Initial commit: OpenClaw Skill Collection

6 custom skills (assign-task, dispatch-webhook, daily-briefing,
task-capture, qmd-brain, tts-voice) with technical documentation.
Compatible with Claude Code, OpenClaw, Codex CLI, and OpenCode.

openclaw-knowhow-skill/output/openclaw-docs_data/pages/LLM_Task_c10ff20aa7.json

@@ -0,0 +1,52 @@
+{
+  "title": "LLM Task",
+  "content": "`llm-task` is an **optional plugin tool** that runs a JSON-only LLM task and\nreturns structured output (optionally validated against JSON Schema).\n\nThis is ideal for workflow engines like Lobster: you can add a single LLM step\nwithout writing custom OpenClaw code for each workflow.\n\n1. Enable the plugin:\n\n2. Allowlist the tool (it is registered with `optional: true`):\n\n`allowedModels` is an allowlist of `provider/model` strings. If set, any request\noutside the list is rejected.\n\n* `prompt` (string, required)\n* `input` (any, optional)\n* `schema` (object, optional JSON Schema)\n* `provider` (string, optional)\n* `model` (string, optional)\n* `authProfileId` (string, optional)\n* `temperature` (number, optional)\n* `maxTokens` (number, optional)\n* `timeoutMs` (number, optional)\n\nReturns `details.json` containing the parsed JSON (and validates against\n`schema` when provided).\n\n## Example: Lobster workflow step\n\n* The tool is **JSON-only** and instructs the model to output only JSON (no\n  code fences, no commentary).\n* No tools are exposed to the model for this run.\n* Treat output as untrusted unless you validate with `schema`.\n* Put approvals before any side-effecting step (send, post, exec).",
+  "code_samples": [
+    {
+      "code": "2. Allowlist the tool (it is registered with `optional: true`):",
+      "language": "unknown"
+    },
+    {
+      "code": "## Config (optional)",
+      "language": "unknown"
+    },
+    {
+      "code": "`allowedModels` is an allowlist of `provider/model` strings. If set, any request\noutside the list is rejected.\n\n## Tool parameters\n\n* `prompt` (string, required)\n* `input` (any, optional)\n* `schema` (object, optional JSON Schema)\n* `provider` (string, optional)\n* `model` (string, optional)\n* `authProfileId` (string, optional)\n* `temperature` (number, optional)\n* `maxTokens` (number, optional)\n* `timeoutMs` (number, optional)\n\n## Output\n\nReturns `details.json` containing the parsed JSON (and validates against\n`schema` when provided).\n\n## Example: Lobster workflow step",
+      "language": "unknown"
+    }
+  ],
+  "headings": [
+    {
+      "level": "h2",
+      "text": "Enable the plugin",
+      "id": "enable-the-plugin"
+    },
+    {
+      "level": "h2",
+      "text": "Config (optional)",
+      "id": "config-(optional)"
+    },
+    {
+      "level": "h2",
+      "text": "Tool parameters",
+      "id": "tool-parameters"
+    },
+    {
+      "level": "h2",
+      "text": "Output",
+      "id": "output"
+    },
+    {
+      "level": "h2",
+      "text": "Example: Lobster workflow step",
+      "id": "example:-lobster-workflow-step"
+    },
+    {
+      "level": "h2",
+      "text": "Safety notes",
+      "id": "safety-notes"
+    }
+  ],
+  "url": "llms-txt#llm-task",
+  "links": []
+}