feat: add development and hf-hangman-lab skills

development: absorbed openclaw-plugin-dev as a workflow, with
reference docs for plugin structure, hooks, tools, state, config.

hf-hangman-lab: hf-wakeup workflow — full agent wakeup lifecycle:
set busy → check due slots → select & defer → identify task →
plan work → create work channel → execute. All branches end with
status reset to idle.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

development/docs/tools.md

@@ -0,0 +1,40 @@
+# Tool Registration
+
+## Interface
+
+```typescript
+// Without agent context
+api.registerTool({
+  name: "my-tool",
+  description: "Does something",
+  inputSchema: {
+    type: "object",
+    properties: {
+      param: { type: "string", description: "..." },
+    },
+    required: ["param"],
+  },
+  execute: async (toolCallId, params) => {
+    const { param } = params as { param: string };
+    return { result: "ok" };
+  },
+});
+
+// With agent context (factory function)
+api.registerTool((ctx) => ({
+  name: "my-contextual-tool",
+  description: "...",
+  inputSchema: { /* ... */ },
+  execute: async (toolCallId, params) => {
+    const agentId = ctx.agentId;
+    return { result: agentId };
+  },
+}));
+```
+
+## Key Points
+
+- Interface is `execute: async (toolCallId, params)`, NOT `handler:`
+- Use `inputSchema` (JSON Schema), NOT `parameters`
+- Return `{ result: "..." }` object
+- Factory form `(ctx) => ({...})` gives access to agent context (agentId, sessionKey, etc.)