Game Scoring

Use when working with candidate scoring, confidence calculation, softmax aggregation, or guess decision logic. Load for understanding how candidates are ranked, when the system decides to guess, and how semantic + geographic scores combine. Covers temperature tuning, entropy thresholds, and margin logic.

8 stars 3 forksOther 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 game-scoring
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/game-scoring ~/.claude/skills/game-scoring

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

From the SKILL.md

# Game Scoring

Scoring and confidence calculation patterns specific to this game.

> **Announce:** "I'm using game-scoring to understand scoring logic correctly."

## Scoring Pipeline Overview

```
Player Description
       ↓
   Embedding
       ↓
Semantic Similarity (per place)
       ↓
Geographic Filtering (include/exclude regions)
       ↓
Combined Score + Softmax
       ↓
Confidence Metrics (max_prob, margin, entropy)
       ↓
Decision: Ask Question or Guess?
```

## Semantic Similarity

Traits are matched via embedding similarity:

```sql
-- For each place, calculate trait similarity
WITH trait_similarities AS (
  SELECT 
    pt.place_id,
    1 - (te.embedding <=> v_description_embedding) AS similarity
  FROM place_traits pt
  JOIN embeddings te ON te.id = pt.embedding_id
)
```

## Softmax Aggregation

**NOT simple average.** Softmax lets top traits dominate:

```sql
-- Softmax-weighted average
WITH softmax_weights AS (
  SELECT 
    place_id,
    similarity,
    exp(similarity / v_temperature) AS exp_sim,
    SUM(exp(similarity / v_temperature)) OVER (PARTITION BY place_id) AS sum_exp
  FROM trait_similarities
)
SELECT 
  place_id,
  SUM((exp_sim / sum_exp) * similarity) AS aggregated_score
FROM softmax_weights
GROUP BY place_id;
```

**Temperature effect:**
- Low (0.1): Top traits dominate strongly
- High (1.0): All traits contribute more equally

## Confidence Metrics

Three metrics determine when to guess:
Read the full skill on GitHub

Details

Skill name
game-scoring
Path
skills/game-scoring/SKILL.md
Repo updated
10 January 2026

FAQ

What does the Game Scoring skill do?

Use when working with candidate scoring, confidence calculation, softmax aggregation, or guess decision logic. Load for understanding how candidates are ranked, when the system decides to guess, and how semantic + geographic scores combine. Covers temperature tuning, entropy thresholds, and margin logic.

How do I install the Game Scoring 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 Game Scoring popular?

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

Related skills

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.