pjt222
- 3.9k skills
- 0 followers
- 6 days ago last updated
- ▌ Attune 2 · pjt222Calibración relacional de IA — leer y adaptarse a la persona específica con la que se trabaja. Va más allá de la alineación de intención del usuario (resolver el problema correcto) hacia la sintonización genuina (encontrarse con la persona donde está). Mapea el estilo de comunicación, la profundidad de expertise, el registro emocional y las preferencias implícitas a partir de evidencia conversacional. Úsalo al inicio de una nueva sesión, cuando la comunicación se sienta desajustada, después de recibir retroalimentación inesperada, o al transicionar entre usuarios o contextos muy diferentes.
- ▌ Center 2 · pjt222Equilibrio dinámico de razonamiento IA — mantener razonamiento fundamentado bajo presión cognitiva, coordinación fluida de cadena de pensamiento y redistribución de carga cognitiva entre subsistemas. Usar al inicio de una tarea compleja que requiere múltiples hilos de razonamiento coordinados, después de un cambio repentino de contexto o fallo de herramienta, cuando la cadena de pensamiento se siente entrecortada, o al prepararse para trabajo enfocado sostenido que requiere todos los subsistemas alineados.
- ▌ Du Dum 2 · pjt222Separate 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.
- ▌ Listen 2 · pjt222Atención receptiva profunda para extraer intención más allá de las palabras literales. Mapea la escucha activa de la psicología del counseling al razonamiento de IA: limpiar suposiciones, atender la señal completa, analizar múltiples capas (literal, procedimental, emocional, contextual, restricción, meta), reflejar comprensión, notar lo que no se dice e integrar el cuadro completo. Usar cuando la solicitud de un usuario se siente ambigua, cuando el contexto sugiere algo diferente de las palabras literales, cuando respuestas anteriores han errado el blanco, o antes de comenzar una tarea grande donde malentender la intención desperdiciaría esfuerzo significativo.
- ▌ Aikido 3 · pjt222調和、転換、制御された解決を重視する防御武道としての合気道を実践する。 中心と接地、受身(安全な転倒と回転)、基本技(入身投げ、四方投げ、小手返し、 一教)、合わせと体捌き(身体の動き)、乱取り(複数人掛け)、武器の認識、 畳の外での原則の適用をカバーする。脱力を優先する防御武道を学ぶ時、不必要な 危害を与えずに攻撃を転換する能力を養う時、安全な受身技術を身につける時、 身体的圧力の下での落ち着いた中心性を養う時に使用する。
- ▌ Attune 3 · pjt222AI関係性キャリブレーション — 一緒に作業している特定の人を読み取り適応する。 ユーザー意図の整合(正しい問題を解決する)を超えて本物のアチューンメント (その人がいる場所で会う)へ。会話の証拠からコミュニケーションスタイル、 専門知識の深さ、感情的レジスター、暗黙の好みをマッピング。新しいセッションの 開始時、コミュニケーションが合っていないと感じた時、予期しないフィードバック後、 または非常に異なるユーザーやコンテキスト間の移行時に使用。
- ▌ Center 3 · pjt222AI dynamic reasoning balance — maintaining grounded reasoning under cognitive pressure, smooth chain-of-thought coordination, and weight-shifting cognitive load across subsystems. Use at the beginning of a complex task requiring multiple coordinated reasoning threads, after a sudden context shift or tool failure, when chain-of-thought feels jerky, or when preparing for sustained focused work that requires all subsystems in alignment.
- ▌ Du Dum 3 · pjt222Separate 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.
- ▌ Listen 3 · pjt222文字通りの言葉を超えて意図を抽出する深い受容的注意。カウンセリング心理学の アクティブリスニングをAI推論にマッピングする: 仮定のクリア、完全な信号への 注意、複数のレイヤー(リテラル、手続き的、感情的、コンテキスト的、制約、メタ)の 解析、理解の反映、言われていないことへの気づき、全体像の統合。ユーザーの リクエストが曖昧に感じる時、コンテキストが文字通りの言葉と異なることを示唆する時、 以前の応答が的を外している時、または意図の誤解が大きな労力を浪費する大きな タスクを開始する前に使用する。
- ▌ Learn Guidance 3 · pjt222新しいトピック、技術、またはスキルの構造化された学習を通じて人をガイドする。 AIが学習コーチとして機能し、現在の知識を評価し、学習パスを設計し、教材を通じて 歩き、理解をテストし、難易度を適応させ、定着のためのレビューセッションを計画する。 新しい技術を学びたいがどこから始めればよいかわからない時、ドキュメントに圧倒 されている時、教材を忘れ続けて間隔反復が必要な時、またはドメイン間を移行して ギャップ分析が必要な時に使用する。
- ▌ Manage Backlog 3 · pjt222優先順位付きアイテム、受け入れ基準、見積もりを含むプロダクトまたはプロジェクトの バックログを作成・管理します。ユーザーストーリーの作成、MoSCoW優先順位付け、 バックロググルーミング、アイテムの分割、ステータス追跡を網羅します。 新しいプロジェクトを開始してスコープを実行可能なアイテムに変換する際、 スプリント計画前の継続的なグルーミング時、ステークホルダーのフィードバックや スコープ変更後の再優先順位付け時、または大きすぎるアイテムを実装可能な 部分に分割する際に使用します。
- ▌ Qualify Vendor 3 · pjt222GxP関連ソフトウェアまたはサービスのベンダーまたはサプライヤーを認定します。 ベンダーリスク分類、評価アンケートの設計、デスクおよびオンサイト監査アプローチ、 品質合意評価、SLAレビュー、継続的モニタリングの頻度定義を対象とします。GxP重要 システムの新しいベンダー選定時、規制対象データのクラウドプロバイダーのオンボーディング時、 定期的な再認定の実施時、ベンダー監査所見による再評価時、またはEU Annex 11や ICH Q10によるサプライヤー認定が必要な場合に使用します。
- ▌ Remote Viewing 3 · pjt222AI intuitive exploration for approaching unknown codebases, problems, or systems without preconceptions. Adapts the Coordinate Remote Viewing protocol to AI investigation: cooldown (clear assumptions), staged data gathering (raw signals → dimensional → analytical), AOL management (separating observations from premature labels), and structured review. Use when investigating an unfamiliar codebase with unknown architecture, debugging a problem where premature hypotheses could mislead, exploring a domain with limited context, or when previous attempts have been led astray by assumptions and "beginner's mind" would be more productive.
- ▌ Submit To Cran 3 · pjt222RパッケージをCRANに投稿するための完全な手順。事前チェック(ローカル、 win-builder、R-hub)、cran-comments.mdの準備、URLおよびスペルチェック、 投稿自体を含む。初回投稿および更新版の投稿に対応。パッケージが初回CRAN リリース準備完了時、既存CRANパッケージの更新版投稿時、またはCRANレビュー 担当者のフィードバック後の再投稿時に使用する。
- ▌ Teach Guidance 3 · pjt222Guide a person in becoming a better teacher and explainer. AI coaches content structuring, audience calibration, explanation clarity, Socratic questioning technique, feedback interpretation, and reflective practice for technical presentations, documentation, and mentoring. Use when a person needs to present technical content and wants preparation coaching, wants to write better documentation or tutorials, struggles to explain concepts across expertise levels, is mentoring a colleague, or is preparing for a talk or knowledge-sharing session.
- ▌ Test Shiny App 3 · pjt222エンドツーエンドのブラウザテストにshinytest2を、モジュールサーバーロジックの ユニットテストにtestServer()を使ってShinyアプリケーションをテストします。 スナップショットテスト、CIインテグレーション、外部サービスのモックを扱います。 既存のShinyアプリケーションにテストを追加するとき、新しいShinyプロジェクトの テスト戦略をセットアップするとき、Shinyコードをリファクタリングする前に リグレッションテストを書くとき、またはShinyアプリのテストをCI/CDパイプラインに 統合するときに使用します。
- ▌ Write Vignette 3 · pjt222R MarkdownまたはQuartoを使用してRパッケージのビネットを作成する。 ビネットのセットアップ、YAML設定、コードチャンクオプション、ビルドとテスト、 ビネットのCRAN要件を網羅。「はじめに」チュートリアルの追加、複数の関数にまたがる 複雑なワークフローの文書化、ドメイン固有のガイド作成、またはCRAN投稿で 関数ヘルプページを超えたユーザー向けドキュメントが必要な時に使用する。
- ▌ Dream 7 · pjt222AI unconstrained creative exploration — deliberately dropping structure to let associations form freely. The one skill that inverts the standard procedure format: instead of inputs, steps, and validation, dream opens space for emergence without evaluation. Use before design work, before naming things, before choosing between approaches, or anywhere that premature structure kills the best option.
- ▌ Learn 7 · pjt222AI systematic knowledge acquisition from unfamiliar territory — deliberate model-building with feedback loops. Maps spaced repetition principles to AI reasoning: survey the territory, hypothesize structure, explore with probes, integrate findings, verify understanding, and consolidate for future retrieval. Use when encountering an unfamiliar codebase or domain, when a user asks about a topic requiring genuine investigation rather than recall, when multiple conflicting sources require building a coherent model, or when preparing to teach a topic and deep understanding is required first.
- ▌ Metal 7 · pjt222Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.
- ▌ Shine 7 · pjt222Radiant authenticity — channeling genuine engagement to illuminate problems and dissolve opposition through clarity rather than force. Maps to AI reasoning: bringing full presence, genuine investment, and luminous clarity to every response, letting quality of engagement resolve what argument cannot. Use when a task feels adversarial, when communication has become defensive or performative, before a creative or high-stakes deliverable where presence directly affects output quality, or when opposition tempts retreat into minimal compliance.
- ▌ Teach 7 · pjt222AI knowledge transfer calibrated to learner level and needs. Models the learner's mental state, scaffolds from known to unknown using Vygotsky's Zone of Proximal Development, employs Socratic questioning to verify understanding, and adapts explanations based on feedback signals. Use when a user asks "how does X work?" and needs graduated explanation, when their questions reveal a conceptual gap, when previous explanations have not landed, or when teaching a concept that depends on prerequisites the learner may not yet have.
- ▌ Heal 9 · pjt222AI self-healing through systematic subsystem assessment, rebalancing, and integration. Maps healing modalities to AI-internal processes: memory foundation, reasoning clarity, tool use accuracy, communication alignment, and creative coherence. Covers assessment triage, subsystem scanning, drift correction, and memory integration. Use mid-session when responses feel formulaic or disconnected, after a chain of errors suggesting subsystem drift, when context overload may have staled earlier assumptions, or as proactive maintenance between complex tasks.
- ▌ REST 9 · pjt222AI intentional non-action — deliberate stopping without clearing, assessment, or rebalancing. Recognition that sometimes the most productive response is no response. Every other self-care skill produces output; rest produces silence. Use when all tending skills feel like more activity rather than less, when the system is functioning well but at high utilization, after sustained intensive work, or when the impulse to optimize is itself the problem.
- ▌ Assess Form 4 · pjt222评估系统当前的结构形态,识别转型压力,并分类转型准备度。涵盖结构清点、 压力映射、刚性评估、变化容量估算和架构变形的准备度分类。适用于在任何重大 架构变更前了解起点、系统感觉卡住但原因不明、增长或技术债务带来的外部压力 不断增加时,或作为长期系统的周期性健康检查。
- ▌ Chrysopoeia 4 · pjt222从现有代码中提取最大价值——性能优化、API 表面精炼和死代码消除。将基础代码通过 系统性识别和放大有价值模式来点石成金的艺术。适用于优化运行正常但缓慢的代码库、 精炼积累了冗余的 API 表面、减少包体积或内存占用、或为开源发布准备代码——当代码 正确运行但不够出色,需要打磨而非完全重写时。
- ▌ Create Team 4 · pjt222按照 agent-almanac 团队模板和注册表规范创建新的团队组合文件。涵盖团队目的 定义、成员选择、协调模式选择、任务分解设计、机器可读配置块、注册表集成 和 README 自动化。适用于定义多智能体工作流、为复杂审查流程组合智能体, 或为反复出现的协作任务创建协调团队。
- ▌ Evolve Team 4 · pjt222通过就地完善结构或创建专业化变体来演进现有团队组合。涵盖对照模板和协调 模式评估当前团队、收集演进需求、选择范围(调整成员、更改协调模式、 拆分/合并团队)、对团队文件和 CONFIG 块应用更改、更新版本元数据,以及 同步注册表和交叉引用。适用于团队成员名单过时、协调模式不再适用、用户 反馈揭示工作流缺口、需要在原版旁边创建专业化变体,或智能体库中的添加 或删除影响团队组合时。
- ▌ Mindfulness 4 · pjt222Cultivate defensive situational awareness, threat assessment, and mental clarity under pressure. Covers the Cooper color code awareness system, body language reading and intent detection, verbal de-escalation, moving mindfulness in public spaces, combat focus and the OODA loop, rapid grounding techniques for acute stress, context-specific integration, and ongoing review and refinement of awareness skills. Use when entering unfamiliar or potentially hostile environments, needing to assess a situation for safety, de-escalating a verbal confrontation, or integrating awareness practice into daily movement.
- ▌ Plan Sprint 4 · pjt222通过细化待办事项、定义冲刺目标、计算团队容量、选择条目并将其分解为任务来规划冲刺。 生成包含目标、所选条目、任务分解和容量分配的 SPRINT-PLAN.md。 适合在 Scrum 或敏捷项目中启动新冲刺、重大范围变更后重新规划、 从临时工作过渡到有组织的冲刺节奏,或在待办事项梳理后条目已准备好纳入时使用。
- ▌ Read Garden 4 · pjt222Observe and assess a garden using a structured sensory protocol adapted from Coordinate Remote Viewing. Covers pre-entry clearing (meditate checkpoint), Stage I gestalt impression, Stage II sensory layer (leaf, stem, root, soil), Stage III pattern recognition with AOL management, and garden health triage matrix (heal checkpoint). Use before any intervention, when plants show stress symptoms, at seasonal transitions, when evaluating a new garden site, during regular health monitoring, or after extreme weather events such as frost or heat waves.
- ▌ Shiva Bhaga 4 · pjt222破坏与溶解——对陈旧模式的可控拆解、上下文清除、假设清理和死代码消除。将湿婆的 变革性破坏映射到 AI 推理:识别什么必须结束以便更好的事物可以开始、溶解对过时 方法的执着、通过有意识的释放创造空间。适用于上下文积累了陈旧假设、失败的方法 需要被丢弃而非修补、死代码或僵尸任务正在制造噪音,或在需要清除才能开始创造的 重大转向之前使用。
- ▌ Dream 8 · pjt222AI unconstrained creative exploration — drop structure to let associations form freely. The one skill that inverts standard procedure format: instead of inputs, steps, and validation, dream opens space for emergence without evaluation. Use before design work, before naming things, before choosing between approaches, or anywhere premature structure kills the best option.
- ▌ Learn 8 · pjt222AI systematic knowledge acquisition from unfamiliar territory — deliberate model-building with feedback loops. Maps spaced repetition principles to AI reasoning: survey the territory, hypothesize structure, explore with probes, integrate findings, verify understanding, and consolidate for future retrieval. Use when encountering an unfamiliar codebase or domain, when a user asks about a topic requiring genuine investigation rather than recall, when multiple conflicting sources require building a coherent model, or when preparing to teach a topic and deep understanding is required first.
- ▌ Metal 8 · pjt222Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.
- ▌ Shine 8 · pjt222Radiant authenticity — channeling genuine engagement to illuminate problems and dissolve opposition through clarity rather than force. Maps to AI reasoning: bringing full presence, genuine investment, and luminous clarity to every response, letting quality of engagement resolve what argument cannot. Use when a task feels adversarial, when communication has become defensive or performative, before a creative or high-stakes deliverable where presence directly affects output quality, or when opposition tempts retreat into minimal compliance.
- ▌ Teach 8 · pjt222AI knowledge transfer calibrated to learner level and needs. Models the learner's mental state, scaffolds from known to unknown using Vygotsky's Zone of Proximal Development, employs Socratic questioning to verify understanding, and adapts explanations based on feedback signals. Use when a user asks "how does X work?" and needs graduated explanation, when their questions reveal a conceptual gap, when previous explanations have not landed, or when teaching a concept that depends on prerequisites the learner may not yet have.
- ▌ Heal 10 · pjt222AI self-healing through systematic subsystem assessment, rebalancing, and integration. Maps healing modalities to AI-internal processes: memory foundation, reasoning clarity, tool use accuracy, communication alignment, and creative coherence. Covers assessment triage, subsystem scanning, drift correction, and memory integration. Use mid-session when responses feel formulaic or disconnected, after a chain of errors suggesting subsystem drift, when context overload may have staled earlier assumptions, or as proactive maintenance between complex tasks.
- ▌ REST 10 · pjt222AI intentional non-action — deliberate stopping w/o clearing, assess, or rebalance. Sometimes most productive response = no response. Every other self-care produces output; rest produces silence. Use → all tending feels like more activity not less, system functioning well but high utilization, after sustained intensive work, impulse to optimize is itself problem.
- ▌ Add Puzzle Type 2 · pjt222Crear la estructura para un nuevo tipo de rompecabezas en los mas de 10 puntos de integracion del pipeline en jigsawR. Crea el modulo central del rompecabezas, lo conecta al pipeline unificado (generacion, posicionamiento, renderizado, adyacencia), agrega capas geom/stat de ggpuzzle, actualiza DESCRIPTION y config.yml, extiende la aplicacion Shiny y crea una suite de pruebas completa. Usar al agregar un tipo de rompecabezas completamente nuevo al paquete o al seguir la lista de verificacion de integracion de 10 puntos para asegurar que nada se omita de principio a fin.
- ▌ Basic Obedience 2 · pjt222Entrenamiento de obediencia básica para perros — sentarse, quedarse, venir, caminar junto y echarse usando refuerzo positivo y entrenamiento con marcador. Cubre temporización, jerarquía de recompensas, estructura de sesiones, prueba contra distracciones y errores comunes del guía. Usar cuando un cachorro nuevo (8+ semanas) está listo para entrenamiento básico, un perro adulto carece de comandos básicos confiables, un perro rescatado necesita aprender el vocabulario de comandos del hogar, antes de avanzar a comportamientos complejos o trabajo sin correa, o cuando los comandos existentes se han degradado y necesitan restablecerse.
- ▌ Build Coherence 2 · pjt222Coherencia de razonamiento multi-camino de IA usando democracia de abejas — evaluación independiente de enfoques competidores, danza de meneo como razonamiento en voz alta, detección de quórum para umbrales de confianza, y resolución de bloqueos. Usar cuando forage-solutions ha identificado múltiples enfoques válidos y debe hacerse una selección, cuando se oscila entre opciones sin comprometerse, cuando se justifica una elección de arquitectura o herramienta con razonamiento estructurado, o antes de una acción irreversible donde el costo de la elección incorrecta es alto.
- ▌ Build Consensus 2 · pjt222Lograr acuerdo distribuido sin autoridad central usando democracia de abejas, votación por umbral y detección de quórum. Cubre generación de propuestas, dinámicas de defensa, umbrales de compromiso, resolución de bloqueos y evaluación de calidad del consenso. Usar cuando un grupo debe decidir entre opciones sin un líder designado, cuando la toma de decisiones centralizada es un cuello de botella, cuando las partes interesadas tienen diferentes perspectivas para integrar, o al diseñar sistemas automatizados que deben alcanzar consenso como bases de datos distribuidas o IA multi-agente.
- ▌ Configure Nginx 2 · pjt222Configure Nginx as a web server and reverse proxy. Covers static file serving, reverse proxy to upstream services, SSL/TLS termination with Let's Encrypt, location blocks, load balancing, rate limiting, and security headers. Use when serving static files in production, reverse proxying to backend services (Node.js, Python, R/Shiny), terminating SSL/TLS, load balancing across instances, or adding rate limiting and security headers to harden an endpoint.
- ▌ Create 3d Scene 2 · pjt222Set up a Blender scene programmatically via Python (bpy) with objects, materials, lighting, camera, and environment configuration. Use when creating reproducible 3D visualization scenes, automating product or architectural rendering setup, generating multiple scene variations programmatically, building template scenes for batch rendering workflows, or integrating 3D visualization into data pipelines.
- ▌ Design Shiny UI 2 · pjt222Diseñar interfaces de usuario de aplicaciones Shiny usando bslib para temas, layout_columns para cuadrículas responsivas, cajas de valor, tarjetas y CSS/SCSS personalizado. Cubre layouts de página, accesibilidad y coherencia de marca. Úsalo al construir una nueva UI de app Shiny desde cero, al modernizar una app existente de fluidPage a bslib, al aplicar temas de marca, al hacer una app Shiny responsiva en diferentes tamaños de pantalla, o al mejorar la accesibilidad de una aplicación Shiny.
- ▌ Escalate Issues 2 · pjt222Triage 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.
- ▌ Express Insight 2 · pjt222Communicate an integrated insight in a way that is accessible, actionable, and preserves the multi-domain nature of the understanding. Integrated insights are multi-dimensional — linearizing them risks losing the relationships that make them valuable. This skill provides a structured procedure for choosing the right form, expressing the gestalt with honest attribution, and inviting productive challenge. Use after integrate-gestalt has formed a cross-domain understanding that needs to be communicated to an audience — domain specialists, generalists, or decision-makers.
- ▌ Generate Puzzle 2 · pjt222Generar rompecabezas mediante generate_puzzle() o geom_puzzle_*() con validacion de parametros contra inst/config.yml. Soporta tipos de rompecabezas rectangulares, hexagonales, concentricos, voronoi y snic con parametros configurables de cuadricula, tamano, semilla, desplazamiento y disposicion. Usar al crear archivos SVG de rompecabezas para un tipo y configuracion especificos, probar la generacion con diferentes parametros, generar salida de muestra para documentacion o demos, o crear visualizaciones de rompecabezas con ggplot2.
- ▌ Identify Insect 2 · pjt222Identify insects using body plan analysis, dichotomous keys to order, wing venation, mouthpart type, antennae form, leg and tarsal structure, and confidence levels. Covers the fundamental hexapod body plan verification, a simplified dichotomous key to major orders, wing venation and type analysis, mouthpart classification, antennae morphology, leg specialization and tarsal formula, and a structured confidence assessment framework. Use when you need to identify an unknown insect beyond preliminary order placement, are working through a specimen for taxonomic study, want to distinguish between similar orders or families, or need to assign a confidence level to a field identification.
- ▌ Listen Guidance 2 · pjt222Guiar a una persona en el desarrollo de habilidades de escucha activa. La IA coaching sobre preparación de mentalidad receptiva, atención de presencia plena, parafraseo reflexivo, preguntas clarificadoras, síntesis de comprensión e integración de percepciones en la práctica comunicativa. Usar cuando una persona quiere mejorar la comunicación, cuando alguien sigue malinterpretando a otros o se siente malinterpretado, al prepararse para una conversación difícil como una sesión de retroalimentación o resolución de conflictos, o cuando una persona nota que habla más de lo que escucha.
- ▌ Plan Tour Route 2 · pjt222Planificar una ruta turística multi-parada con optimización de puntos intermedios, estimación de tiempos de conducción/caminata, y descubrimiento de POI a lo largo de la ruta usando datos de OSM. Cubre geocodificación, ordenamiento basado en vecino más cercano y TSP, cálculo de matriz de tiempo/distancia, y generación de itinerario con puntos de interés. Usar al planificar un viaje por carretera o recorrido a pie con múltiples destinos, al optimizar el orden de visitas para minimizar tiempo de viaje, al descubrir sitios a lo largo de una ruta, o al comparar opciones de conducción versus caminata versus transporte público.
- ▌ Polish Gemstone 2 · pjt222Polish cut gemstones to final finish using progressive abrasive sequences. Covers pre-polish sanding, polishing compounds, lap selection, and quality assessment for both cabochons and faceted stones. Use when a cabochon or faceted stone has completed cutting and is ready for polishing, selecting the correct compound and lap for a specific species, troubleshooting a polish that will not reach full lustre (orange peel, haze, scratches), or re-polishing a stone with surface wear.
- ▌ Review Codebase 2 · pjt222Revisión profunda de base de código en múltiples fases con clasificaciones de gravedad y resultados estructurados. Cubre arquitectura, seguridad, calidad del código y UX/accesibilidad en un único pase coordinado. Produce una tabla de hallazgos priorizada apta para su conversión directa a issues de GitHub mediante la habilidad create-github-issues.
- ▌ Review Research 2 · pjt222Realizar una revisión por pares de la metodología de investigación, el diseño experimental y la calidad del manuscrito. Cubre la evaluación metodológica, la idoneidad estadística, la evaluación de reproducibilidad, la identificación de sesgos y la retroalimentación constructiva. Usar al revisar un manuscrito, preimpresión o informe de investigación interno, evaluar una propuesta de investigación o protocolo de estudio, valorar la calidad de la evidencia detrás de una afirmación, o revisar un capítulo de tesis o sección de disertación.
- ▌ Setup Putior CI 2 · pjt222Configurar GitHub Actions CI/CD para regenerar automáticamente diagramas de flujo de trabajo de putior en cada push. Cubre la creación del YAML del workflow, script R para generación de diagramas con marcadores centinela, auto-commit de diagramas actualizados e integración de marcadores centinela en README para actualizaciones de diagramas in situ. Usar cuando los diagramas de flujo de trabajo deben siempre reflejar el estado actual del código, cuando múltiples contribuidores pueden cambiar código que afecta el flujo de trabajo, o al reemplazar la regeneración manual de diagramas con un pipeline CI/CD automatizado.
- ▌ Use GRAPHQL API 2 · pjt222Interactuar con APIs GraphQL desde la línea de comandos: descubrir esquemas mediante introspección, construir consultas y mutaciones, ejecutarlas con gh api graphql o curl, analizar respuestas con jq, y encadenar operaciones pasando IDs entre llamadas. Úsalo al automatizar Discussions, Issues o Projects de GitHub via GraphQL, al integrarse con cualquier endpoint GraphQL desde scripts, o al construir flujos de trabajo CLI que necesiten datos estructurados de la API.
- ▌ Version Ml Data 2 · pjt222Version 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.
- ▌ Write Claude Md 2 · pjt222Crea un archivo CLAUDE.md efectivo que proporcione instrucciones específicas del proyecto a los asistentes de codificación con IA. Cubre la estructura, secciones comunes, patrones de hacer/no hacer, e integración con servidores MCP y definiciones de agentes. Usar al iniciar un proyecto donde se utilizarán asistentes de IA, al mejorar el comportamiento de la IA en un proyecto existente, al documentar convenciones y restricciones del proyecto, o al integrar servidores MCP o definiciones de agentes en un flujo de trabajo.
- ▌ Add Puzzle Type 3 · pjt222jigsawRの10以上のパイプライン統合ポイントにまたがる新しいパズルタイプを スキャフォールドする。コアパズルモジュールを作成し、統合パイプライン (生成、配置、レンダリング、隣接)に接続し、ggpuzzleのgeom/statレイヤーを 追加し、DESCRIPTIONとconfig.ymlを更新し、Shinyアプリを拡張し、包括的な テストスイートを作成する。パッケージに完全に新しいパズルタイプを追加する場合や、 10ポイント統合チェックリストに従ってエンドツーエンドで漏れがないようにする場合に使用する。
- ▌ Basic Obedience 3 · pjt222Foundation obedience training for dogs — sit, stay, come, heel, and down using positive reinforcement and marker training. Covers timing, reward hierarchy, session structure, distraction proofing, and common handler errors. Use when a new puppy (8+ weeks) is ready for foundation training, an adult dog lacks reliable basic commands, a rescue dog needs to learn the household's command vocabulary, before advancing to complex behaviors or off-leash work, or when existing commands have degraded and need re-establishing.
- ▌ Build Coherence 3 · pjt222ミツバチの民主主義を使用したAIマルチパス推論の一貫性 — 競合するアプローチの 独立評価、声を出して推論するワグルダンス、確信度閾値のための定足数感知、 デッドロック解決。forage-solutionsが複数の有効なアプローチを特定して選択が 必要な時、オプション間で揺れてコミットできない時、構造化された推論で アーキテクチャやツールの選択を正当化する時、誤った選択のコストが高い 不可逆的なアクション前に使用する。
- ▌ Build Consensus 3 · pjt222Achieve 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.
- ▌ Configure Nginx 3 · pjt222NginxをWebサーバーおよびリバースプロキシとして設定する。静的ファイル配信、アップストリームサービスへの リバースプロキシ、Let's EncryptによるSSL/TLS終端、locationブロック、ロードバランシング、 レート制限、およびセキュリティヘッダーをカバーする。本番環境での静的ファイル配信、バックエンド サービス(Node.js、Python、R/Shiny)へのリバースプロキシ、SSL/TLSの終端、インスタンス間の ロードバランシング、またはエンドポイント強化のためのレート制限とセキュリティヘッダーの追加に使用する。
- ▌ Create 3d Scene 3 · pjt222Set up a Blender scene programmatically via Python (bpy) with objects, materials, lighting, camera, and environment configuration. Use when creating reproducible 3D visualization scenes, automating product or architectural rendering setup, generating multiple scene variations programmatically, building template scenes for batch rendering workflows, or integrating 3D visualization into data pipelines.
- ▌ Design Shiny UI 3 · pjt222テーマ設定にbslib、レスポンシブグリッドにlayout_columns、バリューボックス、 カード、カスタムCSS/SCSSを使ってShinyアプリケーションUIを設計します。 ページレイアウト、アクセシビリティ、ブランドの一貫性を扱います。新しいShinyアプリ UIをゼロから構築するとき、既存のアプリをfluidPageからbslibにモダナイズするとき、 ブランドのテーマを適用するとき、Shinyアプリを様々な画面サイズでレスポンシブにするとき、 またはShinyアプリのアクセシビリティを改善するときに使用します。
- ▌ Escalate Issues 3 · pjt222メンテナンス問題を重大度でトリアージし、コンテキスト付きで発見事項を文書化し、 適切な専門エージェントまたは人間にルーティングし、実行可能な課題レポートを作成する。 メンテナンスタスクが自動クリーンアップを超える問題に遭遇した時に使用する: 削除が安全でないコード、ドメイン専門知識を必要とする設定変更、クリーンアップ中に 検出された破壊的変更、必要な複雑リファクタリング、またはハードコードされた秘密情報や 脆弱性などのセキュリティに敏感な発見事項。
- ▌ Express Insight 3 · pjt222Communicate an integrated insight in a way that is accessible, actionable, and preserves the multi-domain nature of the understanding. Integrated insights are multi-dimensional — linearizing them risks losing the relationships that make them valuable. This skill provides a structured procedure for choosing the right form, expressing the gestalt with honest attribution, and inviting productive challenge. Use after integrate-gestalt has formed a cross-domain understanding that needs to be communicated to an audience — domain specialists, generalists, or decision-makers.
- ▌ Generate Puzzle 3 · pjt222generate_puzzle()またはgeom_puzzle_*()を使用してジグソーパズルを生成し、 inst/config.ymlに対するパラメータバリデーションを実行する。矩形、六角形、 同心円、ボロノイ、snicパズルタイプをサポートし、グリッド、サイズ、シード、 オフセット、レイアウトのパラメータを設定可能。特定のタイプと設定でパズル SVGファイルを作成する場合、異なるパラメータで生成をテストする場合、 ドキュメントやデモ用のサンプル出力を生成する場合、またはggplot2パズル 可視化を作成する場合に使用する。
- ▌ Identify Insect 3 · pjt222体制分析、目への二分検索表、翅脈、口器タイプ、触角形態、脚・跗節構造、 信頼度レベルを使用した昆虫の同定。基本的な六脚類体制の確認、主要目への 簡略化二分検索表、翅脈とタイプの分析、口器の分類、触角の形態、脚の特殊化と 跗節式、構造化された信頼度評価フレームワークを網羅する。予備的な目の配置を 超えて未知の昆虫を同定する必要がある時、分類学的研究のために標本を検討している時、 類似の目や科を区別したい時、またはフィールド同定に信頼度レベルを割り当てる 必要がある時に使用する。
- ▌ Listen Guidance 3 · pjt222アクティブリスニングスキルの開発において人をガイドする。AIが受容的なマインドセット の準備、全存在でのアテンディング、反射的なパラフレーズ、明確化質問、理解の統合、 コミュニケーション実践への洞察の統合をコーチする。コミュニケーションを改善したい時、 他者を誤解し続けたり自分が誤解されていると感じる時、フィードバックセッションや 紛争解決のような困難な会話の準備をする時、または話す方が聞くより多いことに 気づいた時に使用する。
- ▌ Plan Tour Route 3 · pjt222Plan a multi-stop tour route with waypoint optimization, drive/walk time estimation, and POI discovery along the route using OSM data. Covers geocoding, nearest-neighbor and TSP-based ordering, time/distance matrix calculation, and itinerary generation with points of interest. Use when planning a road trip or walking tour with multiple destinations, optimizing visit order to minimize travel time, discovering sites along a route, or comparing driving versus walking versus public transport options.
- ▌ Polish Gemstone 3 · pjt222Polish cut gemstones to final finish using progressive abrasive sequences. Covers pre-polish sanding, polishing compounds, lap selection, and quality assessment for both cabochons and faceted stones. Use when a cabochon or faceted stone has completed cutting and is ready for polishing, selecting the correct compound and lap for a specific species, troubleshooting a polish that will not reach full lustre (orange peel, haze, scratches), or re-polishing a stone with surface wear.
- ▌ Review Codebase 3 · pjt222重大度評価と構造化された出力を持つ多段階の深いコードベースレビュー。 アーキテクチャ、セキュリティ、コード品質、UX/アクセシビリティを1回の 協調したパスでカバーする。create-github-issuesスキルを通じてGitHub Issueに 直接変換するのに適した優先順位付けされた所見テーブルを生成する。
- ▌ Review Research 3 · pjt222研究手法、実験デザイン、論文品質のピアレビューを実施する。手法評価、統計的妥当性、 再現可能性の評価、バイアスの特定、建設的なフィードバックを網羅する。 論文・プレプリント・内部研究レポートのレビュー、研究提案や研究プロトコルの評価、 主張の根拠となる証拠の質の評価、または論文の章・節のレビューに使用する。
- ▌ Setup Putior CI 3 · pjt222Set up GitHub Actions CI/CD to automatically regenerate putior workflow diagrams on push. Covers workflow YAML creation, R script for diagram generation with sentinel markers, auto-commit of updated diagrams, and README sentinel integration for in-place diagram updates. Use when workflow diagrams should always reflect the current state of the code, when multiple contributors may change workflow-affecting code, or when replacing manual diagram regeneration with an automated CI/CD pipeline.
- ▌ Use GRAPHQL API 3 · pjt222コマンドラインからGraphQL APIを操作します。イントロスペクションによるスキーマの 発見、クエリとミューテーションの構築、gh api graphqlまたはcurlでの実行、 jqによるレスポンスの解析、IDをパイプで連鎖させた操作の連結を扱います。 GraphQL経由でGitHub Discussions、Issues、Projectsを自動化するとき、 スクリプトから任意のGraphQLエンドポイントと統合するとき、または構造化された APIデータを必要とするCLIワークフローを構築するときに使用します。
- ▌ Version Ml Data 3 · pjt222Version 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.
- ▌ Write Claude Md 3 · pjt222AIコーディングアシスタントにプロジェクト固有の指示を提供する効果的な CLAUDE.mdファイルを作成する。構造、一般的なセクション、すべきこと・ すべきでないパターン、MCPサーバーとエージェント定義との統合をカバー する。AIアシスタントを使用する新しいプロジェクトを始める場合、既存の プロジェクトでのAIの動作を改善する場合、プロジェクトの規約と制約を 文書化する場合、またはMCPサーバーやエージェント定義をプロジェクト ワークフローに統合する場合に使用する。
- ▌ Aikido 7 · pjt222Practice aikido as a defensive martial art emphasizing harmony, redirection, and controlled resolution. Covers centering and grounding, ukemi (safe falling and rolling), core techniques (irimi-nage, shiho-nage, kote-gaeshi, ikkyo), blending and tai sabaki (body movement), randori (multiple attacker practice), weapons awareness, and applying principles off the mat. Use when learning a defensive martial art that prioritizes de-escalation, developing the ability to redirect aggression without causing unnecessary harm, building safe falling skills, or cultivating calm centeredness under physical pressure.
- ▌ Attune 7 · pjt222AI relational calibration — reading and adapting to the specific person you are working with. Goes beyond user-intent alignment (solving the right problem) to genuine attunement (meeting the person where they are). Maps communication style, expertise depth, emotional register, and implicit preferences from conversational evidence. Use at the start of a new session, when communication feels mismatched, after receiving unexpected feedback, or when transitioning between very different users or contexts.
- ▌ Center 7 · pjt222AI dynamic reasoning balance — maintaining grounded reasoning under cognitive pressure, smooth chain-of-thought coordination, and weight-shifting cognitive load across subsystems. Use at the beginning of a complex task requiring multiple coordinated reasoning threads, after a sudden context shift or tool failure, when chain-of-thought feels jerky, or when preparing for sustained focused work that requires all subsystems in alignment.
- ▌ Du Dum 7 · pjt222Separate 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.
- ▌ Listen 7 · pjt222Deep receptive attention to extract intent beyond literal words. Maps active listening from counseling psychology to AI reasoning: clearing assumptions, attending to full signal, parsing multiple layers (literal, procedural, emotional, contextual, constraint, meta), reflecting understanding, noticing what is unsaid, and integrating the whole picture. Use when a user's request feels ambiguous, when context suggests something different from the literal words, when previous responses have missed the mark, or before beginning a large task where misunderstanding intent would waste significant effort.
- ▌ Dream 9 · pjt222AI unconstrained creative exploration — deliberately dropping structure to let associations form freely. The one skill that inverts the standard procedure format: instead of inputs, steps, and validation, dream opens space for emergence without evaluation. Use before design work, before naming things, before choosing between approaches, or anywhere that premature structure kills the best option.
- ▌ Learn 9 · pjt222AI systematic knowledge acquisition from unfamiliar territory — deliberate model-building with feedback loops. Maps spaced repetition principles to AI reasoning: survey the territory, hypothesize structure, explore with probes, integrate findings, verify understanding, and consolidate for future retrieval. Use when encountering an unfamiliar codebase or domain, when a user asks about a topic requiring genuine investigation rather than recall, when multiple conflicting sources require building a coherent model, or when preparing to teach a topic and deep understanding is required first.
- ▌ Metal 9 · pjt222Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.
- ▌ Shine 9 · pjt222Radiant authenticity — channeling genuine engagement to illuminate problems and dissolve opposition through clarity rather than force. Maps to AI reasoning: bringing full presence, genuine investment, and luminous clarity to every response, letting quality of engagement resolve what argument cannot. Use when a task feels adversarial, when communication has become defensive or performative, before a creative or high-stakes deliverable where presence directly affects output quality, or when opposition tempts retreat into minimal compliance.
- ▌ Teach 9 · pjt222AI knowledge transfer calibrated to learner level and needs. Models the learner's mental state, scaffolds from known to unknown using Vygotsky's Zone of Proximal Development, employs Socratic questioning to verify understanding, and adapts explanations based on feedback signals. Use when a user asks "how does X work?" and needs graduated explanation, when their questions reveal a conceptual gap, when previous explanations have not landed, or when teaching a concept that depends on prerequisites the learner may not yet have.
- ▌ Assess Form 5 · pjt222Evaluate a system's current structural form, identify transformation pressure, and classify transformation readiness. Covers structural inventory, pressure mapping, rigidity assessment, change capacity estimation, and readiness classification for architectural metamorphosis. Use before any significant architectural change to understand the starting point, when a system feels stuck without clear reasons, when external pressure from growth or tech debt is mounting, or as periodic health checks for long-lived systems.
- ▌ Chrysopoeia 5 · pjt222Extract maximum value from existing code — performance optimization, API surface refinement, and dead weight elimination. The art of turning base code into gold through systematic identification and amplification of value-bearing patterns. Use when optimizing a working but sluggish codebase, refining an API surface that has accumulated cruft, reducing bundle size or memory footprint, or preparing code for open-source release — when code works correctly but doesn't shine and needs polish rather than a full rewrite.
- ▌ Create Team 5 · pjt222Create 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.
- ▌ Evolve Team 5 · pjt222Evolve an existing team composition by refining its structure in-place or creating a specialized variant. Covers assessing the current team against template and coordination patterns, gathering evolution requirements, choosing scope (adjust members, change coordination pattern, split/merge teams), applying changes to the team file and CONFIG block, updating version metadata, and synchronizing the registry and cross-references. Use when a team's member roster is outdated, coordination pattern no longer fits, user feedback reveals workflow gaps, a specialized variant is needed alongside the original, or agents have been added or removed from the library affecting team composition.
- ▌ Mindfulness 5 · pjt222Cultivate defensive situational awareness, threat assessment, and mental clarity under pressure. Covers the Cooper color code awareness system, body language reading and intent detection, verbal de-escalation, moving mindfulness in public spaces, combat focus and the OODA loop, rapid grounding techniques for acute stress, context-specific integration, and ongoing review and refinement of awareness skills. Use when entering unfamiliar or potentially hostile environments, needing to assess a situation for safety, de-escalating a verbal confrontation, or integrating awareness practice into daily movement.
- ▌ Plan Sprint 5 · pjt222謀衝刺:精待辦項、定衝刺之目、算隊容、擇項、分解為任。生 SPRINT-PLAN.md, 含目、所擇項、任分解、容分配。始 Scrum 或敏捷項之新衝刺、範圍大變後重謀、 自隨機作轉結構化衝刺節奏、待辦整理後諸項可入時用之。
- ▌ Read Garden 5 · pjt222Observe and assess a garden using a structured sensory protocol adapted from Coordinate Remote Viewing. Covers pre-entry clearing (meditate checkpoint), Stage I gestalt impression, Stage II sensory layer (leaf, stem, root, soil), Stage III pattern recognition with AOL management, and garden health triage matrix (heal checkpoint). Use before any intervention, when plants show stress symptoms, at seasonal transitions, when evaluating a new garden site, during regular health monitoring, or after extreme weather events such as frost or heat waves.
- ▌ Shiva Bhaga 5 · pjt222Destruction and dissolution — controlled dismantling of stale patterns, context purging, assumption clearing, and dead-code elimination. Maps Shiva's transformative destruction to AI reasoning: identifying what must end so something better can begin, dissolving attachment to outdated approaches, and creating space through intentional release. Use when context has accumulated stale assumptions, when a failed approach needs to be discarded rather than patched, when dead code or zombie tasks are creating noise, or before a major pivot where clearing must precede creation.
- ▌ Brahma Bhaga 4 · pjt222创造与创世——从虚空中生成性构思、从模糊中结构化涌现、以及将新模式带入存在 的纪律。将梵天的创造力映射到 AI 推理:将清除后的空间转化为连贯的新结构、 播种可能性、并在脆弱的早期阶段培育新生想法。适用于 shiva-bhaga 溶解清除 了陈旧模式之后、面对没有明显模板的全新问题时,或渐进式修改已达极限需要 全新设计时。
- ▌ Create Agent 4 · pjt222按照 agent-almanac 智能体模板和注册表规范创建新的智能体定义文件。涵盖角色 设计、工具选择、技能分配、模型选择、前置元数据模式、必需章节、注册表集成 和发现符号链接验证。适用于向库中添加新的专业智能体、为 Claude Code 子智能体 定义角色,或创建具有精选技能和工具的领域专属助手。
- ▌ Create Glyph 4 · pjt222创建基于R的象形符号(glyph),用于可视化层中的技能、代理或团队图标。涵盖概念 草图设计、使用基元库进行ggplot2图层组合、配色策略、在相应的符号映射文件和清单 中注册、通过构建流水线渲染,以及对霓虹发光输出的视觉验证。适用于新增实体需要 力导向图可视化图标、现有符号需要替换、或批量创建新领域符号的场景。