AI & ML

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

Triage maintenance problems by severity, document findings with context, route to appropriate specialist agent or human, and create actionable issue reports. Use when a maintenance task encounters problems beyond automated cleanup: code that is unsafe to delete, configuration changes requiring domain expertise, breaking changes detected during cleanup, complex refactoring needed, or security-sensitive findings such as hardcoded secrets or vulnerabilities.

pjt222 Skill

Create effective CLAUDE.md file giving project-specific instructions to AI coding assistants. Covers structure, common sections, do/don't patterns, integration with MCP servers and agent definitions. Use when starting new project where AI assistants will be used, improving AI behavior on existing project, documenting project conventions and constraints, or integrating MCP servers or agent definitions into project workflow.

pjt222 Skill

任意のコードベースを分析し、MCPツールとして公開するのに適した関数、API、 データソースを特定し、ツール仕様書を作成する。既存プロジェクトのMCPサーバーを 計画する時、AI対応ツールサーフェスとしてラップする前にコードベースを監査する時、 コードベースの機能とMCP経由で既に公開されている機能を比較する時、 scaffold-mcp-serverに渡すツール仕様を生成する時に使用する。

pjt222 Skill

再起動後の一貫したエージェント動作 — コンテキストをダンプするのではなく段階的に ロードするアイデンティティの漸進的読み込み、永続的アーティファクトからの作業 コンテキスト再構築、フレッシュ対継続の検出、センタリングとアチューンメントによる キャリブレーション、一貫性のためのアイデンティティ検証。エージェントが記憶では なく証拠から誰であるかと何をしていたかを再構築しなければならないコールドスタート 問題に対処する。すべての新しいセッションの開始時、セッションの中断またはクラッシュ 後、エージェントの動作が以前のセッションと一貫していないと感じるとき、または 永続的なメモリと現在のコンテキストが矛盾しているように見えるときに使用する。

pjt222 Skill

Assess an open-source agent framework for investment readiness by evaluating community health, supersession risk, architecture alignment, and governance sustainability. Produces a four-tier classification (INVEST / EVALUATE-FURTHER / CONTRIBUTE-CAUTIOUSLY / AVOID) to guide resource allocation decisions before committing engineering effort.

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

Triage maintenance problems by severity, document findings with context, route to appropriate specialist agent or human, and create actionable issue reports. Use when a maintenance task encounters problems beyond automated cleanup: code that is unsafe to delete, configuration changes requiring domain expertise, breaking changes detected during cleanup, complex refactoring needed, or security-sensitive findings such as hardcoded secrets or vulnerabilities.

pjt222 Skill

Create an effective CLAUDE.md file that provides project-specific instructions to AI coding assistants. Covers structure, common sections, do/don't patterns, and integration with MCP servers and agent definitions. Use when starting a new project where AI assistants will be used, improving AI behavior on an existing project, documenting project conventions and constraints, or integrating MCP servers or agent definitions into a project workflow.

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

Configure the putior MCP server to expose 16 workflow visualization tools to AI assistants. Covers Claude Code and Claude Desktop setup, dependency installation (mcptools, ellmer), tool verification, and optional ACP server configuration for agent-to-agent communication. Use when enabling AI assistants to annotate and visualize workflows interactively, setting up a new development environment with putior MCP integration, or configuring agent-to-agent communication via ACP for automated pipelines.

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

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

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

Triage maintenance problems by severity, document findings with context, route to appropriate specialist agent or human, and create actionable issue reports. Use when a maintenance task encounters problems beyond automated cleanup: code that is unsafe to delete, configuration changes requiring domain expertise, breaking changes detected during cleanup, complex refactoring needed, or security-sensitive findings such as hardcoded secrets or vulnerabilities.

pjt222 Skill

Create an effective CLAUDE.md file that provides project-specific instructions to AI coding assistants. Covers structure, common sections, do/don't patterns, and integration with MCP servers and agent definitions. Use when starting a new project where AI assistants will be used, improving AI behavior on an existing project, documenting project conventions and constraints, or integrating MCP servers or agent definitions into a project workflow.

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

Configure the putior MCP server to expose 16 workflow visualization tools to AI assistants. Covers Claude Code and Claude Desktop setup, dependency installation (mcptools, ellmer), tool verification, and optional ACP server configuration for agent-to-agent communication. Use when enabling AI assistants to annotate and visualize workflows interactively, setting up a new development environment with putior MCP integration, or configuring agent-to-agent communication via ACP for automated pipelines.

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

Fit cognitive drift-diffusion models (Ratcliff DDM) to reaction time and accuracy data with parameter estimation (drift rate, boundary separation, non-decision time), model comparison, and parameter recovery validation. Use when modeling binary decision-making with reaction time data, estimating cognitive parameters from experimental data, comparing sequential sampling model variants, or decomposing speed-accuracy tradeoff effects into latent cognitive components.

pjt222 Skill

Generate themed Mermaid flowchart diagrams from putior workflow data. Covers theme selection (9 themes including 4 colorblind-safe), output modes (console, file, clipboard, raw), interactive features (clickable nodes, source info), and embedding in README, Quarto, and R Markdown. Use after annotating source files and ready to produce a visual diagram, when regenerating a diagram after workflow changes, or when switching themes or output formats for different audiences.

pjt222 Skill

認知的ドリフト拡散モデル（Ratcliff DDM）を反応時間と正確度データに適合させ、 パラメータ推定（ドリフト率、境界分離、非決定時間）、モデル比較、パラメータ回復 バリデーションを行う。反応時間データを用いた二項選択の意思決定モデリング時、 実験データからの認知パラメータ推定時、逐次サンプリングモデルバリアントの比較時、 または速度-正確度トレードオフ効果を潜在的認知コンポーネントに分解する時に使用する。

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

Implement a generative diffusion model (DDPM or score-based) with noise scheduling, U-Net architecture, training loop, and sampling procedures including DDIM acceleration. Use when building a generative model for image, audio, or molecular synthesis; implementing DDPM from a research paper; adding a custom noise schedule or conditioning mechanism; replacing a GAN-based generator with a diffusion alternative; or prototyping before scaling with production frameworks like diffusers.

pjt222 Skill

Diagnosticar y corregir problemas de conexión de servidores MCP entre Claude Code, Claude Desktop y servidores MCP. Cubrir el análisis de argumentos en Windows, fallos de autenticación, problemas de transporte y depuración específica por plataforma. Usar cuando Claude Code o Claude Desktop falla al conectar con un servidor MCP, cuando las herramientas MCP no aparecen en las sesiones, ante errores de "cannot attach the server", cuando una conexión funcionando ha dejado de funcionar, o al configurar MCP en una máquina nueva.

pjt222 Skill

ノイズスケジューリング、U-Netアーキテクチャ、訓練ループ、およびDDIM加速を含む サンプリング手順を備えた生成的拡散モデル（DDPMまたはスコアベース）を実装する。 画像、音声、または分子合成の生成モデルを構築する時、研究論文からDDPMを実装する時、 カスタムノイズスケジュールまたは条件付けメカニズムを追加する時、GANベースの ジェネレータを拡散ベースの代替に置き換える時、またはdiffusersのようなプロダクション フレームワークでスケーリングする前にプロトタイピングする時に使用する。

pjt222 Skill

Diagnose and fix MCP server connection issues between Claude Code, Claude Desktop, and MCP servers. Covers Windows argument parsing, authentication failures, transport issues, and platform-specific debugging. Use when Claude Code or Claude Desktop fails to connect to an MCP server, when MCP tools don't appear in sessions, on "cannot attach the server" errors, when a working connection has stopped, or when setting up MCP on a new machine.

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.

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 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

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

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, 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.