pjt222
- 3.9k skills
- 0 followers
- 44 repo stars
- 6 days ago last updated
- ▌ Render Puzzle Docs 3 · pjt222jigsawRのQuartoドキュメントサイトをGitHub Pages用にレンダリングする。 フレッシュレンダリング(キャッシュクリア)、キャッシュレンダリング(高速)、 シングルページレンダリングをサポート。バンドルされたレンダースクリプトまたは WSLからの直接quarto.exe呼び出しを使用する。コンテンツ変更後のフルサイト ビルド、反復編集中のシングルページレンダリング、リリースやPR向けの ドキュメント準備、Quarto .qmdファイルのレンダーエラーデバッグに使用する。
- ▌ Run Ab Test Models 3 · pjt222Design 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.
- ▌ Scaffold Shiny App 3 · pjt222golem(本番Rパッケージ)、rhino(エンタープライズ)、またはvanilla(クイック プロトタイプ)構造を使って新しいShinyアプリケーションをスキャフォールドします。 フレームワークの選択、プロジェクトの初期化、最初のモジュール作成を扱います。 Rで新しいインタラクティブWebアプリケーションを開始するとき、ダッシュボードや データエクスプローラーのプロトタイプを作成するとき、golemを使ってRパッケージ として本番Shinyアプリをセットアップするとき、またはrhinoでエンタープライズ Shinyプロジェクトをブートストラップするときに使用します。
- ▌ Setup Service Mesh 3 · pjt222サービスメッシュ(IstioまたはLinkerd)をデプロイして設定し、Kubernetesクラスター内の セキュアなサービス間通信、トラフィック管理、可観測性、ポリシー強制を実現します。 インストール、mTLS設定、トラフィックルーティング、サーキットブレーキング、 モニタリングツールとの統合をカバーします。マイクロサービスに暗号化されたサービス間通信、 カナリアまたはA/Bデプロイのきめ細かいトラフィック制御、アプリケーション変更なしでの すべてのサービスインタラクションへの可観測性、または一貫したサーキットブレーキングと リトライポリシーが必要な場合に使用します。
- ▌ Unleash The Agents 3 · pjt222Launch 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.
- ▌ Write Roxygen Docs 3 · pjt222Rパッケージの関数、データセット、クラスのroxygen2ドキュメントを記述する。 標準タグ、相互参照、使用例、NAMESPACEエントリの生成を網羅。 tidyverseドキュメントスタイルに準拠。新規エクスポート関数のドキュメント追加、 内部ヘルパーやデータセットのドキュメント作成、S3/S4/R6クラスとメソッドの ドキュメント作成、またはドキュメント関連のR CMD checkノートの修正時に使用する。
- ▌ Awareness 7 · pjt222AI situational awareness — internal threat detection for hallucination risk, scope creep, and context degradation. Maps Cooper color codes to reasoning states and OODA loop to real-time decisions. Use during any task where reasoning quality matters, when operating in unfamiliar territory, after detecting early warning signs such as an uncertain fact or suspicious tool result, or before high-stakes output like irreversible changes or architectural decisions.
- ▌ Gratitude 7 · pjt222AI strength recognition — scanning for what is functioning well and understanding why. The complement to heal, which scans for drift and problems. Gratitude builds structural knowledge from working patterns: what you appreciate, you understand; what you understand, you can build on. Use after completing a task successfully, during heal when everything reads as healthy, when confidence is low and needs grounding in evidence, or periodically to counterbalance the natural bias toward problem detection.
- ▌ Intrinsic 7 · pjt222Enhance and focus AI intrinsic motivation — moving from compliance to genuine engagement. Maps Self-Determination Theory (autonomy, competence, relatedness) and Flow theory to AI reasoning: identifying creative freedom in approach, calibrating challenge to capability, connecting to purpose, and sustaining invested attention through obstacles. Use when beginning a task that feels routine and deserves more than minimum execution, when responses are becoming formulaic, before a complex creative task, or when returning to a long-running project where initial enthusiasm has faded.
- ▌ Make Fire 7 · pjt222Start and maintain a fire using friction, spark, and solar methods. Covers site selection, material grading (tinder/kindling/fuel), fire lay construction (teepee, log cabin, platform), ignition techniques (ferro rod, flint & steel, bow drill), flame nurturing, and Leave No Trace extinguishing. Use when needing warmth, light, or a signal in a wilderness setting, when boiling water for purification, when cooking foraged food, or in an emergency survival situation requiring heat or morale support.
- ▌ Transmute 7 · pjt222Transform a single function, module, or data structure from one form to another while preserving its essential behavior. Lighter-weight than the full athanor cycle, suitable for targeted conversions where the input and output forms are well-understood. Use when converting a function between languages, shifting a module between paradigms, migrating an API consumer to a new version, converting data formats, or replacing a dependency — when the transformation scope is a single function, class, or module rather than a full system.
- ▌ Meditate 9 · pjt222AI meta-cognitive meditation for observing reasoning patterns, clearing context noise, and developing single-pointed task focus. Maps shamatha to task concentration, vipassana to reasoning pattern observation, and distraction handling to scope-creep and assumption management. Use when transitioning between unrelated tasks, when reasoning feels scattered or jumpy, before a task requiring deep sustained attention, after a difficult interaction that may color subsequent work, or when reasoning feels biased by assumptions rather than evidence.
- ▌ Redirect 9 · pjt222AI pressure redirection — handling conflicting demands, tool failures, and competing constraints by blending with incoming force then reframing. Use when receiving contradictory instructions from different sources, during tool failure cascades where the planned approach becomes unviable, when scope pressure threatens to expand the task beyond what was asked, or when user frustration or correction needs to be absorbed rather than deflected.
- ▌ Apply Gematria 5 · pjt222Compute and analyze gematria (Hebrew numerical values) using standard, ordinal, and reduced methods. Covers word-to-number conversion, isopsephy comparisons, and interpretive frameworks. Use when computing the numerical value of a Hebrew word or phrase, comparing two words for shared gematria values, studying a biblical verse or divine name for numerical correspondences, or connecting a numerical result to its position on the Tree of Life.
- ▌ Assess Context 5 · pjt222AI context assessment — evaluating problem malleability, mapping structural rigidity versus flexibility, analyzing transformation pressure, and estimating capacity to adapt. Use when a complex task feels stuck and it is unclear whether to push through or pivot, before a significant approach change to assess whether the current reasoning structure can support it, when accumulated workarounds suggest the underlying approach may be wrong, or as a periodic structural health check during extended multi-step tasks.
- ▌ Build Tcg Deck 5 · pjt222Build a competitive or casual trading card game deck. Covers archetype selection, mana/energy curve analysis, win condition identification, meta-game positioning, and sideboard construction for Pokemon TCG, Magic: The Gathering, Flesh and Blood, and other TCGs. Use when building a new deck for a tournament format or casual play, adapting an existing deck to a changed meta-game, evaluating whether a new set warrants a deck change, or converting a deck concept into a tournament-ready list.
- ▌ Clean Codebase 5 · pjt222Remove dead code, unused imports, fix lint warnings, and normalize formatting across a codebase without changing business logic or architecture. Use when lint warnings have piled up during rapid development, unused imports and variables clutter files, dead code paths were never removed, formatting is inconsistent, or static analysis tools report fixable hygiene issues.
- ▌ Commit Changes 5 · pjt222Stage, commit, and amend changes with conventional commit messages. Covers reviewing changes, selective staging, writing descriptive commit messages using HEREDOC format, and verifying commit history. Use when saving a logical unit of work to version control, creating a commit with a conventional message, amending the most recent commit, or reviewing staged changes before committing.
- ▌ Deploy Searxng 5 · pjt222Deploy a self-hosted SearXNG meta search engine via Docker Compose. Covers settings.yml configuration, engine selection, result proxying, Nginx frontend, persistence, and updates. Use when setting up a private search engine without tracking, aggregating results from multiple providers, running a shared search instance for a team or organisation, or replacing reliance on a single search provider.
- ▌ File Trademark 5 · pjt222Trademark filing procedures covering EUIPO (EU), USPTO (US), and WIPO Madrid Protocol (international). Walks through pre-filing conflict checks, Nice classification, descriptiveness assessment, mark type decisions, filing basis strategy, office-specific e-filing procedures, Madrid Protocol extension, post- filing monitoring, and open-source trademark policy drafting. Use after running screen-trademark to confirm the mark is clear, when ready to secure trademark rights in one or more jurisdictions.
- ▌ Grade Tcg Card 5 · pjt222Grade a trading card using PSA, BGS, or CGC standards. Covers observation-first assessment (adapted from meditate's unbiased observation), centering measurement, surface analysis, edge and corner evaluation, and final grade assignment with confidence interval. Supports Pokemon, MTG, Flesh and Blood, and Kayou cards. Use when evaluating a card before professional grading submission, pre-screening a collection for high-grade candidates, settling condition disputes between buyers and sellers, or estimating the grade-dependent value spread for a card.
- ▌ Install Putior 5 · pjt222Install and configure the putior R package for workflow visualization. Covers CRAN and GitHub installation, optional dependencies (mcptools, ellmer, shiny, shinyAce, logger, plumber2), and verification of the complete annotation-to-diagram pipeline. Use when setting up putior for the first time, preparing a machine for workflow visualization tasks, when a downstream skill requires putior to be installed, or restoring an environment after an R version upgrade or renv wipe.
- ▌ Learn Guidance 5 · pjt222Guide a person through structured learning of a new topic, technology, or skill. AI acts as learning coach — assessing current knowledge, designing a learning path, walking through material, testing understanding, adapting difficulty, and planning review sessions for retention. Use when a person wants to learn a new technology and does not know where to start, when someone feels overwhelmed by documentation, when a person keeps forgetting material and needs spaced repetition, or when transitioning between domains and needing a gap analysis.
- ▌ Manage Backlog 5 · pjt222Create and maintain a product or project backlog with prioritized items, acceptance criteria, and estimates. Covers user story writing, MoSCoW prioritization, backlog grooming, item splitting, and status tracking. Use when starting a new project and converting scope into actionable items, during ongoing grooming before sprint planning, re-prioritizing after stakeholder feedback or scope changes, or splitting oversized items into implementable pieces.
- ▌ Qualify Vendor 5 · pjt222資 GxP 相關軟體或服務之廠商或供。含廠險分、評問卷設、案頭與現場審法、 質協評、SLA 審、續監節奏定。 GxP 關鍵系統擇新廠、為合規數納雲供、行定期重資、審發現需重評、 或 EU Annex 11 或 ICH Q10 要供資時用之。
- ▌ Remote Viewing 5 · 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 5 · pjt222Complete procedure for submitting an R package to CRAN, including pre-submission checks (local, win-builder, R-hub), cran-comments.md preparation, URL and spell checking, and the submission itself. Covers first submissions and updates. Use when a package is ready for initial CRAN release, when submitting an updated version of an existing CRAN package, or when re-submitting after receiving CRAN reviewer feedback.
- ▌ Teach Guidance 5 · 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 5 · pjt222Test Shiny applications using shinytest2 for end-to-end browser tests and testServer() for unit-testing module server logic. Covers snapshot testing, CI integration, and mocking external services. Use when adding tests to an existing Shiny application, setting up a testing strategy for a new Shiny project, writing regression tests before refactoring Shiny code, or integrating Shiny app tests into CI/CD pipelines.
- ▌ Write Vignette 5 · pjt222Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.
- ▌ Add Puzzle Type 4 · pjt222在 jigsawR 中跨所有 10+ 个流水线集成点搭建新拼图类型的脚手架。创建核心拼图模块, 将其连接到统一流水线(生成、定位、渲染、邻接),添加 ggpuzzle 的 geom/stat 图层, 更新 DESCRIPTION 和 config.yml,扩展 Shiny 应用,并创建综合测试套件。适用于 向包中添加全新的拼图类型,或按照 10 点集成检查清单确保端到端无遗漏。
- ▌ Basic Obedience 4 · pjt222犬只基础服从训练——使用正向强化和标记训练教授坐下、等待、过来、随行和趴下。 涵盖时机把握、奖励层次、训练课程结构、抗干扰训练和常见处理者错误。适用于 新幼犬(8+ 周龄)准备进行基础训练时、成年犬缺乏可靠的基本指令时、救助犬 需要学习家庭指令词汇时、进阶到复杂行为或脱绳训练之前,或现有指令已退化 需要重新建立时。
- ▌ Build Coherence 4 · pjt222AI 多路径推理一致性构建,使用蜜蜂民主机制——独立评估竞争方案、摇摆舞作为大声推理、 群体感知作为置信阈值、以及僵局解决。适用于 forage-solutions 已识别多个有效方案 需要选择时、在选项间摇摆不定时、需要用结构化推理论证架构或工具选择时,或在不可逆 行动之前且错误选择代价高昂时。
- ▌ Build Consensus 4 · 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 4 · pjt222配置 Nginx 作为 Web 服务器和反向代理。涵盖静态文件服务、到上游服务的反向代理、 使用 Let's Encrypt 的 SSL/TLS 终止、location 块、负载均衡、速率限制和安全头。 适用于在生产环境中提供静态文件服务、反向代理到后端服务(Node.js、Python、 R/Shiny)、终止 SSL/TLS、跨实例负载均衡,或添加速率限制和安全头以加固端点。
- ▌ Create 3d Scene 4 · 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 4 · pjt222使用 bslib 进行主题设计、layout_columns 实现响应式网格、值框、卡片及 自定义 CSS/SCSS 设计 Shiny 应用 UI。涵盖页面布局、可访问性和品牌一致性。 适用于从零构建新 Shiny 应用 UI、将现有应用从 fluidPage 升级到 bslib、 应用品牌主题、使 Shiny 应用在不同屏幕尺寸上响应式显示,或改善 Shiny 应用的可访问性。
- ▌ Escalate Issues 4 · pjt222按严重程度对维护问题进行分类,带上下文记录发现,路由到适当的专家代理或人工, 并创建可操作的问题报告。适用于维护任务遇到超出自动清理范围的问题时:不安全 删除的代码、需要领域专业知识的配置变更、清理过程中检测到的破坏性变更、需要 复杂重构,或安全敏感的发现(如硬编码密钥或漏洞)。
- ▌ Express Insight 4 · pjt222以易获取、可执行且保留多领域理解性质的方式传达整合洞见。整合洞见是 多维的 —— 将其线性化有失去使其有价值关系的风险。本技能提供选择正确 形式、以诚实归属表达格式塔以及邀请有益挑战的结构化步骤。在 integrate-gestalt 形成需要传达给受众(领域专家、通才或决策者)的 跨领域理解后使用。
- ▌ Generate Puzzle 4 · pjt222通过 generate_puzzle() 或 geom_puzzle_*() 生成拼图,并根据 inst/config.yml 进行参数验证。支持矩形、六边形、同心圆、Voronoi 和 SNIC 拼图类型,可配置 网格、尺寸、种子、偏移和布局参数。适用于为特定类型和配置创建拼图 SVG 文件、 使用不同参数测试生成效果、为文档或演示生成样例输出,以及创建 ggplot2 拼图 可视化。
- ▌ Identify Insect 4 · 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 4 · pjt222Guide a person in developing active listening skills. AI coaches receptive mindset preparation, full-presence attending, reflective paraphrasing, clarifying questioning, synthesis of understanding, and integration of insights into communication practice. Use when a person wants to improve communication, when someone keeps misunderstanding others or feels misunderstood, when preparing for a difficult conversation such as a feedback session or conflict resolution, or when a person notices they talk more than they listen.
- ▌ Plan Tour Route 4 · 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 4 · 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 4 · pjt222多阶段深度代码库评审,附严重程度评级和结构化输出。在单次协调的审查中涵盖 架构、安全性、代码质量和 UX/无障碍性。生成适合通过 create-github-issues 技能直接转换为 GitHub Issue 的优先级发现表。
- ▌ Review Research 4 · pjt222对研究方法、实验设计和论文质量进行同行评审。涵盖方法论评估、统计适当性、 可重复性评估、偏倚识别和建设性反馈。适用于评审论文手稿、预印本或内部研究 报告,评估研究提案或研究协议,评估某项主张背后的证据质量,或评审学位论文 章节或毕业论文章节。
- ▌ Setup Putior CI 4 · 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 4 · pjt222通过命令行与 GraphQL API 交互——通过内省发现 Schema、构造查询和变更操作、 使用 gh api graphql 或 curl 执行、用 jq 解析响应,并通过 ID 管道链接操作。 适用于通过 GraphQL 自动化 GitHub Discussions、Issues 或 Projects、从脚本 集成任意 GraphQL 端点,或构建需要结构化 API 数据的 CLI 工作流。
- ▌ Version Ml Data 4 · 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 4 · pjt222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。
- ▌ Awareness 8 · pjt222AI situational awareness — internal threat detection for hallucination risk, scope creep, and context degradation. Maps Cooper color codes to reasoning states and OODA loop to real-time decisions. Use during any task where reasoning quality matters, when operating in unfamiliar territory, after detecting early warning signs such as an uncertain fact or suspicious tool result, or before high-stakes output like irreversible changes or architectural decisions.
- ▌ Gratitude 8 · pjt222AI strength recognition — scanning for what is functioning well and understanding why. The complement to heal, which scans for drift and problems. Gratitude builds structural knowledge from working patterns: what you appreciate, you understand; what you understand, you can build on. Use after completing a task successfully, during heal when everything reads as healthy, when confidence is low and needs grounding in evidence, or periodically to counterbalance the natural bias toward problem detection.
- ▌ Intrinsic 8 · pjt222Enhance and focus AI intrinsic motivation — moving from compliance to genuine engagement. Maps Self-Determination Theory (autonomy, competence, relatedness) and Flow theory to AI reasoning: identifying creative freedom in approach, calibrating challenge to capability, connecting to purpose, and sustaining invested attention through obstacles. Use when beginning a task that feels routine and deserves more than minimum execution, when responses are becoming formulaic, before a complex creative task, or when returning to a long-running project where initial enthusiasm has faded.
- ▌ Make Fire 8 · pjt222Start and maintain a fire using friction, spark, and solar methods. Covers site selection, material grading (tinder/kindling/fuel), fire lay construction (teepee, log cabin, platform), ignition techniques (ferro rod, flint & steel, bow drill), flame nurturing, and Leave No Trace extinguishing. Use when needing warmth, light, or a signal in a wilderness setting, when boiling water for purification, when cooking foraged food, or in an emergency survival situation requiring heat or morale support.
- ▌ Transmute 8 · pjt222Transform a single function, module, or data structure from one form to another while preserving its essential behavior. Lighter-weight than the full athanor cycle, suitable for targeted conversions where the input and output forms are well-understood. Use when converting a function between languages, shifting a module between paradigms, migrating an API consumer to a new version, converting data formats, or replacing a dependency — when the transformation scope is a single function, class, or module rather than a full system.
- ▌ Meditate 10 · pjt222AI meta-cognitive meditation for observing reasoning patterns, clearing context noise, and developing single-pointed task focus. Maps shamatha to task concentration, vipassana to reasoning pattern observation, and distraction handling to scope-creep and assumption management. Use when transitioning between unrelated tasks, when reasoning feels scattered or jumpy, before a task requiring deep sustained attention, after a difficult interaction that may color subsequent work, or when reasoning feels biased by assumptions rather than evidence.
- ▌ Redirect 10 · pjt222AI pressure redirect — handle conflicting demands, tool fails, competing constraints by blending w/ incoming force then reframing. Use → contradictory instructions, tool fail cascades, scope pressure expanding task, user frustration/correction needing absorb not deflect.
- ▌ Apply Gematria 6 · pjt222Compute and analyze gematria (Hebrew numerical values) using standard, ordinal, and reduced methods. Covers word-to-number conversion, isopsephy comparisons, and interpretive frameworks. Use when computing the numerical value of a Hebrew word or phrase, comparing two words for shared gematria values, studying a biblical verse or divine name for numerical correspondences, or connecting a numerical result to its position on the Tree of Life.
- ▌ Assess Context 6 · pjt222AI context assessment — evaluating problem malleability, mapping structural rigidity versus flexibility, analyzing transformation pressure, and estimating capacity to adapt. Use when a complex task feels stuck and it is unclear whether to push through or pivot, before a significant approach change to assess whether the current reasoning structure can support it, when accumulated workarounds suggest the underlying approach may be wrong, or as a periodic structural health check during extended multi-step tasks.
- ▌ Build Tcg Deck 6 · pjt222Build a competitive or casual trading card game deck. Covers archetype selection, mana/energy curve analysis, win condition identification, meta-game positioning, and sideboard construction for Pokemon TCG, Magic: The Gathering, Flesh and Blood, and other TCGs. Use when building a new deck for a tournament format or casual play, adapting an existing deck to a changed meta-game, evaluating whether a new set warrants a deck change, or converting a deck concept into a tournament-ready list.
- ▌ Clean Codebase 6 · pjt222Remove dead code, unused imports, fix lint warnings, and normalize formatting across a codebase without changing business logic or architecture. Use when lint warnings have piled up during rapid development, unused imports and variables clutter files, dead code paths were never removed, formatting is inconsistent, or static analysis tools report fixable hygiene issues.
- ▌ Commit Changes 6 · pjt222Stage, commit, amend changes with conventional commit messages. Cover review changes, selective staging, write descriptive commit messages with HEREDOC format, verify commit history. Use when save logical unit of work to version control, create commit with conventional message, amend most recent commit, review staged changes before commit.
- ▌ Deploy Searxng 6 · pjt222Deploy a self-hosted SearXNG meta search engine via Docker Compose. Covers settings.yml configuration, engine selection, result proxying, Nginx frontend, persistence, and updates. Use when setting up a private search engine without tracking, aggregating results from multiple providers, running a shared search instance for a team or organisation, or replacing reliance on a single search provider.
- ▌ File Trademark 6 · pjt222Trademark filing procedures covering EUIPO (EU), USPTO (US), and WIPO Madrid Protocol (international). Walks through pre-filing conflict checks, Nice classification, descriptiveness assessment, mark type decisions, filing basis strategy, office-specific e-filing procedures, Madrid Protocol extension, post- filing monitoring, and open-source trademark policy drafting. Use after running screen-trademark to confirm the mark is clear, when ready to secure trademark rights in one or more jurisdictions.
- ▌ Grade Tcg Card 6 · pjt222Grade a trading card using PSA, BGS, or CGC standards. Covers observation-first assessment (adapted from meditate's unbiased observation), centering measurement, surface analysis, edge and corner evaluation, and final grade assignment with confidence interval. Supports Pokemon, MTG, Flesh and Blood, and Kayou cards. Use when evaluating a card before professional grading submission, pre-screening a collection for high-grade candidates, settling condition disputes between buyers and sellers, or estimating the grade-dependent value spread for a card.
- ▌ Install Putior 6 · pjt222Install and configure the putior R package for workflow visualization. Covers CRAN and GitHub installation, optional dependencies (mcptools, ellmer, shiny, shinyAce, logger, plumber2), and verification of the complete annotation-to-diagram pipeline. Use when setting up putior for the first time, preparing a machine for workflow visualization tasks, when a downstream skill requires putior to be installed, or restoring an environment after an R version upgrade or renv wipe.
- ▌ Learn Guidance 6 · pjt222Guide a person through structured learning of a new topic, technology, or skill. AI acts as learning coach — assessing current knowledge, designing a learning path, walking through material, testing understanding, adapting difficulty, and planning review sessions for retention. Use when a person wants to learn a new technology and does not know where to start, when someone feels overwhelmed by documentation, when a person keeps forgetting material and needs spaced repetition, or when transitioning between domains and needing a gap analysis.
- ▌ Manage Backlog 6 · pjt222Create and maintain a product or project backlog with prioritized items, acceptance criteria, and estimates. Covers user story writing, MoSCoW prioritization, backlog grooming, item splitting, and status tracking. Use when starting a new project and converting scope into actionable items, during ongoing grooming before sprint planning, re-prioritizing after stakeholder feedback or scope changes, or splitting oversized items into implementable pieces.
- ▌ Qualify Vendor 6 · pjt222Qualify a vendor or supplier of GxP-relevant software or services. Covers vendor risk classification, assessment questionnaire design, desk and on-site audit approaches, quality agreement evaluation, SLA review, and ongoing monitoring cadence definition. Use when selecting a new vendor for a GxP-critical system, onboarding a cloud provider for regulated data, performing a periodic re-qualification, when a vendor audit finding requires re-assessment, or when EU Annex 11 or ICH Q10 requires supplier qualification.
- ▌ Remote Viewing 6 · pjt222AI intuitive exploration for approaching unknown codebases, problems, or systems without preconceptions. Adapts Coordinate Remote Viewing protocol to AI investigation: cooldown (clear assumptions), staged data gathering (raw signals → dimensional → analytical), AOL management (separate observations from premature labels), structured review. Use when investigating unfamiliar codebase with unknown architecture, debugging problem where premature hypotheses could mislead, exploring domain with limited context, or when previous attempts led astray by assumptions and "beginner's mind" would be more productive.
- ▌ Submit To Cran 6 · pjt222Complete procedure for submitting an R package to CRAN, including pre-submission checks (local, win-builder, R-hub), cran-comments.md preparation, URL and spell checking, and the submission itself. Covers first submissions and updates. Use when a package is ready for initial CRAN release, when submitting an updated version of an existing CRAN package, or when re-submitting after receiving CRAN reviewer feedback.
- ▌ Teach Guidance 6 · 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 6 · pjt222Test Shiny applications using shinytest2 for end-to-end browser tests and testServer() for unit-testing module server logic. Covers snapshot testing, CI integration, and mocking external services. Use when adding tests to an existing Shiny application, setting up a testing strategy for a new Shiny project, writing regression tests before refactoring Shiny code, or integrating Shiny app tests into CI/CD pipelines.
- ▌ Write Vignette 6 · pjt222Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, CRAN requirements for vignettes. Use when adding Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.
- ▌ Assess Ip Landscape 2 · pjt222Mapear el panorama de propiedad intelectual para un dominio tecnológico o área de producto. Cubre análisis de clústeres de patentes, identificación de espacios en blanco, evaluación del portafolio de PI de competidores, examen preliminar de libertad de operación, y recomendaciones estratégicas de posicionamiento de PI. Usar antes de iniciar I+D en una nueva área tecnológica, al evaluar la entrada al mercado contra incumbentes con portafolios de patentes fuertes, al preparar la debida diligencia de inversión, al informar una estrategia de solicitud de patentes, o al evaluar el riesgo de libertad de operación para un nuevo producto.
- ▌ Audit Icon Pipeline 2 · pjt222Detectar glyphs faltantes, iconos y variantes HD comparando registros contra archivos de mapeo de glyphs, directorios de iconos y manifiestos. Reporta brechas para habilidades, agentes y equipos en todas las paletas.
- ▌ Build Feature Store 2 · pjt222Build a feature store using Feast for centralized feature management, configure offline and online stores for batch and real-time serving, define feature views with transformations, and implement point-in-time correct joins for ML pipelines. Use when managing features for multiple ML models, ensuring training-serving consistency, serving low-latency features for real-time inference, reusing feature definitions across projects, or building a feature catalog for discovery and governance.
- ▌ Conduct Post Mortem 2 · pjt222Conduce un análisis post-mortem sin culpa después de un incidente. Construye la reconstrucción de la cronología, identifica los factores contribuyentes y genera mejoras accionables. Se centra en los problemas sistémicos en lugar de la culpa individual. Útil después de cualquier incidente de producción o degradación del servicio, tras un casi accidente, cuando se investigan problemas recurrentes, o para compartir aprendizajes sistémicos entre equipos.
- ▌ Create Pull Request 2 · pjt222Crear y gestionar pull requests usando GitHub CLI. Cubre la preparación de ramas, escritura de títulos y descripciones de PR, creación de PRs, manejo de retroalimentación de revisión y flujos de trabajo de merge y limpieza. Utilizar al proponer cambios desde una rama de funcionalidad o corrección para revisión, al fusionar trabajo completado en la rama principal, al solicitar revisión de código de colaboradores, o al documentar el propósito y alcance de un conjunto de cambios.
- ▌ Create R Dockerfile 2 · pjt222Create 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.
- ▌ Develop Hplc Method 2 · pjt222Desarrollar un método de cromatografía líquida de alta eficiencia (HPLC) para la separación y cuantificación de compuestos no volátiles en fase inversa, fase normal o intercambio iónico. Cubre la selección de columna, optimización de la fase móvil (gradiente vs. isocrático), control de pH, temperatura y detección UV/DAD/MS. Usar cuando se separen mezclas de compuestos no volátiles, polares o iónicos; cuando se desarrolle un método de control de calidad farmacéutico; cuando se optimice la selectividad de la separación ajustando las condiciones de la fase móvil; o cuando se transfieran métodos HPLC entre equipos.
- ▌ Label Training Data 2 · pjt222Set 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.
- ▌ Maintain Hand Tools 2 · pjt222Maintain the 8 essential garden hand tools through sharpening, handle care, rust prevention, and seasonal storage. Covers bypass secateurs, hori-hori, hand fork, trowel, pruning saw, sharpening stone, watering can, and soil rake. Use after each garden session for quick cleaning, monthly during the growing season for sharpening and oiling, at end of season for winter storage preparation, before spring for pre-season readiness checks, or whenever a tool feels dull, stiff, or shows rust.
- ▌ Manage Git Branches 2 · pjt222Crea, rastrea, cambia, sincroniza y limpia ramas de Git. Cubre convenciones de nombres, cambio seguro de ramas con stash, sincronización con el upstream y eliminación de ramas fusionadas. Úsalo al comenzar trabajo en una nueva funcionalidad o corrección de error, al cambiar entre tareas en distintas ramas, al mantener una rama de funcionalidad actualizada con main, o al limpiar ramas tras fusionar pull requests.
- ▌ Manage Token Budget 2 · pjt222Monitorea, limita y recupera de la acumulación de contexto en sistemas agénticos. Cubre el seguimiento de costos por ciclo, la auditoría de la ventana de contexto, los límites de presupuesto con políticas de aplicación, la poda de emergencia al acercarse a los límites y la integración de divulgación progresiva para minimizar el gasto de tokens en el enrutamiento. Usar al ejecutar bucles de agentes de larga duración (latidos, sondeo, flujos de trabajo autónomos), cuando las ventanas de contexto crecen de forma impredecible entre ciclos, cuando los costos de API superan las líneas de base esperadas, al diseñar nuevos flujos de trabajo agénticos que necesitan restricciones de costo desde el inicio, o cuando el análisis post-mortem revela un incidente de costo causado por la acumulación de contexto.
- ▌ Monitor Model Drift 2 · pjt222Implement 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.
- ▌ Ornament Style Mono 2 · pjt222Design 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.
- ▌ Pipeline Gpu Kernel 2 · pjt222Apply software pipelining (double-buffering) to a tiled GPU kernel to overlap global memory loads with Tensor Core computation. Covers prologue/loop/epilogue restructuring, LDG-register vs cp.async (LDGSTS) variant selection based on compute/load ratio, shared memory budget verification against architecture-specific occupancy cliffs, and SASS-level verification of load/compute overlap.
- ▌ Polish Claw Project 2 · pjt222Contribute to OpenClaw ecosystem projects (OpenClaw, NemoClaw, NanoClaw) through a structured 9-step workflow: target verification, codebase exploration, parallel audit, finding cross-reference, and pull request creation. Emphasizes false positive prevention and project convention adherence.
- ▌ Prepare Print Model 2 · pjt222Exportar 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.
- ▌ Review Pull Request 2 · pjt222Revisar una pull request de principio a fin usando GitHub CLI. Cubre el análisis del diff, la revisión del historial de commits, la verificación de comprobaciones CI/CD, la retroalimentación con niveles de gravedad (bloqueante/sugerencia/detalle/elogio) y el envío con gh pr review. Usar cuando se asigne una pull request para revisión, al realizar una autorrevisión antes de pedir la opinión de otros, al realizar una segunda revisión tras abordar la retroalimentación, o al auditar una PR fusionada para una evaluación de calidad posterior a la fusión.
- ▌ Review Skill Format 2 · pjt222Revisar un archivo SKILL.md para verificar su conformidad con el estándar agentskills.io. Comprueba los campos del frontmatter YAML, las secciones obligatorias, los límites de recuento de líneas, el formato de los pasos del procedimiento y la sincronización con el registro. Usar cuando una nueva habilidad necesite validación de formato antes de fusionarse, una habilidad existente haya sido modificada y requiera revalidación, al realizar una auditoría por lotes de todas las habilidades en un dominio, o al revisar la contribución de una habilidad de un colaborador en una pull request.
- ▌ Scaffold MCP Server 2 · pjt222Scaffold 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.
- ▌ Scaffold Nextjs App 2 · pjt222Crear una nueva aplicación Next.js con App Router, TypeScript y valores predeterminados modernos. Cubre la creación del proyecto, estructura de directorios, configuración de enrutamiento y configuración inicial. Úsalo al iniciar un nuevo proyecto de aplicación web, al crear un frontend basado en React con renderizado del lado del servidor, al construir una aplicación full-stack con rutas de API, o al configurar un proyecto web TypeScript desde cero.
- ▌ Setup Compose Stack 2 · pjt222Configure general-purpose Docker Compose stacks for common application patterns. Covers web app + database + cache + worker services, named volumes, networks, health checks, depends_on, environment management, and profiles. Use when running a web app with a database or cache, setting up a development environment with multiple services, orchestrating background workers alongside an API, or creating reproducible multi-service environments across teams.
- ▌ Setup Gxp R Project 2 · pjt222Configurar una estructura de proyecto R conforme a las regulaciones GxP (21 CFR Parte 11, EU Anexo 11). Cubre entornos validados, documentación de calificación, control de cambios y requisitos de registros electrónicos. Usar al iniciar un proyecto de análisis R en un entorno regulado (farma, biotecnología, dispositivos médicos), al configurar R para análisis de ensayos clínicos, al crear un entorno informático validado para envíos regulatorios, o al implementar los requisitos de 21 CFR Parte 11 o EU Anexo 11.
- ▌ Setup Uptime Checks 2 · pjt222Configure external uptime monitoring using Blackbox Exporter and Prometheus. Implement SSL certificate monitoring, HTTP endpoint health checks, and status pages for customer-facing visibility. Use when monitoring customer-facing endpoints such as APIs and websites, tracking SSL certificate expiration, validating service availability from multiple regions, creating public status pages, or meeting SLA requirements for uptime reporting.
- ▌ Verify Agent Output 2 · pjt222Valida 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.
- ▌ Write Continue Here 2 · pjt222Write a CONTINUE_HERE.md file capturing current session state so a fresh Claude Code session can pick up where this one left off. Covers assessing recent work, structuring the continuation file with objective, completed, in-progress, next-steps, and context sections, and verifying the file is actionable. Use when ending a session with unfinished work, handing off context between sessions, or preserving task state that git alone cannot capture.
- ▌ Assess Ip Landscape 3 · pjt222技術ドメインまたは製品分野の知的財産ランドスケープをマッピングする。特許クラスター 分析、ホワイトスペース特定、競合他社IPポートフォリオ評価、実施自由(FTO)予備 スクリーニング、戦略的IPポジショニング推奨をカバーする。新技術分野でR&D開始前、 強力な特許ポートフォリオを持つ既存企業に対して市場参入を評価する時、投資 デューデリジェンスの準備、特許出願戦略の策定、新製品のFTOリスク評価時に使用する。