feat(core): add skill persistence layer for cross-session learning

.claude/skills/learned/SKILL.md

@@ -0,0 +1,73 @@
+---
+name: learned-skills-index
+description: Index directory for automatically learned skills from execution feedback
+type: index
+---
+
+# Learned Skills Index
+
+This directory contains skills that have been automatically extracted from successful
+execution sessions. These skills represent patterns that led to quality improvements
+and are available for retrieval in future tasks.
+
+## How Skills Are Learned
+
+1. **Execution**: Claude Code runs a task with `--loop` enabled
+2. **Feedback Collection**: Each iteration's quality scores and improvements are recorded
+3. **Pattern Extraction**: Successful patterns are extracted from quality-improving iterations
+4. **Skill Generation**: Patterns are compiled into a learnable skill definition
+5. **Promotion Gate**: Skills must meet quality thresholds before promotion
+
+## Skill Status
+
+| Status | Meaning |
+|--------|---------|
+| **Pending** | Skill extracted but not yet promoted (needs more validation) |
+| **Promoted** | Skill has been validated and can be applied to new tasks |
+| **Archived** | Skill deprecated or superseded by newer learning |
+
+## Quality Thresholds for Promotion
+
+- Minimum quality score: 85.0
+- Minimum successful applications: 2
+- Minimum success rate: 70%
+
+## Directory Structure
+
+```
+learned/
+├── SKILL.md                    # This index file
+├── learned-backend-auth/       # Example learned skill
+│   ├── SKILL.md               # Skill definition
+│   └── metadata.json          # Machine-readable metadata
+└── learned-frontend-form/      # Another learned skill
+    ├── SKILL.md
+    └── metadata.json
+```
+
+## Integration
+
+Learned skills are automatically retrieved based on:
+- Task description keywords
+- File types being modified
+- Domain context
+
+To manually query learned skills:
+```python
+from core.skill_persistence import retrieve_skills_for_task
+
+skills = retrieve_skills_for_task(
+    task_description="your task here",
+    domain="backend"  # optional
+)
+```
+
+## Safety
+
+All learned skills include full provenance:
+- Source session ID
+- Source repository
+- Timestamp of learning
+- Quality progression
+
+This enables rollback and audit of any behavioral changes from learned skills.

.claude/skills/sc-implement/SKILL.md

@@ -88,8 +88,52 @@ This skill requires evidence. You MUST:
 /sc:implement "enterprise auth system" --orchestrate --strategy systematic --delegate
 ```
 
+## Loop Mode & Learning
+
+When using `--loop`, this skill integrates with the skill persistence layer for cross-session learning:
+
+### How Learning Works
+
+1. **Feedback Recording** - Each iteration's quality scores and improvements are persisted
+2. **Skill Extraction** - Successful patterns are extracted when quality threshold is met
+3. **Skill Retrieval** - Relevant learned skills are injected into subsequent tasks
+4. **Effectiveness Tracking** - Applied skills are tracked for success rate
+
+### Loop Flags
+
+| Flag | Type | Default | Description |
+|------|------|---------|-------------|
+| `--loop` | int | 3 | Enable iterative improvement (max 5) |
+| `--learn` | bool | true | Enable learning from this session |
+| `--auto-promote` | bool | false | Auto-promote high-quality skills |
+
+### Example with Learning
+
+```bash
+# Iterative implementation with learning
+/sc:implement auth flow --loop 3 --learn
+
+# View learned skills
+python scripts/skill_learn.py '{"command": "stats"}'
+
+# Retrieve relevant skills
+python scripts/skill_learn.py '{"command": "retrieve", "task": "auth"}'
+```
+
+### Learned Skills Location
+
+Promoted skills are stored in:
+```
+.claude/skills/learned/
+├── SKILL.md                    # Index
+├── learned-backend-auth/       # Example promoted skill
+│   ├── SKILL.md
+│   └── metadata.json
+```
+
 ## Resources
 
 - [PERSONAS.md](PERSONAS.md) - Available persona definitions
 - [scripts/select_agent.py](scripts/select_agent.py) - Agent selection logic
 - [scripts/evidence_gate.py](scripts/evidence_gate.py) - Evidence validation
+- [scripts/skill_learn.py](scripts/skill_learn.py) - Skill learning management