fix(skill): re-inject skill index into local-agent system prompt

The contributor's original PR (#1917) appended an ``Available Skills``
index to the system prompt before the LLM saw the user message, so the
LLM could decide whether to activate a skill. ``7145447b`` removed the
text-marker activation flow and, together with it, the entire system
prompt injection — but the Tool Call replacement only put the available
skills inside the ``activate`` tool's description. In practice the LLM
ignores tool descriptions for selection and goes straight to native
tools, so user-visible skill activation silently broke.

Restore the injection, adapted for the Tool Call era:

- SkillManager regains ``get_skill_index(bound_skills)`` and
  ``build_skill_aware_prompt_addition(bound_skills)``. The addendum
  carries only ``name (display_name): description`` for each
  pipeline-visible skill plus one instruction line pointing at the
  ``activate`` tool. No SKILL.md contents — KV cache stays clean
- PreProcessor appends the addendum to the first system message (or
  inserts a new one) of ``query.prompt.messages`` for the local-agent
  runner. Handles plain-string and ContentElement[] bodies. Skips
  cleanly when no skills are visible
- 3 new test_preproc cases: injection happens, bound-skills subset
  honoured, empty addendum touches nothing. 280 passed

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/langbot/pkg/pipeline/preproc/preproc.py

@@ -248,30 +248,67 @@ class PreProcessor(stage.PipelineStage):
         query.prompt.messages = event_ctx.event.default_prompt
         query.messages = event_ctx.event.prompt
 
-        # =========== Store bound skills for runtime visibility checks ===========
-        # Skills are now activated through the `activate` tool (Tool Call mechanism),
-        # not through system prompt injection. This aligns with Claude Code's design.
+        # =========== Skill awareness for the local-agent runner ===========
+        # The actual activation goes through the ``activate`` Tool Call so the
+        # LLM doesn't see full SKILL.md instructions until it commits to a
+        # skill (Claude Code's progressive disclosure). But the LLM still has
+        # to KNOW which skills exist to make that choice, so we:
+        #   1. resolve the pipeline's bound skills and stash them in
+        #      ``query.variables['_pipeline_bound_skills']`` for downstream
+        #      visibility checks (skill loader, native exec workdir);
+        #   2. inject a short ``Available Skills`` index (name + description
+        #      only) into the system prompt. The contributor's original PR
+        #      relied on this injection; without it the LLM never discovers
+        #      the skills are there and just calls native tools instead.
         if selected_runner == 'local-agent' and self.ap.skill_mgr:
-            # Get bound skills from pipeline extensions_preferences
             pipeline_data = await self.ap.pipeline_service.get_pipeline(query.pipeline_uuid)
             extensions_prefs = (pipeline_data or {}).get('extensions_preferences', {})
             enable_all_skills = extensions_prefs.get('enable_all_skills', True)
 
             if enable_all_skills:
-                bound_skills = None  # None = all skills available
+                bound_skills = None  # None = all loaded skills are visible
             else:
-                # Get specific bound skill names
                 bound_skills = extensions_prefs.get('skills', [])
 
-            # Store bound skills in query variables for runtime path visibility checks
             query.variables['_pipeline_bound_skills'] = bound_skills
 
-            loaded_count = len(self.ap.skill_mgr.skills)
-            self.ap.logger.debug(
-                f'Skills available for activate tool: '
-                f'pipeline={query.pipeline_uuid} '
-                f'loaded_skills={loaded_count} '
-                f'bound_skills={bound_skills or "all"}'
+            skill_addition = self.ap.skill_mgr.build_skill_aware_prompt_addition(
+                bound_skills=bound_skills,
             )
+            if skill_addition:
+                # Append to the first system message; create one if the
+                # prompt has none. Handles both plain-string and
+                # content-element (list) message bodies.
+                if query.prompt.messages and query.prompt.messages[0].role == 'system':
+                    head = query.prompt.messages[0]
+                    if isinstance(head.content, str):
+                        head.content = head.content + skill_addition
+                    elif isinstance(head.content, list):
+                        appended = False
+                        for ce in head.content:
+                            if getattr(ce, 'type', None) == 'text':
+                                ce.text = (ce.text or '') + skill_addition
+                                appended = True
+                                break
+                        if not appended:
+                            head.content.append(provider_message.ContentElement(type='text', text=skill_addition))
+                else:
+                    query.prompt.messages.insert(
+                        0,
+                        provider_message.Message(role='system', content=skill_addition.strip()),
+                    )
+                self.ap.logger.debug(
+                    f'Skill index injected into system prompt: '
+                    f'pipeline={query.pipeline_uuid} '
+                    f'bound_skills={bound_skills or "all"} '
+                    f'loaded_skills={len(self.ap.skill_mgr.skills)}'
+                )
+            else:
+                self.ap.logger.debug(
+                    f'No skills available for prompt injection: '
+                    f'pipeline={query.pipeline_uuid} '
+                    f'loaded_skills={len(self.ap.skill_mgr.skills)} '
+                    f'bound_skills={bound_skills}'
+                )
 
         return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)