/nav-profile

name: nav-profile
description: Manage user preferences and corrections for bilateral modeling. Auto-learns from session corrections. Use when user says "save my preferences", "remember I like...", or auto-triggers after corrections.
allowed-tools: Read, Write, Edit, Bash
version: 1.0.0

Navigator Profile Skill

Manage user preferences for bilateral modeling - enabling Claude to understand and adapt to your working style, technical preferences, and past corrections.

Why This Exists (Theory of Mind)

Based on Riedl & Weidmann 2025 research on Human-AI Synergy:

• Theory of Mind (ToM) is the key differentiator in human-AI collaboration success
• Users with higher ToM achieve 23-29% performance boost
• **Bilateral modeling** completes the ToM loop: Claude models you, you model Claude

This skill enables Claude to:

• Remember your preferences across sessions
• Learn from corrections without you repeating them
• Adapt communication style to your level
• Build a persistent mental model of YOU

When to Invoke

**Auto-invoke when**:

• User says "save my preferences", "remember I like..."
• User says "update my profile", "change my preference for..."
• After detecting a correction pattern (auto-learn mode)
• User says "show my profile", "what do you know about me?"

**DO NOT invoke if**:

• User is creating a context marker (use nav-marker)
• User wants session-specific preferences only
• User explicitly says "just for this session"

Profile Location

`.agent/.user-profile.json` (git-ignored, session-persistent)

Execution Steps

Step 1: Determine Action

**SHOW** (viewing profile):

User: "Show my profile", "What do you remember about me?"
→ Display current profile

**UPDATE** (explicit preference):

User: "Remember I prefer functional style", "Save that I like concise explanations"
→ Update specific preference

**LEARN** (auto-detect correction):

[Internal trigger after correction detected]
→ Extract and save correction pattern

**RESET** (clear profile):

User: "Reset my profile", "Clear my preferences"
→ Confirm and delete profile

Step 2: Load or Initialize Profile

**Check if profile exists**:

if [ -f ".agent/.user-profile.json" ]; then
  echo "Profile exists"
else
  echo "No profile found, will create new"
fi

**Initialize new profile** (if not exists):

{
  "version": "1.0",
  "created": "{YYYY-MM-DD}",
  "last_updated": "{YYYY-MM-DD}",
  "preferences": {
    "communication": {
      "verbosity": "balanced",
      "confirmation_threshold": "high-stakes",
      "explanation_style": "examples"
    },
    "technical": {
      "preferred_frameworks": [],
      "code_style": "mixed",
      "testing_preference": "tdd"
    },
    "workflow": {
      "autonomous_commits": true,
      "auto_compact_threshold": 80,
      "marker_before_risky": true
    }
  },
  "corrections": [],
  "goals": []
}

Step 3A: Show Profile (If SHOW Action)

**Display current profile**:

Your Navigator Profile
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Communication Preferences:
- Verbosity: {verbosity}
- Confirmation: {confirmation_threshold} (when to verify understanding)
- Explanations: {explanation_style}

Technical Preferences:
- Preferred frameworks: {frameworks or "none set"}
- Code style: {code_style}
- Testing: {testing_preference}

Workflow Preferences:
- Autonomous commits: {autonomous_commits}
- Auto-compact at: {auto_compact_threshold}% context
- Markers before risky changes: {marker_before_risky}

Learned Corrections ({count}):
{recent_corrections_list}

Active Goals ({count}):
{active_goals_list}

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Last updated: {last_updated}

Step 3B: Update Profile (If UPDATE Action)

**Parse preference from user input**:

User: "Remember I prefer functional style"
→ Category: technical
→ Field: code_style
→ Value: functional

User: "I like concise explanations"
→ Category: communication
→ Field: verbosity
→ Value: concise

**Map common expressions to profile fields**:

| User Says | Category | Field | Value | |-----------|----------|-------|-------| | "concise", "brief", "short" | communication | verbosity | concise | | "detailed", "thorough" | communication | verbosity | detailed | | "always confirm" | communication | confirmation_threshold | always | | "skip confirmations" | communication | confirmation_threshold | never | | "functional style" | technical | code_style | functional | | "OOP style" | technical | code_style | oop | | "prefer React" | technical | preferred_frameworks | [append "react"] | | "prefer Express" | technical | preferred_frameworks | [append "express"] |

**Update and save**:

// Update specific field
profile.preferences[category][field] = value;
profile.last_updated = "{YYYY-MM-DD}";

// Write to file
Write(".agent/.user-profile.json", JSON.stringify(profile, null, 2));

**Confirm update**:

✅ Profile updated!

Changed: {category}.{field}
From: {old_value}
To: {new_value}

This will affect future sessions.

Step 3C: Auto-Learn Correction (If LEARN Action) [AUTO-TRIGGER]

**IMPORTANT**: This action triggers automatically - no explicit skill invocation needed.

**When to detect corrections** (monitor ALL conversations):

• User says "No, I meant...", "Actually...", "Not X, use Y"
• User repeats a correction they gave before
• User shows frustration at repeated mistake

**Trigger patterns to watch for**:

"No, ..." → Direct correction
"I said ..." → Repeated instruction
"Actually, ..." → Clarification
"Not X, Y" → Substitution
"Always use ..." → Rule establishment
"Never do ..." → Anti-pattern
"I prefer ..." → Preference

**When detected**:

User: "No, I meant plural /users not /user"
→ Correction detected: REST naming convention preference
→ Auto-save to profile (silent)

**Extract correction pattern**:

correction = {
  "date": "{YYYY-MM-DD}",
  "context": "{what we were doing}",
  "original": "{what I s