AI & ML

pjt222 Skill

Audit, classify, and selectively forget stored memories. Covers memory enumeration and classification by type/age/access frequency, staleness detection for outdated references, fidelity checks using external anchors, a decision tree for selective deletion, counter-memory inoculation for failed strategies that would otherwise be re-derived, preemptive filtering rules for what should never become memories, and an audit trail so forgetting itself is reviewable. Use when memory has grown large and uncurated, when project state has shifted significantly since memories were written, when retrieval quality has degraded, or as periodic maintenance alongside manage-memory.

pjt222 Skill

Design and execute A/B tests for ML models in production using traffic splitting, statistical significance testing, and canary/shadow deployment strategies. Measure performance differences and make data-driven decisions about model rollout. Use when validating a new model version before full rollout, comparing candidate models trained with different algorithms, measuring business metric impact of model changes, or when regulatory requirements mandate gradual rollout.

pjt222 Skill

Launch all available agents in parallel waves for open-ended hypothesis generation on problems where correct domain unknown. Use when face cross-domain problem with no clear starting point, when single-agent approaches stalled, or when diverse perspectives more valuable than deep expertise. Produces ranked hypothesis set with convergence analysis, adversarial refinement.

pjt222 Skill

Build a custom MCP (Model Context Protocol) server that exposes domain-specific tools to AI assistants. Covers server implementation in Node.js or R, tool definitions, the resources and prompts primitives, transport configuration, and testing with Claude Code. Use when you need to expose custom functionality beyond what mcptools provides, when building specialized domain-specific AI integrations, or when wrapping existing APIs or services as MCP tools.

pjt222 Skill

Ajustar modelos ocultos de Markov usando el algoritmo de Baum-Welch (EM) con selección de modelo, decodificación de Viterbi para secuencias de estados y probabilidades forward-backward. Usar cuando las observaciones son generadas por estados latentes no observables, se necesita segmentar una serie temporal en regímenes latentes (regímenes de mercado, fonemas del habla, secuencias biológicas), calcular probabilidades de secuencia, decodificar la ruta de estados ocultos más probable, o comparar modelos con diferentes números de estados ocultos.

pjt222 Skill

Install skills, agents, and teams from agent-almanac into any supported agentic framework using the CLI. Covers framework detection, content search, installation with dependency resolution, health auditing, and manifest-based syncing. Use when setting up a new project with agentic capabilities, installing specific skills or entire domains, targeting multiple frameworks simultaneously, or maintaining a declarative manifest of installed content.

pjt222 Skill

AIアシスタントにドメイン固有のツールを公開するカスタムMCP（Model Context Protocol） サーバーを構築する。Node.jsまたはRでのサーバー実装、ツール定義、トランスポート 設定、Claude Codeでのテストをカバーする。mcptoolsが提供する以上のカスタム機能を 公開する必要がある時、特化したドメイン固有のAI統合を構築する時、既存のAPIや サービスをMCPツールとしてラップする時に使用する。

pjt222 Skill

Baum-Welch（EM）アルゴリズムによる隠れマルコフモデルの適合、モデル選択、 状態系列のViterbiデコーディング、前向き-後ろ向き確率を行う。観測値が観測不能な 潜在状態から生成される時、時系列を潜在レジーム（市場レジーム、音声の音素、生物学的 配列）にセグメント化する必要がある時、系列確率を計算する時、最も可能性の高い隠れ状態 パスをデコーディングする時、または異なる隠れ状態数のモデルを比較する時に使用する。

pjt222 Skill

Install skills, agents, and teams from agent-almanac into any supported agentic framework using the CLI. Covers framework detection, content search, installation with dependency resolution, health auditing, and manifest-based syncing. Use when setting up a new project with agentic capabilities, installing specific skills or entire domains, targeting multiple frameworks simultaneously, or maintaining a declarative manifest of installed content.

pjt222 Skill

遷移行列の構築、状態分類、定常分布の計算、平均初到達時間を含む離散または連続 マルコフ連鎖の構築と分析。観測された遷移カウントまたはレートを持つ記憶のない システムをモデル化する時、長期的な定常状態確率を計算する時、期待到達時間また は吸収確率を決定する時、状態を一時的または再帰的に分類する時、または隠れ マルコフモデルや強化学習MDPの基礎を構築する時に使用する。

pjt222 Skill

保存されたメモリを監査、分類し、選択的に忘却します。タイプ/年齢/アクセス頻度 によるメモリの列挙と分類、古い参照に対する陳腐化検出、外部アンカーを使用した フィデリティチェック、選択的削除のデシジョンツリー、削除しなければ再導出 されてしまう失敗戦略に対するカウンターメモリ・イノキュレーション、永続メモリ にすべきでないものに対する予防フィルタリングルール、および忘却自体がレビュー 可能な監査証跡をカバーします。メモリが大きくキュレーションされていない場合、 プロジェクトの状態がメモリの書き込み以来大幅に変化した場合、検索品質が低下 した場合、または manage-memory と一緒に定期的なメンテナンスとして使用します。

pjt222 Skill

Design and execute A/B tests for ML models in production using traffic splitting, statistical significance testing, and canary/shadow deployment strategies. Measure performance differences and make data-driven decisions about model rollout. Use when validating a new model version before full rollout, comparing candidate models trained with different algorithms, measuring business metric impact of model changes, or when regulatory requirements mandate gradual rollout.

pjt222 Skill

Launch all available agents in parallel waves for open-ended hypothesis generation on problems where the correct domain is unknown. Use when facing a cross-domain problem with no clear starting point, when single-agent approaches have stalled, or when diverse perspectives are more valuable than deep expertise. Produces a ranked hypothesis set with convergence analysis and adversarial refinement.

pjt222 Skill

Achieve distributed agreement without central authority using bee democracy, threshold voting, and quorum sensing. Covers proposal generation, advocacy dynamics, commitment thresholds, deadlock resolution, and consensus quality assessment. Use when a group must decide between options without a designated leader, when centralized decision-making is a bottleneck, when stakeholders have different perspectives to integrate, or when designing automated systems that must reach consensus such as distributed databases or multi-agent AI.

pjt222 Skill

Version machine learning datasets using DVC (Data Version Control) with remote storage backends, build reproducible data pipelines with dependency tracking, integrate with Git workflows, and ensure data lineage for model reproducibility. Use when versioning large datasets that do not fit in Git, tracking data changes alongside code changes, ensuring ML experiment reproducibility, sharing datasets across team members, or auditing data lineage for compliance requirements.

pjt222 Skill

创建有效的 CLAUDE.md 文件，为 AI 编程助手提供项目专属指令。涵盖结构设计、 常用章节、规范与禁忌模式，以及与 MCP 服务器和智能体定义的集成。适用于新项目 引入 AI 助手、优化现有项目的 AI 行为、记录项目约定与限制，或将 MCP 服务器 或智能体定义集成到项目工作流中。

pjt222 Skill

Create a Dockerfile for R projects using rocker base images. Covers system dependency installation, R package installation, renv integration, and optimized layer ordering for fast rebuilds. Use when containerizing an R application or analysis, creating reproducible R environments, deploying R-based services (Shiny, Plumber, MCP server), or setting up consistent development environments across machines.

pjt222 Skill

Set up systematic data labeling workflows using Label Studio or similar tools. Implement quality controls, measure inter-annotator agreement, manage labeler teams, and integrate labeled data into ML training pipelines. Use when starting a supervised ML project that requires labeled training data, when model performance is limited by insufficient labeled examples, when labeling text, images, audio, or video, or when implementing active learning to prioritize the most valuable examples.

pjt222 Skill

Implement comprehensive model drift monitoring using Evidently AI, statistical tests (PSI, KS), and custom metrics to detect data drift and concept drift in production ML systems. Set up automated alerting and reporting workflows to catch degradation before it impacts business metrics. Use when production models show unexplained performance degradation, when new data distributions differ from training data, when seasonal shifts affect input features, or when regulatory requirements mandate model monitoring.

pjt222 Skill

Design monochrome ornamental patterns grounded in Alexander Speltz's classical ornament taxonomy. Covers historical period selection, motif structural analysis, prompt construction for line art and silhouette rendering, and AI-assisted image generation via Z-Image. Use when creating decorative borders, medallions, or friezes in a single color, exploring historical ornament styles through generative AI, producing line art or pen-and-ink renderings of classical motifs, or generating reference imagery for design or educational materials.

pjt222 Skill

Exportar y optimizar modelos 3D para impresión FDM/SLA incluyendo exportación STL/3MF, verificación de integridad de malla, comprobación de grosor de pared, generación de soportes y laminado. Usar al exportar desde software CAD o de modelado para impresión 3D, verificar que archivos STL/3MF sean imprimibles antes del laminado, resolver problemas de modelos que fallan al laminar correctamente, optimizar la orientación de piezas para resistencia o acabado superficial, o convertir entre formatos de modelo preservando la imprimibilidad.

pjt222 Skill

Scaffold a new MCP server from tool specifications using the official SDK (TypeScript or Python), including transport configuration, tool handlers, and test harness. Use when you have a tool specification and need a working server, when starting a new MCP server project and want correct structure from the start, when migrating an existing tool integration to the MCP protocol, or when prototyping a tool surface to test with Claude Code before full implementation.

pjt222 Skill

Valida entregables y construye rastros de evidencia cuando el trabajo pasa entre agentes. Cubre la especificación de resultados esperados antes de la ejecución, la generación de evidencia estructurada durante la ejecución, la validación de entregables contra anclas externas después de la ejecución, verificaciones de fidelidad para salidas comprimidas o resumidas, clasificación de límites de confianza, e informes de desacuerdo estructurado en caso de fallo de verificación. Usar al coordinar flujos de trabajo multi-agente, al revisar transferencias entre agentes, al producir salidas de cara al exterior, o al auditar si el resumen de un agente representa fielmente su material fuente.

pjt222 Skill

rockerベースイメージを使用してRプロジェクト用のDockerfileを作成する。システム依存関係のインストール、 Rパッケージのインストール、renv統合、高速リビルドのための最適化されたレイヤー順序をカバーする。 Rアプリケーションや分析のコンテナ化、再現可能なR環境の構築、Rベースサービス（Shiny、Plumber、 MCPサーバー）のデプロイ、またはマシン間で一貫した開発環境を構築する際に使用する。

pjt222 Skill

Evidently AI、統計テスト（PSI、KS）、カスタムメトリクスを使用した包括的なモデル ドリフトモニタリングの実装。本番MLシステムのデータドリフトとコンセプトドリフトを 検出する。ビジネスメトリクスに影響する前に劣化を検出するための自動アラートと レポートワークフローを設定する。本番モデルが原因不明のパフォーマンス劣化を示す 時、新しいデータ分布がトレーニングデータと異なる時、季節的シフトが入力特徴に 影響する時、または規制要件がモデルモニタリングを義務付ける時に使用する。

pjt222 Skill

Design monochrome ornamental patterns grounded in Alexander Speltz's classical ornament taxonomy. Covers historical period selection, motif structural analysis, prompt construction for line art and silhouette rendering, and AI-assisted image generation via Z-Image. Use when creating decorative borders, medallions, or friezes in a single color, exploring historical ornament styles through generative AI, producing line art or pen-and-ink renderings of classical motifs, or generating reference imagery for design or educational materials.

pjt222 Skill

Design an A2A Agent Card (.well-known/agent.json) manifest describing agent capabilities, skills, authentication requirements, and supported content types. Use when building an agent that must be discoverable by other A2A-compliant agents, exposing capabilities for multi-agent orchestration, migrating an existing agent to the A2A protocol, defining the public contract for an agent before implementation, or integrating with agent registries that consume Agent Cards.

pjt222 Skill

エージェントの機能、スキル、認証要件、サポートするコンテンツタイプを記述するA2A Agent Card（.well-known/agent.json）マニフェストを設計する。他のA2A準拠エージェント から発見可能なエージェントを構築する時、マルチエージェントオーケストレーション用に 機能を公開する時、既存エージェントをA2Aプロトコルに移行する時、実装前にエージェントの パブリック契約を定義する時、Agent Cardを消費するエージェントレジストリと統合する時に 使用する。

pjt222 Skill

Create a new SKILL.md file following the Agent Skills open standard (agentskills.io). Covers frontmatter schema, section structure, writing effective procedures with Expected/On failure pairs, validation checklists, cross-referencing, and registry integration. Use when codifying a repeatable procedure for agents, adding a new capability to the skills library, converting a guide or runbook into agent-consumable format, or standardizing a workflow across projects or teams.

pjt222 Skill

Evolve an existing agent definition by refining its persona in-place or creating an advanced variant. Covers assessing the current agent against best practices, gathering evolution requirements, choosing scope (refinement vs. variant), applying changes to skills, tools, capabilities, and limitations, updating version metadata, and synchronizing the registry and cross-references. Use when an agent's skills list is outdated, user feedback reveals capability gaps, tool requirements have changed, an advanced variant is needed alongside the original, or the agent's scope needs sharpening after real-world use.

pjt222 Skill

Create a new team composition file following the agent-almanac team template and registry conventions. Covers team purpose definition, member selection, coordination pattern choice, task decomposition design, machine-readable configuration block, registry integration, and README automation. Use when defining a multi-agent workflow, composing agents for a complex review process, or creating a coordinated group for recurring collaborative tasks.

pjt222 Skill

Register trained models in MLflow Model Registry with version control, implement stage transitions (Staging, Production, Archived) with approval workflows, and manage model lineage with comprehensive metadata and deployment tracking. Use when promoting a trained model from experimentation to production, managing multiple model versions across development stages, implementing approval workflows for governance, rolling back to previous versions, or auditing model changes for compliance.

pjt222 Skill

Translate agent-almanac content (skills, agents, teams, guides) into a target locale while preserving code blocks, IDs, and technical structure. Covers scaffolding, frontmatter setup, prose translation, code preservation, and freshness tracking. Use when localizing content for a new language, updating stale translations after source changes, or batch-translating a domain.

pjt222 Skill

构建和分析离散或连续马尔可夫链，包括转移矩阵构建、状态分类、平稳分布计算 和平均首达时间。适用于对无记忆系统建模观测到的转移计数或速率、计算长期稳态 概率、确定期望命中时间或吸收概率、将状态分类为瞬态或常返态，或为隐马尔可夫 模型或强化学习 MDP 建立基础时。

pjt222 Skill

审计、分类并选择性地遗忘已存储的记忆。涵盖按类型/时间/访问频率进行记忆枚举 与分类、检测过时引用的陈旧性检测、使用外部锚点进行保真度检查、选择性删除的 决策树、对那些原本会被重新推导出来的失败策略进行反向记忆免疫、关于什么内容 不应成为记忆的预防性过滤规则，以及使遗忘本身可追溯的审计记录。当记忆已增长 为大型未整理状态、项目状态自记忆写入以来发生重大变化、检索质量下降，或作为 与 manage-memory 配套的定期维护时使用。

pjt222 Skill

Design and execute A/B tests for ML models in production using traffic splitting, statistical significance testing, and canary/shadow deployment strategies. Measure performance differences and make data-driven decisions about model rollout. Use when validating a new model version before full rollout, comparing candidate models trained with different algorithms, measuring business metric impact of model changes, or when regulatory requirements mandate gradual rollout.