MCP HubMCP Hub
スキル一覧に戻る

complexity-scorer-5-confidence-scoring

vamseeachanta
更新日 Today
10 閲覧
3
2
3
GitHubで表示
その他general

について

このサブスキルは、評価の信頼性を示す信頼度スコアを複雑性の推定値に追加します。テキストの長さとキーワードの一致度に基づいて信頼度を計算し、自動採点に対する確実性の尺度を開発者に提供します。複雑性の分類がどの程度信頼できるかを判断する必要がある場合にご利用ください。

クイックインストール

Claude Code

推奨
メイン
npx skills add vamseeachanta/workspace-hub
プラグインコマンド代替
/plugin add https://github.com/vamseeachanta/workspace-hub
Git クローン代替
git clone https://github.com/vamseeachanta/workspace-hub.git ~/.claude/skills/complexity-scorer-5-confidence-scoring

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

5. Confidence Scoring (+1)

5. Confidence Scoring

Add confidence to scoring:

#!/bin/bash
# ABOUTME: Confidence scoring for complexity estimates
# ABOUTME: Indicates reliability of the score

# Calculate confidence
calculate_confidence() {
    local text="$1"
    local confidence=50  # Base confidence

    local word_count=$(echo "$text" | wc -w)
    local keyword_matches=0
    local text_lower=$(echo "$text" | tr '[:upper:]' '[:lower:]')

    # More words = higher confidence (more context)
    if [[ $word_count -gt 15 ]]; then
        ((confidence+=20))
    elif [[ $word_count -gt 8 ]]; then
        ((confidence+=10))
    elif [[ $word_count -lt 3 ]]; then
        ((confidence-=20))
    fi

    # Keyword matches boost confidence
    for pattern in "$HIGH_COMPLEXITY" "$MEDIUM_COMPLEXITY" "$LOW_COMPLEXITY"; do
        if echo "$text_lower" | grep -qE "$pattern"; then
            ((keyword_matches++))
        fi
    done

    ((confidence += keyword_matches * 10))

    # Cap confidence
    [[ $confidence -gt 100 ]] && confidence=100
    [[ $confidence -lt 10 ]] && confidence=10

    echo $confidence
}

# Get confidence label
confidence_label() {
    local confidence="$1"

    if [[ $confidence -ge 80 ]]; then
        echo "High"
    elif [[ $confidence -ge 60 ]]; then
        echo "Medium"
    elif [[ $confidence -ge 40 ]]; then
        echo "Low"
    else
        echo "Very Low"
    fi
}

6. Historical Learning

Adjust based on past accuracy:

#!/bin/bash
# ABOUTME: Historical learning for complexity scoring
# ABOUTME: Track and adjust based on actual outcomes

HISTORY_FILE="${HOME}/.complexity-scorer/history.log"

# Log prediction vs actual
log_outcome() {
    local task="$1"
    local predicted_score="$2"
    local actual_complexity="$3"  # user-provided feedback
    local timestamp=$(date '+%Y-%m-%d_%H:%M:%S')

    mkdir -p "$(dirname "$HISTORY_FILE")"
    echo "${timestamp}|${predicted_score}|${actual_complexity}|${task}" >> "$HISTORY_FILE"
}

# Calculate prediction accuracy
calculate_accuracy() {
    local correct=0
    local total=0

    while IFS='|' read -r ts predicted actual task; do
        [[ "$ts" =~ ^#.*$ ]] && continue
        [[ -z "$ts" ]] && continue

        ((total++))

        local predicted_class=$(classify_complexity "$predicted")
        if [[ "$predicted_class" == "$actual" ]]; then
            ((correct++))
        fi
    done < "$HISTORY_FILE"

    if [[ $total -gt 0 ]]; then
        echo $((correct * 100 / total))
    else
        echo 0
    fi
}

# Find common misclassifications
find_patterns() {
    echo "Analyzing misclassification patterns..."

    while IFS='|' read -r ts predicted actual task; do
        local predicted_class=$(classify_complexity "$predicted")
        if [[ "$predicted_class" != "$actual" ]]; then
            echo "Predicted: $predicted_class, Actual: $actual"
            echo "Task: $task"
            echo "---"
        fi
    done < "$HISTORY_FILE"
}

GitHub リポジトリ

vamseeachanta/workspace-hub
パス: .claude/skills/_core/bash/complexity-scorer/5-confidence-scoring

関連スキル

algorithmic-art

メタ

This Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.

スキルを見る

subagent-driven-development

開発

This skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.

スキルを見る

executing-plans

デザイン

Use the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.

スキルを見る

cost-optimization

その他

This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.

スキルを見る