Trait Learning

Use when working with trait extraction, place enrichment, or the learning loop. Load for understanding how the system learns from gameplay, how traits are extracted from Nominatim + player sessions, async queue processing, and LLM prompt configuration. Covers update_place_traits, pgmq, and edge function flow.

8 stars 3 forksLearning & Education Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add Freddy-CHEN-ux/00_claude_skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Freddy-CHEN-ux/00_claude_skills --skill trait-learning
Manual install
git clone --depth 1 https://github.com/Freddy-CHEN-ux/00_claude_skills.git /tmp/00_claude_skills
mkdir -p ~/.claude/skills
cp -r /tmp/00_claude_skills/skills/trait-learning ~/.claude/skills/trait-learning

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Trait Learning

How the system learns from gameplay and enriches places with traits.

> **Announce:** "I'm using trait-learning to understand the learning mechanism."

## Learning Loop Overview

```
Player completes game
        ↓
    Trigger fires (on correct submission)
        ↓
    Job queued to pgmq.trait_extraction
        ↓
    Edge function called via pg_net
        ↓
    update_place_traits() executes
        ↓
    LLM curates traits from all sources
        ↓
    Place traits replaced with new set
```

## Data Sources for Learning

The LLM receives all available context when extracting traits:

```sql
-- 1. Nominatim data (class, type, extratags)
v_nominatim_data := game_logic.fetch_nominatim_place(v_place.osm_id);

-- 2. Session descriptions (what players typed)
SELECT array_agg(DISTINCT description)
FROM game_sessions
WHERE place_id = p_place_id;

-- 3. Game answers (confirmed yes/no from gameplay)
-- Format: "+ trait text" for yes, "- trait text" for no
SELECT array_agg(
  CASE WHEN ga.answer = 'yes' THEN '+ ' || t.clause
       WHEN ga.answer = 'no' THEN '- ' || t.clause
  END
)
FROM game_answers ga
JOIN traits t ON t.id = ga.trait_id;

-- 4. Existing traits (for review/curation)
SELECT array_agg(t.clause)
FROM place_traits pt
JOIN traits t ON t.id = pt.trait_id;
```

## Trait Table Schema
Read the full skill on GitHub

Details

Skill name
trait-learning
Path
skills/trait-learning/SKILL.md
Repo updated
10 January 2026

FAQ

What does the Trait Learning skill do?

Use when working with trait extraction, place enrichment, or the learning loop. Load for understanding how the system learns from gameplay, how traits are extracted from Nominatim + player sessions, async queue processing, and LLM prompt configuration. Covers update_place_traits, pgmq, and edge function flow.

How do I install the Trait Learning skill?

Claude Code plugin: /plugin marketplace add Freddy-CHEN-ux/00_claude_skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Trait Learning popular?

It lives in Freddy-CHEN-ux/00_claude_skills, which has 8 GitHub stars and 3 forks.

Related skills

Add Integration

8

Freddy-CHEN-ux/00_claude_skills

Build a new API integration for Nexus. Load when user mentions "add integration", "new integration", "integrate with", "connect to [service]", or "build [service] integration". Interactive workflow that discovers API endpoints, plans the integration, and creates a project for implementation.

Software Development

AI Agents

8

Freddy-CHEN-ux/00_claude_skills

Production-grade AI agent patterns with MCP integration, agentic RAG, handoff orchestration, multi-layer guardrails, and observability (modern best practices)

AI, LLMs & Agents

AI LLM

8

Freddy-CHEN-ux/00_claude_skills

Production LLM engineering skill. Covers strategy selection (prompting vs RAG vs fine-tuning), dataset design, PEFT/LoRA, evaluation workflows, deployment handoff to inference serving, and lifecycle operations with cost/safety controls.

AI, LLMs & Agents

Student Exam Analysis

5

eshmith7/claude-skills-library

Turn past papers into weightage by marks, reliability bands, repeated question patterns and a strategy for what to finish first. Use for past papers, weightage or exam pattern.

Learning & Education

Teaching

5

vnovakovits/claude-skills

Teach a concept, language, library, codebase or technique over one or many sessions so that it sticks, using the evidence on how people learn. The learner does the thinking (generation, retrieval practice), reviews are spaced and interleaved, new material starts from what the learner already knows, worked examples fade into problems as skill grows, and understanding is checked by prediction and explanation rather than "does that make sense?". In a working directory it keeps a learning plan, a session log and a spaced-review queue, so a later session picks up where the last one stopped. Draws o

Learning & Education

Student Mistake Log

5

eshmith7/claude-skills-library

Classify every wrong answer as concept, application, execution or time, find the pattern across tests, and produce three ranked fixes. Use for test review or mistake analysis.

Learning & Education

Browse the most popular Claude skills, all learning & education skills, or write your own with the skills generator.