GitHub
plan-mode-arc-gsm8k-improvement
AEGISモデルのARC-Challenge評価改善とGSM8K健全性チェックのためのPlanモード。タイムアウト率・抽出失敗率分析、頑健な回答抽出、データ汚染検査、複数seed評価を実行。
☆ 0View skill
Tools AI Skills
Discover Tools skills, compare source repositories and read the instructions for each workflow.
Categories: Tools
Tools Clear filters
Browse skills
GitHub
plan-mode-aegis-v25-development
AEGIS v2.5開発の包括的Planモード。数学データ収集、形式証明環境構築、GRPO訓練パイプライン、MCP/A2Aエージェント開発、進捗監視を実装。SO(8)四重推論再現のための完全開発ワークフロー。
☆ 0View skill
GitHub
plan-mode
AEGISモデルのARC-Challenge改善、GSM8K健全性検証、GRPO報酬多目的化のための包括的Planモード。頑健な回答抽出、タイムアウト最適化、データ汚染チェック、複数seed評価、汎化性能向上を実装。
☆ 0View skill
GitHub
plan-mode-creation
Planモードの設計・作成・設定を自動化するスキル。AI開発ワークフローのPlanモードを効率的に構築し、チェックポイント管理・進捗監視・エラー回復機能を統合。SO8Tプロジェクト専用に最適化。
☆ 0View skill
GitHub
plan-mode-official-leaderboard-abctest
公式リーダーボード準拠のA/B/Cテストを実行するPlanモードスキル。Phi-3.5-mini-instruct、Borea-phi3.5-instinct-jp、AEGIS-Phi3.5mini-jpv2.4を標準化ベンチマークで比較評価し、統計的有意性を検証。
☆ 0View skill
GitHub
plan-mode-advanced
Create and execute advanced execution plans for complex AI model development incorporating 2024-2026 cutting-edge techniques (DeepSeek GRPO, manifold-constrained architectures, geometric scaling). Use when plan...
☆ 0View skill
GitHub
mathematical-theorem-prover
Implement comprehensive mathematical theorem proving capabilities with SFT+GRPO training, MCP/A2A agent integration, and imatrix quantization protection to surpass Boreas-phi3.5-instinct-jp in formal proof gene...
☆ 0View skill
GitHub
quantization-evaluation-pipeline
Execute GGUF quantization with imatrix protection, perform statistical benchmark evaluation with error bars, generate academic-style methodology documentation, and create comprehensive scorecards. Use when eval...
☆ 0View skill
GitHub
chrome-devtools-validation
Validate UI changes in the AntonioHC Next.js portfolio using the Chrome DevTools MCP. Use when asked to verify sections, layouts, light/dark theming, responsive behavior, or visual regressions on http://localho...
☆ 0View skill
GitHub
code-review
バグ、スタイルの問題、ベストプラクティスについてコードの変更をレビューします。プルリクエスト（PR）の確認やコード品質のチェック時に使用してください。
☆ 0View skill
GitHub
debugging-assistant
Diagnose bugs, analyze stack traces, provide fixes
☆ 0View skill
GitHub
context-engineering
Context engineering and prompt patterns for AI agents
☆ 0View skill
GitHub
ui-ux-principles
Modern UI/UX: minimalist, keyboard-driven, accessible
☆ 0View skill
GitHub
product-manager
Product management: PRDs, RICE prioritization, metrics
☆ 0View skill
GitHub
planning-with-files
Manus-style planning with persistent markdown files
☆ 0View skill
GitHub
git-analyzer
Git repository analysis: status, history, changes
☆ 0View skill
GitHub
code-reviewer
Code review: security, performance, best practices
☆ 0View skill
GitHub
error-handling
Common errors and fixes. Use when debugging or troubleshooting.
☆ 0View skill
GitHub
database-patterns
SQLite veritabani yapisi ve CRUD pattern referansi. Use when working with database operations, queries, or understanding the data model.
☆ 0View skill
GitHub
olivenet-brand
Olivenet marka sesi ve icerik stratejisi. Use when creating content, captions, hooks, or understanding brand voice.
☆ 0View skill
GitHub
multi-agent-architecture
Multi-agent sistem mimarisi referansi. Use when working with agents, pipelines, or understanding the content generation workflow.
☆ 0View skill
GitHub
cloudinary-cdn
Video CDN yonetimi. Use when uploading videos for Instagram Reels.
☆ 0View skill
GitHub
video-generation
AI video generation with Sora, Veo, and Kling. Use when creating Reels, video prompts, or handling video generation workflows.
☆ 0View skill
GitHub
telegram-bot
Telegram bot komutlari ve handler referansi. Use when working with Telegram bot commands, callbacks, or approval workflows.
☆ 0View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.