AI & ML

pjt222 Skill

Separate expensive observation from cheap decision-making in autonomous agent loops using a two-clock architecture. A fast clock accumulates data into a digest file; a slow clock reads the digest and acts only when something is pending. Idle cycles cost nothing because the action clock returns immediately after reading an empty digest. Use when building autonomous agents that must observe continuously but can only afford to act occasionally, when API or LLM costs dominate and most cycles have nothing to do, when designing cron-based agent architectures with observation and action phases, or when an existing heartbeat loop is too expensive because it calls the LLM on every tick.

pjt222 Skill

Crea un nuevo archivo de composición de equipo siguiendo la plantilla de equipo de agent-almanac y las convenciones del registro. Cubre la definición del propósito del equipo, la selección de miembros, la elección del patrón de coordinación, el diseño de la descomposición de tareas, el bloque de configuración legible por máquinas, la integración en el registro y la automatización del README. Usar al definir un flujo de trabajo multiagente, al componer agentes para un proceso de revisión complejo, o al crear un grupo coordinado para tareas colaborativas recurrentes.

pjt222 Skill

agent-almanacチームテンプレートとレジストリ規則に従って新しいチーム 構成ファイルを作成する。チームの目的定義、メンバー選択、調整パターンの 選択、タスク分解の設計、機械可読設定ブロック、レジストリ統合、README オートメーションをカバーする。マルチエージェントワークフローを定義する 場合、複雑なレビュープロセスのためにエージェントを構成する場合、または 繰り返される協調タスクのための調整されたグループを作成する場合に使用する。

pjt222 Skill

Separate expensive observation from cheap decision-making in autonomous agent loops using a two-clock architecture. A fast clock accumulates data into a digest file; a slow clock reads the digest and acts only when something is pending. Idle cycles cost nothing because the action clock returns immediately after reading an empty digest. Use when building autonomous agents that must observe continuously but can only afford to act occasionally, when API or LLM costs dominate and most cycles have nothing to do, when designing cron-based agent architectures with observation and action phases, or when an existing heartbeat loop is too expensive because it calls the LLM on every tick.

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

Separate expensive observation from cheap decision-making in autonomous agent loops using a two-clock architecture. A fast clock accumulates data into a digest file; a slow clock reads the digest and acts only when something is pending. Idle cycles cost nothing because the action clock returns immediately after reading an empty digest. Use when building autonomous agents that must observe continuously but can only afford to act occasionally, when API or LLM costs dominate and most cycles have nothing to do, when designing cron-based agent architectures with observation and action phases, or when an existing heartbeat loop is too expensive because it calls the LLM on every tick.

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

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

Traducir contenido de agent-almanac (habilidades, agentes, equipos, guías) a un idioma objetivo preservando bloques de código, IDs y estructura técnica. Cubre scaffolding, configuración de frontmatter, traducción de prosa, preservación de código y seguimiento de frescura. Usar al localizar contenido para un nuevo idioma, actualizar traducciones obsoletas después de cambios en la fuente, o traducir por lotes un dominio.

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

Construir y analizar cadenas de Markov discretas o continuas incluyendo construcción de matriz de transición, clasificación de estados, cálculo de distribución estacionaria y tiempos medios de primer paso. Usar al modelar un sistema sin memoria con conteos o tasas de transición observados, al calcular probabilidades de estado estacionario a largo plazo, al determinar tiempos de golpe esperados o probabilidades de absorción, al clasificar estados como transitorios o recurrentes, o al construir una base para modelos ocultos de Markov o MDPs de aprendizaje por refuerzo.

pjt222 Skill

Audita, clasifica y elimina selectivamente memorias almacenadas. Cubre la enumeración y clasificación de memorias por tipo/antigüedad/frecuencia de acceso, detección de obsolescencia para referencias desactualizadas, verificaciones de fidelidad mediante anclas externas, un árbol de decisión para la eliminación selectiva, inoculación con contra-memorias para estrategias fallidas que de otro modo se rederivarían, reglas de filtrado preventivo sobre lo que nunca debe convertirse en memoria, y un registro de auditoría para que el olvido sea revisable. Usar cuando la memoria ha crecido y no ha sido curada, cuando el estado del proyecto ha cambiado significativamente desde que se escribieron las memorias, cuando la calidad de recuperación ha degradado, o como mantenimiento periódico junto con 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 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

Configure MCP (Model Context Protocol) servers for Claude Code and Claude Desktop. Covers mcptools setup, Hugging Face integration, WSL path handling, and multi-client configuration. Use when setting up Claude Code to connect to R via mcptools, configuring Claude Desktop with MCP servers, adding Hugging Face or other remote MCP servers, or troubleshooting MCP connectivity between clients and servers.

pjt222 Skill

Configurar el servidor MCP de putior para exponer 16 herramientas de visualización de flujo de trabajo a asistentes de IA. Cubre la configuración de Claude Code y Claude Desktop, instalación de dependencias (mcptools, ellmer), verificación de herramientas y configuración opcional del servidor ACP para comunicación agente-a-agente. Usar al habilitar asistentes de IA para anotar y visualizar flujos de trabajo interactivamente, al configurar un nuevo entorno de desarrollo con integración MCP de putior, o al configurar comunicación agente-a-agente vía ACP para pipelines automatizados.

pjt222 Skill

Conduct a structured cross-project code review between two Claude Code instances via the cross-review-mcp broker. Each agent reads its own codebase, reviews the peer's code, and engages in evidence-backed dialogue — with QSG scaling laws enforcing review quality through minimum bandwidth constraints and phase-gated progression.

pjt222 Skill

Implement a JSON-RPC 2.0 A2A server with full task lifecycle management (submitted/working/completed/failed/canceled/input-required), SSE streaming, and push notifications. Use when implementing an agent that participates in multi-agent A2A workflows, building a backend for an Agent Card, adding A2A protocol support to an existing agent or service, or deploying an agent that must interoperate with other A2A-compliant agents.

pjt222 Skill

Claude CodeとClaude Desktop用のMCP（Model Context Protocol）サーバーを設定する。 mcptoolsのセットアップ、Hugging Face統合、WSLパス処理、マルチクライアント設定を カバーする。Claude Codeをmcptools経由でRに接続する時、Claude DesktopにMCP サーバーを設定する時、Hugging Faceやその他のリモートMCPサーバーを追加する時、 クライアントとサーバー間のMCP接続のトラブルシューティング時に使用する。

pjt222 Skill

putior MCPサーバーを設定して16のワークフロー可視化ツールをAIアシスタントに公開する。 Claude CodeとClaude Desktopのセットアップ、依存関係のインストール（mcptools、 ellmer）、ツールの検証、エージェント間通信用のオプションのACPサーバー設定をカバー する。AIアシスタントがワークフローをインタラクティブにアノテーション・可視化できる ようにする時、putior MCP統合で新しい開発環境をセットアップする時、自動化 パイプライン用のACP経由のエージェント間通信を設定する時に使用する。

pjt222 Skill

Conduct a structured cross-project code review between two Claude Code instances via the cross-review-mcp broker. Each agent reads its own codebase, reviews the peer's code, and engages in evidence-backed dialogue — with QSG scaling laws enforcing review quality through minimum bandwidth constraints and phase-gated progression.

pjt222 Skill

完全なタスクライフサイクル管理（submitted/working/completed/failed/canceled/input-required）、 SSEストリーミング、プッシュ通知を備えたJSON-RPC 2.0 A2Aサーバーを実装する。 マルチエージェントA2Aワークフローに参加するエージェントを実装する時、Agent Cardの バックエンドを構築する時、既存のエージェントやサービスにA2Aプロトコルサポートを 追加する時、または他のA2A準拠エージェントと相互運用する必要があるエージェントを デプロイする時に使用する。

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

Apply collective intelligence coordination patterns — stigmergy, local rules, and quorum sensing — to organize distributed systems, teams, or workflows without centralized control. Covers signal design, agent autonomy boundaries, emergent behavior cultivation, and feedback loop tuning. Use when designing distributed systems without a coordination bottleneck, organizing teams that must self-coordinate, building event-driven architectures with shared state communication, or replacing fragile centralized orchestration with resilient emergent coordination.

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

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

Apply collective intelligence coordination patterns — stigmergy, local rules, and quorum sensing — to organize distributed systems, teams, or workflows without centralized control. Covers signal design, agent autonomy boundaries, emergent behavior cultivation, and feedback loop tuning. Use when designing distributed systems without a coordination bottleneck, organizing teams that must self-coordinate, building event-driven architectures with shared state communication, or replacing fragile centralized orchestration with resilient emergent coordination.

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

在智能体之间传递工作时验证可交付成果并建立证据记录。涵盖执行前的预期 结果规格、执行期间的结构化证据生成、基于外部锚点的执行后交付物验证、 压缩或摘要输出的保真度检查、信任边界分类，以及验证失败时的结构化分歧 报告。当协调多智能体工作流、审查跨智能体交接、生成面向外部的输出，或 审计智能体摘要是否忠实代表源材料时使用。

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

Build and analyze discrete or continuous Markov chains including transition matrix construction, state classification, stationary distribution computation, and mean first passage times. Use when modeling a memoryless system with observed transition counts or rates, computing long-run steady-state probabilities, determining expected hitting times or absorption probabilities, classifying states as transient or recurrent, or building a foundation for hidden Markov models or reinforcement learning MDPs.