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/src/task/executor.ts

@@ -2315,7 +2315,7 @@ export async function runSubprocess(options: ExecutorOptions): Promise<SingleRes
 			// Autoload skills via sendCustomMessage (same mechanic as /skill:<name>)
 			if (options.autoloadSkills?.length) {
 				for (const skill of options.autoloadSkills) {
-					const { message } = await buildSkillPromptMessage(skill, "");
+					const { message } = await buildSkillPromptMessage(skill, "", "autoload");
 					await session.sendCustomMessage(
 						{
 							customType: SKILL_PROMPT_MESSAGE_TYPE,