chore: clean up legacy playbook references in engine crate

- Rename PLAYBOOK_MIN_STEPS/ACTIONS → SKILL_EXTRACTION_MIN_STEPS/ACTIONS
- Fix pattern DB uses DocType::Note instead of DocType::Playbook
- Update CLAUDE.md: skill-extraction mission, DocType list, module map

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

crates/ironclaw_engine/CLAUDE.md

@@ -33,7 +33,7 @@ src/
 │   ├── thread.rs         # Thread, ThreadId, ThreadState (state machine), ThreadType, ThreadConfig
 │   ├── step.rs           # Step, StepId, LlmResponse, ActionCall, ActionResult, TokenUsage
 │   ├── capability.rs     # Capability, ActionDef, EffectType, CapabilityLease, PolicyRule
-│   ├── memory.rs         # MemoryDoc, DocId, DocType (Summary/Lesson/Playbook/Issue/Spec/Note)
+│   ├── memory.rs         # MemoryDoc, DocId, DocType (Summary/Lesson/Playbook[legacy]/Skill/Issue/Spec/Note)
 │   ├── project.rs        # Project, ProjectId
 │   ├── event.rs          # ThreadEvent, EventKind (18 variants for event sourcing)
 │   ├── message.rs        # ThreadMessage, MessageRole
@@ -48,7 +48,9 @@ src/
 ├── capability/           # Capability management
 │   ├── registry.rs       # CapabilityRegistry — register/get/list capabilities
 │   ├── lease.rs          # LeaseManager — grant/check/consume/revoke/expire leases
-│   └── policy.rs         # PolicyEngine — deterministic effect-level allow/deny/approve + provenance taint
+│   ├── policy.rs         # PolicyEngine — deterministic effect-level allow/deny/approve + provenance taint
+│   ├── skill_selector.rs # SkillSelector — MemoryDoc→LoadedSkill bridge, deterministic selection
+│   └── skill_tracker.rs  # SkillTracker — confidence tracking, versioned updates, rollback
 ├── runtime/              # Thread lifecycle management
 │   ├── manager.rs        # ThreadManager — spawn, stop, inject messages, join threads
 │   ├── conversation.rs   # ConversationManager — routes UI messages to threads
@@ -86,7 +88,7 @@ Validated by `ThreadState::can_transition_to()`. Terminal states: `Done`, `Faile
 Three event-driven missions fire automatically after thread completion:
 
 1. **Error diagnosis** (`self-improvement`) — fires when a thread completes with trace issues. Diagnoses root cause and applies prompt overlays or orchestrator patches.
-2. **Playbook extraction** (`playbook-extraction`) — fires when a thread succeeds with 5+ steps and 3+ tool actions. Extracts reusable step-by-step procedures.
+2. **Skill extraction** (`skill-extraction`) — fires when a thread succeeds with 5+ steps and 3+ tool actions. Extracts reusable skills with activation metadata, CodeAct code snippets, and domain tags. Output stored as `DocType::Skill` MemoryDoc.
 3. **Conversation insights** (`conversation-insights`) — fires every 5 completed threads in a project. Extracts user preferences, domain knowledge, and workflow patterns.
 
 Created by `MissionManager::ensure_learning_missions()` at project bootstrap.

crates/ironclaw_engine/src/runtime/mission.rs

@@ -282,10 +282,10 @@ impl MissionManager {
         let mgr = Arc::clone(self);
         let mut rx = mgr.thread_manager.subscribe_events();
 
-        /// Minimum steps for a thread to be a playbook candidate.
-        const PLAYBOOK_MIN_STEPS: usize = 5;
-        /// Minimum distinct action executions for playbook extraction.
-        const PLAYBOOK_MIN_ACTIONS: usize = 3;
+        /// Minimum steps for a thread to be a skill extraction candidate.
+        const SKILL_EXTRACTION_MIN_STEPS: usize = 5;
+        /// Minimum distinct action executions for skill extraction.
+        const SKILL_EXTRACTION_MIN_ACTIONS: usize = 3;
         /// Completed thread interval for conversation insights.
         const CONVERSATION_INSIGHTS_INTERVAL: u32 = 5;
 
@@ -390,8 +390,8 @@ impl MissionManager {
                             && trace.issues.iter().all(|i| {
                                 i.severity != crate::executor::trace::IssueSeverity::Error
                             })
-                            && thread.step_count >= PLAYBOOK_MIN_STEPS
-                            && action_count >= PLAYBOOK_MIN_ACTIONS
+                            && thread.step_count >= SKILL_EXTRACTION_MIN_STEPS
+                            && action_count >= SKILL_EXTRACTION_MIN_ACTIONS
                         {
                             let actions_used: Vec<String> = thread
                                 .events
@@ -549,7 +549,7 @@ impl MissionManager {
             use crate::types::memory::{DocType, MemoryDoc};
             let pattern_doc = MemoryDoc::new(
                 project_id,
-                DocType::Playbook,
+                DocType::Note,
                 FIX_PATTERN_DB_TITLE,
                 SEED_FIX_PATTERNS,
             )
@@ -946,7 +946,7 @@ async fn process_self_improvement_output(
         } else {
             MemoryDoc::new(
                 project_id,
-                DocType::Playbook,
+                DocType::Note,
                 FIX_PATTERN_DB_TITLE,
                 SEED_FIX_PATTERNS,
             )