agentleFS
davekilleendavekilleen/Dex/.agents/skills/identity-snapshot/SKILL.md

identity-snapshot

Skill509 starsChanged 3 months agoMITView on GitHub

Generate a living profile of the user's working patterns, decision tendencies and quality preferences from their Dex data. Use when the user says 'what are my patterns', 'how do I work', or during `week-review`. Also use proactively when the model (older than 7 days) is stale. Not for planning a week; use `week-plan`.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read ALL of the following in parallel before synthesizing:

    line 19
  2. Very specific:

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

    line 38
  3. Distinctive:

    Be specific: Use actual data points, not generic statements.

    line 74
  4. Distinctive:

    Be honest: If a pillar is neglected, say so.

    line 75
  5. Distinctive:

    If any data source is missing or empty, note it as "[No data available]" and move on.

    line 77

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Generated from `.claude/skills/identity-snapshot/SKILL.md` by `scripts/generate-agents-skills.py`. Do not edit. -->

Identity Snapshot

Reads existing Dex 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 Dex — 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.