fix(coding-agent): identify user-invoked skills and expose skill directory

User-invoked skills (typed /skill:, steered, follow-up, interrupted/
resumed via compaction, ACP, RPC) only appended a bare "Skill: <path>"
line, so the model neither learned the user had invoked that specific
skill nor where the skill directory was. Relative paths in skill bodies
(scripts/, templates/) could not be resolved.

Route all user-invoked paths through a self-identifying, baseDir-aware
prompt template; keep hidden autoload skills on the minimal non-user
format. Interactive skillCommands now carries the loaded Skill object
instead of a bare path so baseDir flows through without reconstruction.
The invocation kind defaults to "user" to keep buildSkillPromptMessage
source-compatible.

Op: correct
Restores: spec:user-invoked-skill-prompt-self-identifies-and-exposes-skill-directory

packages/coding-agent/test/rpc-skill-command.test.ts

@@ -33,6 +33,9 @@ describe("tryRunRpcSkillCommand", () => {
 		expect(handled).toEqual({ agentInvoked: true });
 		expect(message?.customType).toBe(SKILL_PROMPT_MESSAGE_TYPE);
 		expect(message?.content).toContain("Review the supplied code carefully.");
+		expect(message?.content).toContain('The user has invoked the "reviewer" skill');
+		expect(message?.content).toContain(`[Skill directory: ${dir}]`);
+		expect(message?.content).toMatch(/[Rr]esolve any relative paths/);
 		expect(message?.content).toContain("User: focus on risks");
 		expect(message?.display).toBe(true);
 		expect(message?.attribution).toBe("user");