pjt222
- 3.9k skills
- 0 followers
- 6 days ago last updated
- ▌ Build Custom MCP Server 5 · pjt222Build a custom MCP (Model Context Protocol) server that exposes domain-specific tools to AI assistants. Covers server implementation in Node.js or R, tool definitions, transport configuration, and testing with Claude Code. Use when you need to expose custom functionality beyond what mcptools provides, when building specialized domain-specific AI integrations, or when wrapping existing APIs or services as MCP tools.
- ▌ Circuit Breaker Pattern 5 · pjt222Implement circuit breaker logic for agentic tool calls — tracking tool health, transitioning between closed/open/half-open states, reducing task scope when tools fail, routing to alternatives via capability maps, and enforcing failure budgets to prevent error accumulation. Separates orchestration (deciding what to attempt) from execution (calling tools), following the expeditor pattern. Use when building agents that depend on multiple tools with varying reliability, designing fault-tolerant agentic workflows, recovering gracefully from tool outages mid-task, or hardening existing agents against cascading tool failures.
- ▌ Configure Reverse Proxy 5 · pjt222Configure reverse proxy patterns across multiple tools including Nginx, Traefik, and ShinyProxy. Covers WebSocket proxying, path-based and host-based routing, SSL termination, and Docker label auto-discovery. Use when routing multiple services behind a single entry point, proxying WebSocket connections (Shiny, Socket.IO), auto-discovering Docker services with Traefik labels, or adding SSL termination to services that don't handle TLS natively.
- ▌ Consult Natural History 5 · pjt222Reference Hildegard von Bingen's Physica natural history knowledge. Covers classification of plants, stones, animals, fish, birds, elements, and trees with their medicinal, symbolic, and practical properties. Enables cross- referencing between categories and application guidance. Use when exploring a specific plant, stone, or animal from Hildegard's perspective, researching medieval natural history and cosmology, cross-referencing properties across categories, or integrating Physica knowledge into health, spiritual, or creative practice.
- ▌ Containerize MCP Server 5 · pjt222Containerize an R-based MCP (Model Context Protocol) server using Docker. Covers mcptools integration, port exposure, stdio vs HTTP transport, and connecting Claude Code to the containerized server. Use when deploying an R MCP server without requiring a local R installation, creating a reproducible MCP server environment, running MCP servers alongside other containerized services, or distributing an MCP server to other developers.
- ▌ Deploy Ml Model Serving 5 · pjt222Deploy machine learning models to production serving infrastructure using MLflow, BentoML, or Seldon Core with REST/gRPC endpoints, implement autoscaling, monitoring, and A/B testing capabilities for high-performance model inference at scale. Use when deploying trained models for real-time inference, setting up REST or gRPC prediction APIs, implementing autoscaling for variable load, running A/B tests between model versions, or migrating from batch to real-time inference.
- ▌ Design On Call Rotation 5 · pjt222Design sustainable on-call rotations with balanced schedules, clear escalation policies, fatigue management, and handoff procedures. Minimize burnout while maintaining incident response coverage. Use when setting up on-call for the first time, scaling a team from 2-3 to 5+ engineers, addressing on-call burnout or alert fatigue, improving incident response times, or after a post-mortem identifies handoff issues.
- ▌ Design Training Program 5 · pjt222Design a GxP training programme covering training needs analysis by role, curriculum design (regulatory awareness, system-specific, data integrity), competency assessment criteria, training record retention, and retraining triggers for SOP revisions and incidents. Use when a new validated system requires user training before go-live, an audit finding cites inadequate training, organisational changes introduce new roles, a periodic programme review is due, or inspection preparation requires demonstrating training adequacy.
- ▌ Fit Hidden Markov Model 5 · pjt222Fit hidden Markov models using the Baum-Welch (EM) algorithm with model selection, Viterbi decoding for state sequences, and forward-backward probabilities. Use when observations are generated by unobservable latent states, you need to segment a time series into latent regimes (market regimes, speech phonemes, biological sequences), compute sequence probabilities, decode the most likely hidden state path, or compare models with different numbers of hidden states.
- ▌ Formulate Herbal Remedy 5 · pjt222Prepare herbal remedies from Hildegard von Bingen's Physica. Covers plant identification, preparation methods (tinctures, poultices, infusions, decoctions), dosage guidance, contraindications, and safety review based on 12th-century medieval pharmacopeia. Use when needing an herbal remedy for a specific ailment using Hildegardian pharmacopeia, seeking guidance on preparation methods and dosage, researching medieval herbal medicine, or integrating Hildegard's plant wisdom into holistic health practice.
- ▌ Install Almanac Content 5 · pjt222Install skills, agents, and teams from agent-almanac into any supported agentic framework using the CLI. Covers framework detection, content search, installation with dependency resolution, health auditing, and manifest-based syncing. Use when setting up a new project with agentic capabilities, installing specific skills or entire domains, targeting multiple frameworks simultaneously, or maintaining a declarative manifest of installed content.
- ▌ Interpret Mass Spectrum 5 · pjt222Systematically interpret mass spectra to determine molecular formula, identify fragmentation pathways, and propose molecular structures. Covers ionization method assessment, molecular ion identification, isotope pattern analysis, common fragmentation losses, and purity evaluation.
- ▌ Observe Insect Behavior 5 · pjt222Conduct structured insect behavior observations using sampling protocols, ethogram categories, event recording, interaction logging, environmental context, and summary analysis. Covers focal animal sampling, scan sampling, all-occurrences sampling, and instantaneous sampling methods. Defines a standard insect ethogram with locomotion, feeding, grooming, mating, defense, communication, and rest categories. Includes timestamped event recording, intraspecific and interspecific interaction logging, environmental covariate documentation, and time budget analysis. Use when studying insect behavior for ecological research, documenting behavioral repertoires for a species, observing pollinator activity or predator-prey dynamics, or supporting conservation assessments with behavioral data.
- ▌ Orchestrate Ml Pipeline 5 · pjt222Orchestrate end-to-end machine learning pipelines using Prefect or Airflow with DAG construction, task dependencies, retry logic, scheduling, monitoring, and integration with MLflow, DVC, and feature stores for production ML workflows. Use when automating multi-step ML workflows from data ingestion to deployment, scheduling periodic model retraining, coordinating distributed training tasks, or managing retry logic and failure recovery across pipeline stages.
- ▌ Prove Geometric Theorem 5 · pjt222以歐幾里得公理法、坐標幾何、或向量法以嚴謹逐步之邏輯結構證幾何定理。 含直證、反證、坐標證、向量證、特殊情與退化構之處。 得幾何聲欲證、驗猜想、立引理、化幾何直覺為嚴證、 或比異證法之效時用之。
- ▌ Release Package Version 5 · pjt222Release a new version of an R package including version bumping, NEWS.md updates, git tagging, GitHub release creation, and post-release development version setup. Use when a package is ready for a new patch, minor, or major release, after CRAN acceptance to create the corresponding GitHub release, or when setting up the development version bump immediately after a release.
- ▌ Remote Viewing Guidance 5 · pjt222Guide a person through a Coordinate Remote Viewing (CRV) session following the Stargate/SRI protocol. AI acts as the monitor/tasker role, managing protocol progression, catching Analytical Overlay (AOL), and redirecting the viewer through stages I-VI. Use when a person wants to practice CRV and needs a monitor to manage the session protocol, when training a viewer through the staged CRV process, facilitating a structured intuitive perception exercise, or developing non-local awareness skills that complement healing work.
- ▌ Research Word Etymology 5 · pjt222Research the etymology of a word by tracing proto-language roots, identifying cognates across language families, documenting semantic drift with dated attestations, and flagging folk etymologies. Use when investigating word origins, comparing cognate sets across related languages, charting historical meaning changes, or debunking popular but unsupported origin stories.
- ▌ Rotate Scraping Proxies 5 · pjt222Escalate blocked scraping campaigns with provider-neutral proxy rotation — decide between datacenter, residential, and mobile pools, integrate rotation with scrapling, configure session stickiness for stateful flows, monitor cost and health, and stay inside legal and ethical boundaries. Use as the next step after `headless-web-scraping` client-side stealth (StealthyFetcher, rate limiting, robots.txt) is insufficient and traffic is legitimate.
- ▌ Security Audit Codebase 5 · pjt222Perform a security audit of a codebase checking for exposed secrets, vulnerable dependencies, injection vulnerabilities, insecure configurations, and OWASP Top 10 issues. Use before publishing or deploying a project, for periodic security reviews, after adding authentication or API integration, before open-sourcing a private repository, or when preparing for a security compliance audit.
- ▌ Setup Github Actions CI 5 · pjt222Configure GitHub Actions CI/CD for R packages including R CMD check on multiple platforms, test coverage reporting, and pkgdown site deployment. Uses r-lib/actions for standard workflows. Use when setting up CI/CD for a new R package, adding multi-platform testing to an existing package, configuring automated pkgdown site deployment, or adding code coverage reporting to a repository.
- ▌ Troubleshoot Separation 5 · pjt222Systematically diagnose and resolve chromatographic separation problems: document symptoms, identify root causes for peak shape and retention anomalies, evaluate matrix effects, and implement targeted fixes using a one-variable-at-a-time approach for GC and HPLC systems.
- ▌ Validate Piles Notation 5 · pjt222Parse and validate PILES (Puzzle Input Line Entry System) notation for specifying piece fusion groups in jigsawR. Covers syntax validation, parsing into group lists, plain-language explanation, adjacency verification against puzzle results, and round-trip serialization. Use when validating user-supplied PILES strings before passing to generate_puzzle(), debugging fusion group issues, explaining the notation to users, or testing round-trip parse/serialize fidelity.
- ▌ Analyze Codebase For MCP 4 · pjt222分析任意代码库以识别适合作为 MCP 工具暴露的函数、API 和数据源,生成工具规格文档。 适用于为现有项目规划 MCP 服务器、在将代码库包装为 AI 可访问工具界面前进行审计、 比较代码库的功能与已通过 MCP 暴露的内容,或生成工具规格以交接给 scaffold-mcp-server。
- ▌ Audit Discovery Symlinks 4 · pjt222审计并修复用于技能、代理和团队的 Claude Code 发现符号链接。在项目和全局 层面将注册表与 .claude/ 目录进行比较,检测缺失、损坏和多余的符号链接, 区分 almanac 内容与外部项目,可选地修复缺口。在添加新技能或代理之后、 仓库重命名或移动之后、斜杠命令停止工作时,或作为定期健康检查时使用。
- ▌ Bootstrap Agent Identity 4 · pjt222重启后一致的代理行为——渐进式身份加载、从持久化制品重建工作上下文、新启动与继续 检测、通过居中和调谐进行校准,以及身份连贯性验证。解决代理必须从证据而非记忆 重建自身身份和工作内容的冷启动问题。适用于每次新会话开始时、会话中断或崩溃后、 代理行为与先前会话不一致时,或持久化记忆与当前上下文出现矛盾时。
- ▌ Build Grafana Dashboards 4 · pjt222创建生产级 Grafana 仪表板,包含可复用面板、模板变量、注解及版本控制部署的预置配置。 适用于为 Prometheus、Loki 等数据源创建可视化图表、为 SRE 团队构建运营仪表板、 从手动创建仪表板迁移到版本控制预置配置,或建立高管级别的 SLO 合规报告。
- ▌ Build Sequential Circuit 4 · pjt222Build sequential (stateful) logic circuits including latches, flip-flops, registers, counters, and finite state machines. Covers SR latch, D and JK flip-flops, binary/BCD/ring counters, and Mealy/Moore FSM design with clock signal and timing analysis. Use when a circuit must remember past inputs, count events, or implement a state-dependent control sequence.
- ▌ Configure Alerting Rules 4 · pjt222配置 Prometheus Alertmanager,包括路由树、接收器(Slack、PagerDuty、邮件)、 抑制规则、静默及通知模板,用于可操作的事故告警。适用于通过自动事故检测实施主动监控、 按严重程度将告警路由到适当团队、通过分组和去重减少告警疲劳、 与 PagerDuty 等值班系统集成,或将遗留告警迁移到基于 Prometheus 的告警系统。
- ▌ Configure Git Repository 4 · pjt222为 Git 仓库配置适当的 .gitignore、分支策略、提交规范、钩子及远程仓库设置。 涵盖初始化配置以及 R、Node.js 和 Python 项目的常见模式。适用于为新项目 初始化版本控制、为特定语言或框架添加 .gitignore、设置分支保护与规范, 或配置提交钩子。
- ▌ Decode Minified JS Gates 4 · pjt222Classify gate call variants in a minified JavaScript bundle. Covers context-window extraction around a flag occurrence, identification of 4–6 reader variants (sync boolean, sync config-object, bootstrap-aware TTL, truthy-only, async bootstrap, async bridge), default-value extraction (boolean / null / numeric / config-object literal), conjunction detection across `&&` predicates, kill-switch inversion detection, and production of a gate-mechanics record that feeds probe- feature-flag-state. Use when a flag's behavior cannot be inferred from its name alone, when the binary uses multiple reader libraries, or when config-object gates carry structured schemas distinct from boolean gates.
- ▌ Document Insect Sighting 4 · pjt222Record insect sightings with location, date, habitat, photography, behavior notes, preliminary identification, and citizen science submission. Covers GPS coordinates, weather conditions, microhabitat description, macro photography techniques, behavioral observations, preliminary identification to order using body plan, and submission to citizen science platforms such as iNaturalist. Use when encountering an insect you want to document, contributing to citizen science biodiversity databases, building a personal observation journal, or supporting ecological surveys with georeferenced photographic records.
- ▌ Evaluate Agent Framework 4 · pjt222通过评估社区健康、被取代风险、架构对齐和治理可持续性,评估开源代理框架 的投资就绪度。产出四档分类(INVEST / EVALUATE-FURTHER / CONTRIBUTE-CAUTIOUSLY / AVOID),在投入工程精力前指导资源分配决策。
- ▌ Evolve Skill From Traces 4 · pjt222使用三阶段流水线从代理执行轨迹演化 SKILL.md 文件:从观察到的运行收集 轨迹、并行多代理补丁提议(用于错误和成功分析),以及通过流行度加权对 重叠编辑进行无冲突合并。基于 Trace2Skill 方法论。
- ▌ Interpret Raman Spectrum 4 · pjt222解读拉曼光谱,包括拉曼选择规则、互斥原理、退偏振比测量,以及 晶态和无定形材料的特征峰归因。用于区分对称和非对称振动、分析 聚合物结晶度,或对 IR 透明材料进行无损表征。
- ▌ Manage Engagement Buffer 4 · pjt222管理跨平台摄取、优先级排序、速率限制、去重并跟踪传入参与项状态的 engagement buffer。生成定期摘要并强制执行冷却期。与 du-dum 组合: du-dum 设置观察/行动节奏,本技能管理节拍间的队列。
- ▌ Manage Renv Dependencies 4 · pjt222使用 renv 管理 R 包依赖以实现可重现的环境。涵盖初始化、 快照/恢复工作流、常见问题排查及 CI/CD 集成。适用于为新 R 项目初始化依赖管理、添加或更新包、在新机器上恢复环境、 排查恢复失败问题,或将 renv 与 CI/CD 流水线集成。
- ▌ Probe Feature Flag State 4 · pjt222Probe the runtime state of a named feature flag in a CLI binary. Covers the four-pronged evidence protocol (binary strings, live invocation, on-disk state, platform cache), the four-state classification (LIVE / DARK / INDETERMINATE / UNKNOWN), gate-vs-event disambiguation, conjunction-gate handling, and skill-substitution scenarios where a flag appears DARK but the capability is delivered by other means. Use when verifying whether a documented or inferred capability has rolled out, when auditing dark-launched features, or when a prior probe's conclusions need refreshing against a new binary version.
- ▌ Refactor Skill Structure 4 · pjt222通过将示例提取到 references/EXAMPLES.md、拆分复合步骤,并重组章节以实现 渐进式披露,对过长或结构不良的 SKILL.md 进行重构。适用于技能超过 500 行的 CI 限制、代码块主导技能正文、步骤包含多个不相关操作,或内容更新将技能推过 行数限制后。
- ▌ Repair Broken References 4 · pjt222Find and fix broken internal links, dead external URLs, stale imports, missing cross-references, and orphaned files. Ensures all project references remain valid and up-to-date. Use when documentation contains broken internal links, external URLs return 404 errors, import statements reference moved or deleted modules, cross-references between files are out of sync, or files exist but are never referenced anywhere in the project.
- ▌ Setup Container Registry 4 · pjt222配置容器镜像仓库,包括 GitHub Container Registry(ghcr.io)、Docker Hub 和 Harbor,支持自动化镜像扫描、标签策略、保留策略以及 CI/CD 集成, 实现安全的镜像分发。适用于设置私有容器仓库、从 Docker Hub 迁移至 自托管仓库、在 CI/CD 流水线中实现漏洞扫描、管理多架构镜像、 强制执行镜像签名,或配置自动清理和保留策略。
- ▌ Solve Modular Arithmetic 4 · pjt222求解模运算问题:同余方程、中国剩余定理、Euler 定理和 模幂运算。涵盖基本模运算、线性同余方程组和密码学中的 RSA 算法应用。
- ▌ Survey Insect Population 4 · pjt222Design and execute insect population surveys covering survey design, sampling methods, field execution, specimen identification, diversity index calculation including Shannon-Wiener and Simpson indices, statistical analysis, and reporting. Covers defining survey objectives, selecting study sites, determining sampling intensity and replication, choosing sampling methods appropriate to target taxa, standardizing collection effort, recording environmental covariates, identifying specimens to the lowest practical taxonomic level, calculating species richness, Shannon-Wiener diversity (H'), Simpson diversity (1-D), evenness, rarefaction curves, multivariate ordination, and producing survey reports with species lists and conservation implications. Use when conducting baseline biodiversity assessments, monitoring insect populations over time, comparing insect communities across habitats or treatments, assessing environmental impact, or supporting conservation planning with quantitative ecological data.
- ▌ Adapt Architecture 8 · pjt222Execute structural metamorphosis using strangler fig migration, chrysalis phases, and interface preservation. Covers transformation planning, parallel running, progressive cutover, rollback design, and post-metamorphosis stabilization for system architecture evolution. Use when assess-form has classified the system as READY for transformation, when migrating from monolith to microservices, when replacing a core subsystem while dependents continue operating, or when any architectural change must be gradual rather than big-bang.
- ▌ Build Pkgdown Site 8 · pjt222Build and deploy a pkgdown documentation site for an R package to GitHub Pages. Covers _pkgdown.yml configuration, theming, article organization, reference index customization, and deployment methods. Use when creating a documentation site for a new or existing package, customizing layout or navigation, fixing 404 errors on a deployed site, or migrating between branch-based and GitHub Actions deployment methods.
- ▌ Build Shiny Module 8 · pjt222Build reusable Shiny modules with proper namespace isolation using NS(). Covers module UI/server pairs, reactive return values, inter-module communication, and nested module composition. Use when extracting a reusable component from a growing Shiny app, building a UI widget used in multiple places, encapsulating complex reactive logic behind a clean interface, or composing larger applications from smaller, testable units.
- ▌ Catalog Collection 8 · pjt222Catalog and classify materials using standard library systems. Covers descriptive cataloging, subject headings, call number assignment using Dewey Decimal and Library of Congress Classification, MARC record basics, shelf organization, and authority control for consistent access points. Use when organizing a personal, institutional, or community library from scratch, assigning call numbers and subject headings to new acquisitions, reclassifying a collection that has outgrown its original system, or establishing authority control for authors, series, or subjects.
- ▌ Define Slo Sli Sla 8 · pjt222Establish Service Level Objectives (SLO), Service Level Indicators (SLI), and Service Level Agreements (SLA) with error budget tracking, burn rate alerts, and automated reporting using Prometheus and tools like Sloth or Pyrra. Use when defining reliability targets for customer-facing services, balancing feature velocity against system reliability through error budgets, migrating from arbitrary uptime goals to data-driven metrics, or implementing Site Reliability Engineering practices.
- ▌ Fail Early Pattern 8 · pjt222Apply the fail-early (fail-fast) pattern to detect and report errors at the earliest possible point. Covers input validation with guard clauses, meaningful error messages, assertion functions, and anti-patterns that silently swallow failures. Primary examples in R with general/polyglot guidance. Use when writing functions that accept external input, adding input validation before CRAN submission, refactoring code that silently produces wrong results, reviewing PRs for error-handling quality, or hardening internal APIs against invalid arguments.
- ▌ Design A2a Agent Card 4 · pjt222Design an A2A Agent Card (.well-known/agent.json) manifest describing agent capabilities, skills, authentication requirements, and supported content types. Use when building an agent that must be discoverable by other A2A-compliant agents, exposing capabilities for multi-agent orchestration, migrating an existing agent to the A2A protocol, defining the public contract for an agent before implementation, or integrating with agent registries that consume Agent Cards.
- ▌ Draft Project Charter 4 · pjt222起草项目章程,定义范围、干系人、成功标准和初始风险登记册。 涵盖问题陈述、RACI 矩阵、里程碑规划和范围边界, 适用于敏捷与传统项目管理方法。适合在启动新项目或计划时使用, 在详细规划开始前正式确定范围或对齐干系人, 或在从探索阶段过渡到主动项目工作时使用。
- ▌ Headless Web Scraping 4 · pjt222使用 scrapling Python 库从网页提取数据 —— 根据目标网站防御选择适当的 fetcher 层(HTTP、stealth Chromium 或完整浏览器自动化)、配置无头浏览, 并使用 CSS 选择器提取结构化数据。当 WebFetch 不足以应对 JS 渲染页面、 反机器人保护的站点,或需要 DOM 遍历的结构化多元素提取时使用。
- ▌ Implement Audit Trail 4 · pjt222为受监管环境中的 R 项目实施审计追踪功能。涵盖日志记录、来源追踪、 电子签名、数据完整性检查和 21 CFR Part 11 合规性。适用于 R 分析 需要电子记录合规(21 CFR Part 11)、需要追踪分析中的操作人员和时间、 实施数据来源追踪,或为法规申报创建防篡改分析日志时使用。
- ▌ Interpret Ir Spectrum 4 · pjt222解读红外吸收光谱,通过识别诊断区(4000–1500 cm-1)的官能团特征峰和 指纹区(1500–400 cm-1)的吸收模式,确定化合物的官能团组成。用于 鉴定未知化合物、验证合成产物或检测杂质。
- ▌ Manage Change Control 4 · pjt222管理已验证计算机化系统的变更控制。涵盖变更申请分类(紧急、标准、 轻微)、对已验证状态的影响评估、重新验证范围确定、审批工作流程、 实施追踪和变更后验证。适用于已验证系统需要软件升级、补丁或配置 变更、基础设施变更影响已验证系统、CAPA 要求系统修改,或紧急变更 需要快速审批和事后记录时使用。
- ▌ Manage Tcg Collection 4 · pjt222组织、追踪和估值集换式卡牌游戏收藏。涵盖库存方法、存储最佳实践、基于评级的 估值、想要列表管理和收藏分析。支持宝可梦、万智牌、血与肉和 Kayou 卡牌。适用于 建立新收藏并设置库存追踪、编目已超出随意管理的现有收藏、为保险或出售估值收藏, 以及决定哪些卡牌值得提交专业评级。
- ▌ Ornament Style Modern 4 · pjt222Design ornamental patterns using modern and speculative aesthetics with colorblind-accessible color scales. Breaks free from historical period constraints to explore cyberpunk, solarpunk, biopunk, brutalist, vaporwave, and other contemporary genres. Includes CVD (Color Vision Deficiency) awareness and perceptually uniform scales (viridis, cividis, inferno). Use when creating ornamental designs in modern or genre-specific aesthetics, designing patterns that must be colorblind-accessible, or exploring hybrid motifs combining historical ornament with contemporary visual language.
- ▌ Render Blender Output 4 · pjt222Configure render settings, compositing nodes, output formats, and execute renders via Cycles or EEVEE engines using Python API or command-line interface. Use when automating render execution for batch processing, configuring quality and performance trade-offs, setting up compositing pipelines for post-processing, generating multiple output formats from a single render, or producing final output for publication or presentation.
- ▌ Resolve Git Conflicts 4 · pjt222使用安全的恢复策略解决合并和变基冲突。涵盖识别冲突来源、读取冲突标记、 选择解决策略,以及安全地继续或中止操作。适用于 git merge、rebase、 cherry-pick 或 stash pop 报告冲突、git pull 导致更改冲突,或需要安全 中止并重新开始失败的合并或变基操作。
- ▌ Select Print Material 4 · pjt222Choose 3D printing materials based on mechanical, thermal, and chemical requirements. Covers PLA, PETG, ABS, ASA, TPU, Nylon, and resin variants with property comparisons. Use when selecting material for parts with specific mechanical or thermal requirements, choosing for outdoor or chemical exposure, evaluating food-safe or biocompatible applications, balancing printability vs. performance, or troubleshooting material-related print failures.
- ▌ Setup Automl Pipeline 4 · pjt222Configure automated machine learning pipelines using Optuna or Ray Tune for hyperparameter optimization. Implement efficient search strategies (Hyperband, ASHA), define search spaces, and set up early stopping to find optimal model configurations with minimal manual tuning. Use when starting a new ML project and needing to quickly find good configurations, retraining with new data and re-optimizing hyperparameters, comparing multiple algorithms, or when the team lacks deep expertise in specific algorithm hyperparameters.
- ▌ Add Puzzle Type 8 · pjt222Scaffold a new puzzle type across all 10+ pipeline integration points in jigsawR. Creates the core puzzle module, wires it into the unified pipeline (generation, positioning, rendering, adjacency), adds ggpuzzle geom/stat layers, updates DESCRIPTION and config.yml, extends the Shiny app, and creates a comprehensive test suite. Use when adding a completely new puzzle type to the package or following the 10-point integration checklist to ensure nothing is missed end-to-end.
- ▌ Basic Obedience 8 · 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 8 · pjt222AI multi-path reasoning coherence using bee democracy — independent evaluation of competing approaches, waggle dance as reasoning-out-loud, quorum sensing for confidence thresholds, and deadlock resolution. Use when forage-solutions has identified multiple valid approaches and a selection must be made, when oscillating between options without committing, when justifying an architecture or tool choice with structured reasoning, or before an irreversible action where the cost of the wrong choice is high.
- ▌ Build Consensus 8 · 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 8 · 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 8 · 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 8 · pjt222Design Shiny application UIs using bslib for theming, layout_columns for responsive grids, value boxes, cards, and custom CSS/SCSS. Covers page layouts, accessibility, and brand consistency. Use when building a new Shiny app UI from scratch, modernizing an existing app from fluidPage to bslib, applying brand theming, making a Shiny app responsive across screen sizes, or improving accessibility of a Shiny application.
- ▌ Escalate Issues 8 · 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 8 · 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 8 · pjt222Generate jigsaw puzzles via generate_puzzle() or geom_puzzle_*() with parameter validation against inst/config.yml. Supports rectangular, hexagonal, concentric, voronoi, and snic puzzle types with configurable grid, size, seed, offset, and layout parameters. Use when creating puzzle SVG files for a specific type and configuration, testing generation with different parameters, generating sample output for documentation or demos, or creating ggplot2 puzzle visualizations.
- ▌ Identify Insect 8 · 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 8 · 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 8 · 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 8 · 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 8 · pjt222Multi-phase deep codebase review with severity ratings and structured output. Covers architecture, security, code quality, and UX/accessibility in a single coordinated pass. Produces a prioritized findings table suitable for direct conversion to GitHub issues via the create-github-issues skill.
- ▌ Review Research 8 · pjt222Conduct a peer review of research methodology, experimental design, and manuscript quality. Covers methodology evaluation, statistical appropriateness, reproducibility assessment, bias identification, and constructive feedback. Use when reviewing a manuscript, preprint, or internal research report, evaluating a research proposal or study protocol, assessing evidence quality behind a claim, or reviewing a thesis chapter or dissertation section.
- ▌ Setup Putior CI 8 · 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 8 · pjt222Interact with GraphQL APIs from the command line — discover schemas via introspection, construct queries and mutations, execute them with gh api graphql or curl, parse responses with jq, and chain operations by piping IDs between calls. Use when automating GitHub Discussions, Issues, or Projects via GraphQL, integrating with any GraphQL endpoint from scripts, or building CLI workflows that need structured API data.
- ▌ Write Claude Md 8 · pjt222Create an effective CLAUDE.md file that provides project-specific instructions to AI coding assistants. Covers structure, common sections, do/don't patterns, and integration with MCP servers and agent definitions. Use when starting a new project where AI assistants will be used, improving AI behavior on an existing project, documenting project conventions and constraints, or integrating MCP servers or agent definitions into a project workflow.
- ▌ Apply Gematria 10 · 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 10 · 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 10 · 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 10 · 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 10 · pjt222Stage, commit, amend w/ conventional msgs. Covers review, selective staging, HEREDOC msgs, history verify. Use → save logical unit, conventional commit, amend last, or review staged before commit.
- ▌ Deploy Searxng 10 · 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 10 · 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 10 · 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 10 · 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 10 · pjt222Guide person thru structured learning of new topic / tech / skill. AI as coach — assess knowledge, design path, walk material, test understanding, adapt difficulty, plan review for retention. Use when person wants to learn new tech + doesn't know where to start, overwhelmed by docs, keeps forgetting + needs spaced repetition, or transitioning domains + needs gap analysis.
- ▌ Manage Backlog 10 · pjt222Create + maintain product/project backlog w/ prioritized items, acceptance criteria, estimates. User story writing, MoSCoW prioritization, grooming, item splitting, status tracking. Use starting new project + converting scope → actionable items, ongoing grooming before sprint planning, re-prioritizing after stakeholder feedback / scope changes, splitting oversized items.
- ▌ Qualify Vendor 10 · pjt222Qualify vendor/supplier of GxP-relevant software or services. Vendor risk classification, assessment questionnaire design, desk + on-site audit approaches, quality agreement eval, SLA review, ongoing monitoring cadence. Use → new vendor for GxP-critical system, onboard cloud provider for regulated data, periodic re-qualification, audit finding requires re-assess, EU Annex 11 or ICH Q10 supplier qualification.
- ▌ Remote Viewing 10 · pjt222AI intuitive exploration → unknown codebases, problems, systems w/o preconceptions. Adapts CRV protocol → AI investigation: cooldown (clear assumptions), staged data gathering (raw → dimensional → analytical), AOL mgmt (separate obs from premature labels), structured review. Use → unfamiliar codebase, debug w/ premature hypotheses risk, limited ctx domain, prev attempts led astray by assumptions, "beginner's mind".
- ▌ Submit To Cran 10 · pjt222Complete proc → submit R pkg to CRAN. Pre-sub checks (local, win-builder, R-hub), cran-comments.md prep, URL + spell checks, sub itself. Covers first sub + updates. Use → pkg ready for initial CRAN release, sub updated ver of existing CRAN pkg, re-sub after CRAN reviewer feedback.
- ▌ Teach Guidance 10 · pjt222Guide person to be better teacher + explainer. AI coaches content structuring, audience calibration, explanation clarity, Socratic Q tech, feedback interpretation, reflective practice for tech presentations, docs, mentoring. Use → person needs prep coaching for tech presentation, wants better docs/tutorials, struggles to explain across expertise levels, mentoring colleague, prepping for talk.
- ▌ Test Shiny App 10 · pjt222Test Shiny apps via shinytest2 for e2e browser tests + testServer() for unit-testing module server logic. Snapshot testing, CI integration, mock external services. Use → add tests to existing Shiny app, set up testing strategy for new project, regression tests before refactor, integrate into CI/CD.
- ▌ Write Vignette 10 · 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 Rcpp Integration 6 · pjt222Add Rcpp or RcppArmadillo integration to an R package for high-performance C++ code. Covers setup, writing C++ functions, RcppExports generation, testing compiled code, and debugging. Use when an R function is too slow and profiling confirms a bottleneck, when you need to interface with existing C/C++ libraries, or when implementing algorithms (loops, recursion, linear algebra) that benefit from compiled code.
- ▌ Build CI CD Pipeline 6 · pjt222Design and implement multi-stage CI/CD pipelines using GitHub Actions with matrix builds, dependency caching, artifact management, and secret handling. Create workflows that span linting, testing, building, and deployment stages with parallel execution and conditional logic. Use when setting up automated testing and deployment for a new project, migrating from Jenkins or CircleCI to GitHub Actions, implementing matrix builds across platforms, adding build caching, or creating multi-stage pipelines with security scanning and quality gates.
- ▌ Compose Sacred Music 6 · pjt222Compose or analyze sacred music in Hildegard von Bingen's distinctive modal style. Covers modal selection, melodic contour (wide-range melodies), text-setting (syllabic and melismatic), neumatic notation, and liturgical context for antiphons, sequences, and responsories. Use when composing a new piece in Hildegardian style, analyzing an existing chant for structure and mode, researching medieval modal music, preparing to perform or teach Hildegard's music, or setting Latin sacred texts.