identity-snapshot

name	identity-snapshot
description	Generate a living identity model from existing Amp data — working patterns, decision tendencies, quality preferences, and growth areas.

Identity Snapshot

Reads existing Amp data and synthesizes System/identity-model.md — a living document the system writes, not the user. This captures who you are as a professional based on your actual behavior, not self-reported traits.

When to Run

• Manually via /identity-snapshot
• Auto-triggered during /week-review (append identity model update to review workflow)

Data Sources

Read ALL of the following in parallel before synthesizing:

1. Quarter Goals — 01-Quarter_Goals/Quarter_Goals.md
   • What you're working toward, pillar distribution, ambition level
2. Week Priorities — 02-Week_Priorities/Week_Priorities.md
   • Recent 4 weeks of priorities (look for patterns in what gets prioritized)
3. Tasks — 03-Tasks/Tasks.md
   • Completion patterns, pillar distribution, velocity, what gets blocked
4. Session Learnings — System/Session_Learnings/*.md (last 30 days)
   • What you've learned, recurring themes
5. Mistake Patterns — 06-Resources/Learnings/Mistake_Patterns.md
   • Known failure modes, triggers, what to watch for
6. Skill Ratings — System/Skill_Ratings/ratings.jsonl
   • Which skills score highest, what you value in AI interactions
7. User Profile — System/user-profile.yaml
   • Existing identity data, communication preferences

Synthesis

Write to System/identity-model.md with this structure:

# Identity Model
*Auto-generated by Amp — last updated YYYY-MM-DD*

## Working Patterns
- Pillar balance: [distribution across pillars]
- Priority cadence: [how often priorities shift, what stays stable]
- Task velocity: [completion rate, average items per week]
- Peak focus areas: [what dominates recent weeks]

## Decision Tendencies
- Under pressure: [what gets prioritized vs deprioritized]
- Goal selection: [ambitious vs tactical, how goals evolve]
- Time allocation: [deep work vs meetings vs quick tasks]

## Quality Preferences
- Highest-rated skills: [from ratings.jsonl]
- What "good" looks like: [patterns from high ratings + notes]
- What frustrates: [patterns from low ratings + mistake patterns]

## Growth Areas
- Recurring gaps: [from mistake patterns, things that keep coming up]
- Skills under development: [from learnings, new capabilities being adopted]
- Blind spots: [pillars or areas consistently neglected]

## Communication Style
- Formality: [from profile + observed patterns]
- Decision speed: [fast/deliberate based on task patterns]
- Feedback preference: [from profile]

Rules

• Never ask the user for input. This is purely observational.
• Be specific. Use actual data points, not generic statements.
• Be honest. If a pillar is neglected, say so. If velocity dropped, note it.
• Date-stamp every generation. The model should show evolution over time.
• If any data source is missing or empty, note it as "[No data available]" and move on.