DevOps & Infra

ferroxlabs Bundle

Secrets management expertise covering HashiCorp Vault and AWS Secrets Manager patterns, secret rotation strategies, environment variable management, config file handling, git secret scanning, CI/CD secret injection, zero-trust secret access, and audit logging for keeping sensitive credentials secure throughout the software lifecycle. Use when the user asks about application secrets security, application secrets security best practices, or needs guidance on application secrets security implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

ferroxlabs Bundle

End-to-end workflow for building a complete DevOps pipeline from an empty repository through CI/CD, infrastructure as code, monitoring, alerting, and incident response. Covers the full lifecycle from first commit to production-grade operations. Use when the user wants to devops pipeline from scratch or needs a structured multi-step process for this goal. Do NOT use when the request is a single-step task or requires professional advice beyond educational guidance.

ferroxlabs Bundle

Incident response expertise covering incident command frameworks, severity classification, communication templates, role assignments, war room coordination, post-mortems, blameless culture, runbook design, and building organizational incident response muscle. Use when the user asks about incident commander, incident commander best practices, or needs guidance on incident commander implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

ferroxlabs Bundle

Infrastructure automation expertise covering Terraform module design and composition, policy-as-code with OPA and Sentinel, drift detection and remediation, self-service provisioning platforms, GitOps workflows, state management strategies, and building internal developer platforms that abstract infrastructure complexity. Use when the user asks about infrastructure automation expert, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of infrastructure automation expert or requires a different specialized skill.

paulasilvatech Skill

Use when reviewing Terraform, Bicep, or CloudFormation, checking drift, or hardening infrastructure code. Triggers include "review terraform", "review bicep", "IaC review", "drift detection", and "state file".

paulasilvatech Bundle

Create, audit, repair, and improve GitHub Copilot Agent Skills for VS Code, GitHub Copilot CLI, and GitHub Copilot cloud agent. Use when a user asks to create a skill, generate a SKILL.md, convert a workflow into a reusable skill, audit an existing skill, fix skill loading issues, optimize a skill description, validate frontmatter, or add references/scripts/assets to a skill package.

paulasilvatech Bundle

Route and support Red Hat Developer Hub (RHDH) work across plugin development, overlay management, local testing, Jira, repository navigation, version compatibility, CI debugging, and environment setup. Use this skill when the user asks about RHDH, Developer Hub, dynamic plugins, overlays, rhdh-local, RHDH Jira, plugin catalogs, repositories, or CI/CD tasks.

paulasilvatech Bundle

Guide for setting up vcpkg in C++ projects, managing dependency versions, and cross-compiling. Covers manifest initialization, CMake and Visual Studio integration, classic-to-manifest migration, version pinning, baselines, overrides, triplets, and cross-compilation. Use when a user is working with vcpkg project setup, installation, version management, or cross-platform builds. For specialized tasks, additional references cover custom registries and overlay ports (references/registries.md), CI/CD and binary caching (references/ci.md), and troubleshooting and dependency lifecycle (references/troubleshooting.md).

paulasilvatech Bundle

Build on Azure AI services including AI Search, Speech, Azure OpenAI, and Document Intelligence, covering keyword, vector, hybrid, and semantic search, speech-to-text, text-to-speech, transcription, and OCR. Use when the user asks about AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcription, OCR, or converting text to speech.

adu2021 Skill

Deploy a state-of-the-art binary classifier using ModernBERT to detect prompt injection attacks and protect LLMs from adversarial input manipulation.

adu2021 Skill

Single cloud-side weight-sorting and fine-tuning supporting multiple on-device pruning rates via efficient SVD and MLP decomposition, achieving 4-5.7× memory reduction and 2.7-3.4× throughput across Transformers, SSMs, and hybrid architectures.

adu2021 Skill

Uses flow maps as look-ahead operators to enable principled reward-guided diffusion by predicting trajectory endpoints at any denoising step. Deploy when applying rewards or preferences to diffusion trajectories with meaningful gradients throughout generation.

adu2021 Skill

8B parameter orchestrator trained with end-to-end RL balancing outcome, efficiency, and user preference rewards to strategically coordinate diverse tools and models. Generate realistic tool-use data via ToolScale synthetic pipeline for verifiable multi-turn scenarios.

adu2021 Skill

Generate spatially-coherent 3D point-cloud videos from single images using depth-fused diffusion with efficient world caching for infinite scene exploration.

undermybelt Skill

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

undermybelt Skill

Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm. Use this skill whenever the user is building any system that picks "the top K items for a (user, context)" — social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking.

undermybelt Skill

Generate candidate fixes for verified security findings. Consumes TRIAGE.json (preferred), VULN-FINDINGS.json, or a vuln-pipeline results directory. Pipeline input is delegated to the execution-verified `vuln-pipeline patch` ladder; static-analysis input gets a per-finding patch subagent + independent reviewer and is written as inert diffs for human review. Writes PATCHES/bug_NN/{patch.diff,patch_result.json}, PATCHES.md, and PATCHES.json. Use when asked to "fix the findings", "patch these vulns", "generate fixes", or "close the loop on triage".

undermybelt Skill

Adapt this C/C++ ASAN vulnerability pipeline to a different vulnerability class, target shape, language, or detection mechanism. Use when the user wants to port, migrate, retarget, customize, or fork the pipeline for something other than C/C++ memory-safety bugs — web apps, smart contracts, deserialization, ML systems, or any other domain.

undermybelt Bundle

This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for GKE, and Managed Identities for AKS.

undermybelt Bundle

This skill teaches security teams how to detect and respond to unauthorized cryptocurrency mining operations in cloud environments. It covers identifying cryptomining indicators through compute usage anomalies, network traffic patterns to mining pools, GuardDuty CryptoCurrency findings, and runtime process monitoring on EC2, ECS, EKS, and Azure Automation workloads.

undermybelt Bundle

This skill covers security hardening for serverless compute platforms including AWS Lambda, Azure Functions, and Google Cloud Functions. It addresses least privilege IAM roles, dependency vulnerability scanning, secrets management integration, input validation, function URL authentication, and runtime monitoring to protect against injection attacks, credential theft, and supply chain compromises.

undermybelt Bundle

This skill guides practitioners through hardening AWS Identity and Access Management configurations to enforce least privilege access across cloud accounts. It covers IAM policy scoping, permission boundaries, Access Analyzer integration, and credential rotation strategies to reduce the blast radius of compromised identities.

undermybelt Bundle

This skill covers deploying and tuning Web Application Firewall rules on AWS WAF, Azure WAF, and Cloudflare to protect cloud-hosted applications against OWASP Top 10 attacks. It details configuring managed rule sets, creating custom rules for business logic protection, implementing rate limiting, deploying bot management, and reducing false positives through rule tuning and logging analysis.

undermybelt Bundle

This skill guides organizations through implementing zero trust architecture in cloud environments following NIST SP 800-207 and Google BeyondCorp principles. It covers identity-centric access controls, micro-segmentation, continuous verification, device trust assessment, and deploying Identity-Aware Proxy to eliminate implicit network trust in AWS, Azure, and GCP environments.

undermybelt Bundle

Detecting exposed AWS credentials in source code repositories, CI/CD pipelines, and configuration files using TruffleHog, git-secrets, and AWS-native detection mechanisms to prevent credential theft and unauthorized account access.

undermybelt Bundle

Pod Security Standards (PSS) define three levels of security policies -- Privileged, Baseline, and Restricted -- enforced by the Pod Security Admission (PSA) controller built into Kubernetes 1.25+. PS

undermybelt Bundle

Deploy and configure Rapid7 InsightVM Security Console and Scan Engines for authenticated and unauthenticated vulnerability scanning across enterprise environments.

undermybelt Bundle

This skill covers deploying HashiCorp Vault for centralized secrets management across cloud environments, including dynamic secret generation for databases and cloud providers, transit encryption, PKI certificate management, and Kubernetes integration. It addresses eliminating hardcoded credentials from application code and CI/CD pipelines by implementing short-lived, automatically rotated secrets.

undermybelt Bundle

Deploy Breach and Attack Simulation tools to continuously validate security control effectiveness by safely emulating real-world attack techniques across the kill chain.

undermybelt Bundle

This skill teaches security teams how to deploy and operationalize Amazon GuardDuty for continuous threat detection across AWS accounts and workloads. It covers enabling protection plans for S3, EKS, EC2 runtime monitoring, and Lambda, interpreting finding severity levels, and building automated response workflows using EventBridge and Lambda.

undermybelt Bundle

This skill instructs security practitioners on deploying Microsoft Defender for Cloud as a cloud-native application protection platform for Azure, multi-cloud, and hybrid environments. It covers enabling Defender plans for servers, containers, storage, and databases, configuring security recommendations, managing Secure Score, and integrating with the unified Defender portal for centralized threat management.

undermybelt Bundle

Implement Kubernetes Pod Security Admission to enforce baseline and restricted security profiles at namespace level using built-in admission controller.

undermybelt Bundle

Deploys DNS, HTTP, and AWS API key canary tokens across network infrastructure to detect unauthorized access and lateral movement. Integrates with webhook alerting (Slack, Teams, email, generic HTTP) for real-time intrusion notifications. Provides automated token generation, placement strategies, and monitoring for enterprise network environments. Use when building deception-based network intrusion detection with Canarytokens.org and Thinkst Canary platforms.

findscripter Skill

当用 Python 做经典机器学习（分类/回归/聚类/降维/特征预处理/模型评估/超参调优）时使用；用 scikit-learn 搭建可复现的 Pipeline 并产出训练好的模型与评估报告；不适用于深度学习/大模型、GPU 训练、超内存的大规模分布式训练。触发词：scikit-learn、sklearn、机器学习、分类、回归、聚类、Pipeline、交叉验证、超参调优

adu2021 Skill

Deploy efficient MoE models on resource-constrained edge devices by learning chunk-level activation sparsity that achieves 3.67× speedup. Use when you need to compress LLMs for on-device inference while maintaining reasoning quality and supporting speculative decoding acceleration.

adu2021 Skill

Scale distributed LLM training without all-reduce synchronization using dynamic pipeline routing and modified Nesterov momentum, achieving 4% faster convergence than DiLoCo with exponentially lower communication.