+        "variant": "low",
+        "skills": [],
+        "mcps": []
+      },
+      "designer": {
+        "model": "openai/gpt-5.4-mini",
+        "variant": "medium",
+        "skills": [],
+        "mcps": []
+      },
+      "fixer": {
+        "model": "openai/gpt-5.5",
+        "variant": "low",
+        "skills": [],
+        "mcps": []
+      }
+    }
+  }
+}
+```
+
+## Skill Reference
+
+Each skill is listed with a short description and its source. The config block
+above shows which agent uses it. `author` means the author's own third party
+skill (not part of the plugin); `public` means a public tool, framework, or MCP
+server.
+
+| Skill | Description | Source |
+| --- | --- | --- |
+| `*` | All installed skills (wildcard) | public |
+| `simplify` | Code simplification | public |
+
+For the complete configuration reference, see
+[Configuration](configuration.md).

docs/opencode-go-preset.md

@@ -88,5 +88,7 @@ setting the top-level `preset` field:
 }
 ```
 
+This preset defines no `skills` or `mcps` per agent. It relies on model selection only (see [Bundled Model Mapping](#bundled-model-mapping)); agents use whatever skills are globally installed.
+
 For the complete configuration reference, see
 [Configuration](configuration.md).