DevOps & Infra

pjt222 Skill

Containerisiere einen R-basierten MCP-Server (Model Context Protocol) mit Docker. Umfasst mcptools-Integration, Port-Freigabe, stdio- vs. HTTP-Transport und die Verbindung von Claude Code mit dem containerisierten Server. Verwende diesen Skill beim Deployen eines R-MCP-Servers ohne lokale R-Installation, beim Erstellen einer reproduzierbaren MCP-Server-Umgebung, beim Betrieb von MCP-Servern neben anderen containerisierten Diensten oder beim Verteilen eines MCP-Servers an andere Entwickler.

pjt222 Skill

Machine-Learning-Modelle auf Produktions-Serving-Infrastruktur mit MLflow, BentoML oder Seldon Core mit REST/gRPC-Endpunkten bereitstellen, Autoscaling, Monitoring und A/B-Test-Faehigkeiten fuer leistungsstarke Modellinferenz im grossen Massstab implementieren. Verwenden beim Bereitstellen trainierter Modelle fuer Echtzeit-Inferenz, beim Einrichten von REST- oder gRPC- Vorhersage-APIs, beim Implementieren von Autoscaling fuer variable Last, beim Durchfuehren von A/B-Tests zwischen Modellversionen oder beim Migrieren von Batch- zu Echtzeit-Inferenz.

pjt222 Skill

Orchestrate end-to-end maschinelles Lernen pipelines using Prefect or Airflow with DAG construction, task Abhaengigkeiten, 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.

pjt222 Skill

Optimiere Docker-Buildzeiten durch Layer-Caching, Multi-Stage-Builds, BuildKit-Funktionen und Abhaengigkeiten-zuerst-Kopiermuster. Anwendbar auf R-, Node.js- und Python-Projekte. Verwende diesen Skill, wenn Docker-Builds durch wiederholte Paketinstallationen langsam sind, wenn Rebuilds bei jeder Code-Aenderung alle Abhaengigkeiten neu installieren, wenn Image-Groessen unnoetig gross sind oder wenn CI/CD-Pipeline-Builds einen Engpass darstellen.

pjt222 Skill

Configure 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.

pjt222 Skill

Kubernetes-Ingress-Networking mit NGINX-Ingress-Controller, cert-manager fuer automatisiertes TLS-Zertifikat-Management, pfadbasiertes Routing, Rate-Limiting und Multi-Domain-Hosting mit SSL-Terminierung und Load-Balancing konfigurieren. Einsatz beim Exponieren mehrerer Kubernetes-Services ueber einen einzelnen Load-Balancer, beim Implementieren von pfad- oder hostbasiertem Routing, beim Automatisieren der TLS- Zertifikatausstellung mit Let's Encrypt oder beim Einrichten von Blue-Green- und Canary-Deployments mit Traffic-Splitting.

pjt222 Skill

Erstelle Multi-Stage-Dockerfiles, die Build- und Laufzeitumgebungen fuer minimale Produktions-Images trennen. Umfasst Builder/Runtime-Stage-Trennung, Artefakt-Kopieren, scratch/distroless/alpine-Ziele und Groessenvergleich. Verwende diesen Skill, wenn Produktions-Images zu gross sind, wenn Build-Tools im finalen Image enthalten sind, wenn separate Entwicklungs- und Produktions-Images aus einem Dockerfile benoetigt werden oder beim Deployen in eingeschraenkten Umgebungen wie Edge oder Serverless.

pjt222 Skill

GitHub Actions CI/CD fuer R-Pakete konfigurieren einschliesslich R CMD check auf mehreren Plattformen, Testabdeckungsberichten und pkgdown-Site- Bereitstellung. Verwendet r-lib/actions fuer Standardworkflows. Anwenden beim Einrichten von CI/CD fuer ein neues R-Paket, beim Hinzufuegen von Multiplattform-Tests zu einem bestehenden Paket, beim Konfigurieren der automatisierten pkgdown-Site-Bereitstellung oder beim Hinzufuegen von Codeabdeckungsberichten zu einem Repository.

pjt222 Skill

Infrastruktur- und Anwendungsmetriken mit Prophet oder statsmodels fuer Kapazitaetsplanung, Kostenoptimierung und proaktive Skalierung prognostizieren. Vorhersagen in Grafana visualisieren und Alarme fuer prognostizierte Ressourcenerschoepfung einrichten. Verwenden beim Prognostizieren von Infrastruktur-Kapazitaetsbedarf fuer CPU, Speicher oder Festplatte, beim Planen von Hardware-Beschaffung fuer das naechste Quartal, beim Vorhersagen von Kostentrends zur Optimierung von Cloud-Ausgaben oder beim Einrichten proaktiver Skalierungsrichtlinien basierend auf vorhergesagter Last.

pjt222 Skill

Configure container image registries including GitHub Container Registry (ghcr.io), Docker Hub, and Harbor with automated image scanning, tagging strategies, retention policies, and CI/CD integration for secure image distribution. Use when setting up a private container registry, migrating from Docker Hub to self-hosted registries, implementing vulnerability scanning in CI/CD pipelines, managing multi-architecture images, enforcing image signing, or configuring automatic cleanup and retention policies.

pjt222 Skill

Evolve SKILL.md files from agent execution traces using a three-stage pipeline: trajectory collection from observed runs, parallel multi-agent patch proposal for error and success analysis, and conflict-free consolidation of overlapping edits via prevalence-weighting. Based on the Trace2Skill methodology.

rudironsoni Bundle

Configures artifacts output layout. UseArtifactsOutput, ArtifactsPath, impact on CI and Docker.

pjt222 Skill

Cloud-Infrastruktur mit Terraform bereitstellen und verwalten — mit HCL-Modulen, Remote-State-Backends, Workspaces und Plan/Apply-Workflow. Infrastructure-as-Code-Muster mit Variablenverwaltung, Ausgabewerten und State-Locking fuer die Zusammenarbeit im Team implementieren. Einsatz beim Bereitstellen neuer Cloud-Infrastruktur, bei der Migration von ClickOps oder CloudFormation zu deklarativem IaC, beim Verwalten mehrerer Umgebungen, beim Versionieren von Infrastruktureaenderungen neben dem Anwendungscode oder beim Durchsetzen von Standards ueber wiederverwendbare Module.

rudironsoni Skill

Adds CI/CD to a .NET project. GitHub Actions vs Azure DevOps detection, workflow templates.

knownasnaffy Bundle

Lint and validate GitLab CI/CD pipeline YAML files (.gitlab-ci.yml) for syntax errors, security issues, deprecated patterns, and best practices. Use when asked to lint, validate, audit, or check GitLab CI pipelines, .gitlab-ci.yml files, or CI/CD configurations for GitLab. Triggers on "lint gitlab", "check pipeline", "validate CI", "audit gitlab-ci", "pipeline issues", "gitlab security".

knownasnaffy Bundle

Structured incident triage for alerts from any monitoring source. Five-step framework: classify severity, scope blast radius, correlate with recent changes, investigate by alert type, and act (summarize, create ticket, escalate). Parses alerts from PagerDuty, Datadog, CloudWatch, Sentry, uptime monitors, GitHub Actions, AWS SNS/EventBridge, and custom webhooks. Customizable escalation policy and runbook. Uses `gh` CLI for deploy correlation. Use when: an alert fires, something is down, error rates spike, a deployment fails, investigating an incident, triaging a monitoring alert, responding to a page, or an exception tracker reports a new or regressed error.

knownasnaffy Bundle

Pre-flight check for GPU cluster nodes — node validation before training, check cluster node health, is my GPU node ready. 26 health checks covering GPU, PCIe, RDMA/IB, Docker, IOMMU, NUMA, firewall, and more

knownasnaffy Bundle

腾讯云 AI 生成图片识别 (TencentCloud Image AIGC Detection) 技能。适用于 AI 生成图片检测、图片真伪鉴别、AI 绘画检测、Deepfake 检测等场景。TencentCloud Image AIGC Detection is an AI-generated content detection service by Tencent Cloud, supporting aigc detection, AI-generated image identification, and image authenticity review.

knownasnaffy Bundle

Automated news analysis pipeline that fetches CNBC world news, classifies articles by topic (geopolitics vs macroeconomics), and invokes specialized skills (geopolitics-expert or the-fed-agent) to produce structured trading analysis. Use when you need systematic news-to-trading-signal workflow for Iran war, US economy, Fed policy, and market impact assessment.

knownasnaffy Bundle

Deterministic memory/context pipeline for agents: route a user message, retrieve relevant memory snippets, compress into a cited Context Pack (sources are snippet IDs), lint, and fall back safely. Prerequisite: a file-based memory layout with memory/always_on.md + topic files (works out-of-the-box with dr-memory-foundation). Use when building or standardizing agent memory, reducing prompt bloat, implementing retrieval+compression, creating a context pack, designing a memory pipeline, adding lint gates, or setting up golden regression tests for agent context. After install, users can simply say: Apply dr-context-pipeline as default behavior.

knownasnaffy Bundle

Use this skill when a clinician, practice manager, or healthcare developer needs to draft, structure, or retrieve clinical documentation — including SOAP notes, referral letters, prior authorization forms, discharge summaries, and care plan narratives. Connects to FHIR R4-compliant APIs (Epic, Cerner, Azure Health Data Services, HAPI FHIR) to pull structured patient data and generate documentation drafts. Also supports manual input when no EHR connection is available. DO NOT use for direct diagnosis, prescribing decisions, or any task requiring a licensed clinical judgment — this skill assists with documentation only.

knownasnaffy Bundle

腾讯云图像与视频理解 (TencentCloud VITA / vita) 技能。用于图片理解、视频理解、图像分析、视频分析、描述生成、监控录像分析、体育高光提取、直播理解、新闻视频摘要、产品演示视频分析，以及设置或更新 vita prompt。支持单张图片、多张图片、视频。TencentCloud VITA (vita) is a multimodal video understanding and image understanding service by Tencent Cloud, supporting video analysis, image analysis, and media content description generation.

knownasnaffy Bundle

Three-layer sycophancy defense based on ArXiv 2602.23971. Use /anti-sycophancy install to deploy all layers, or manage individually via install-claude-code / install-openclaw / uninstall / status / verify. Layer 1: CC-only hook; Layer 2: SKILL (cross-platform); Layer 3: CLAUDE.md (CC) / SOUL.md (OC).

knownasnaffy Bundle

Automate GitHub pull request workflows including creation, review, merging, and monitoring. Handles PR templates, auto-labeling, CI/CD integration, and review automation. Use when users need to create PRs with proper formatting and templates, automate PR reviews and approvals, monitor PR status and CI checks, auto-merge PRs based on conditions, batch process multiple PRs, or track PR metrics and performance.

knownasnaffy Bundle

Use when designing custom voices with Alibaba Cloud Model Studio CosyVoice customization models, especially cosyvoice-v3.5-plus or cosyvoice-v3.5-flash, from a voice prompt plus preview text before using the returned voice_id in TTS.

knownasnaffy Bundle

Persistent adaptive memory for AI agents. Store memories that fade naturally over time (temporal decay), deduplicate automatically (0.85 cosine threshold), score novel information higher (surprise scoring), and search semantically via sqlite-vec KNN. Use when: you need long-term memory across sessions, memory that adapts to what matters, persistent identity blocks, multi-agent memory isolation, or memory that works without cloud services. NOT for: simple key-value storage, ephemeral session context, or when you need a full vector database like Qdrant/Pinecone. Runs entirely on SQLite — no external database server needed.

knownasnaffy Bundle

Use the Fly.io flyctl CLI for deploying and operating apps on Fly.io. Default to read-only diagnostics (status/logs/config/releases). Only perform state-changing operations (deploys, SSH exec, secrets, scaling, machines, volumes, Postgres changes) with explicit user approval. Use when asked to deploy to Fly.io, debug fly deploy/build/runtime failures, set up GitHub Actions deploys/previews, or safely manage Fly apps and Postgres.

knownasnaffy Bundle

Docker 镜像拉取工具，自动切换镜像源。当官方 registry (docker.io) 拉取超时或失败时，自动尝试备用镜像（docker.1ms.run、docker.m.daocloud.io）。适用于网络受限的 Linux 环境。需要 sg (sgdocker group) 和 docker 已安装。触发场景：(1) 用户请求拉取 Docker 镜像，(2) docker pull 失败，(3) 任何涉及 Docker 镜像下载的场景。

knownasnaffy Bundle

Azure Cosmos DB SDK for Python (NoSQL API). Use for document CRUD, queries, containers, and globally distributed data. Triggers: "cosmos db", "CosmosClient", "container", "document", "NoSQL", "partition key".

knownasnaffy Bundle

Build and run multi-agent content production teams on OpenClaw with single-repo architecture, symlink-based file sharing, role-specialized AGENTS.md, and automated review-fix-score loops. Use when: (1) Setting up a team of 3+ agents with writer/reviewer/scorer/fixer roles for content creation, (2) Creating a quality-controlled publishing pipeline, (3) Bootstrapping agent workspaces with symlinks and tool configs from scratch, (4) Running multi-round review→fix→score cycles until a quality threshold is met, (5) Debugging agent spawn permissions, tool-call loops, or symlink issues. Based on real production experience building a 6-agent content team (2026-03-30).

knownasnaffy Bundle

Orchestrate OpenClaw end-to-end R&D delivery in Feishu from requirement intake to closure using PM, developer, reviewer, and tester subagents. Use when handling研发任务 that need structured requirement parsing, project-context enrichment from Feishu history/wiki, coding + PR flow, read-only review/testing gates, bug-loop rework, and final owner notification.

knownasnaffy Bundle

Query Google Analytics 4 (GA4) data through the Google Analytics Data API for trends, countries, sources, pages, and conversion analysis. Use when a user wants GA/GA4 metrics inside OpenClaw, wants to set up GA4 access, or needs GA4 reports such as activeUsers, sessions, country/source breakdowns, page trends, or key event analysis. For enterprise/internal GA data, first verify which Google account actually has permission before proposing service accounts or extra cloud setup.

knownasnaffy Bundle

Control and use an MCP Toolkit running in Docker. Use when setting up Docker MCP Toolkit (docker compose up/down), checking status/logs, configuring environment variables/secrets, listing available MCP tools/servers, or invoking MCP tools (typically via a local HTTP endpoint) to connect OpenClaw workflows to external systems like Postgres/Neon.

knownasnaffy Bundle

Create KSVC-validated Twitter content from research PDFs. Content types: long threads, quick takes, breaking news, shitposts, personal commentary, victory laps. Triggers on "create content", "write thread", "make a post", "shitpost", or when working with PDFs in /Users/Shared/ksvc/pdfs. REQUIRED STEPS - (1a) Explore agents to scan PDFs, (1b) RLM for deep extraction, (1c) Cross-doc synthesis with rlm-multi, (2) KSVC holdings check (preliminary), (3) write data backbone, (4a) AUDIT with RLM verification, (4a.5) Gemini web cross-validation for FAIL/UNSOURCED inferences, (4b) Final holdings verification (ALL 7 models), (4c) Stylize with kirk-mode skill, (4d) humanizer pass, (5) save draft, (6) chart decision & generation.

knownasnaffy Bundle

Query and monitor UniFi network via local gateway API (Cloud Gateway Ultra / UniFi OS). Use when the user asks to "check UniFi", "list UniFi devices", "show who's on the network", "UniFi clients", "UniFi health", "top apps", "network alerts", "UniFi DPI", or mentions UniFi monitoring/status/dashboard.

knownasnaffy Bundle

Deploy and configure CLIProxyAPI, expose its dashboard safely, connect OAuth providers like Claude Code, Gemini, Codex, Qwen, and iFlow, generate a reusable API endpoint and API key, and integrate it with OpenClaw or other OpenAI-compatible tools. Use when the user wants one API layer from subscription-based CLI or OAuth accounts, multi-account routing, or CLIProxy setup on a VPS or local machine.