DevOps & Infra

clawbio Bundle

End-to-end WGS to polygenic risk score pipeline. Takes paired-end FASTQ files (or a pre-existing VCF) through nf-core/sarek for variant calling, applies VCF QC (normalisation, hard filtering, Ti/Tv and Het/Hom checks), then computes polygenic risk scores via the PGS Catalog. Fills the FASTQ to VCF gap upstream of the gwas-prs skill.

vanman2024 Bundle

Cloud GPU Configurations Skill

hughdbrown Bundle

Multi-agent editorial review of a book in Hugh Brown's "N in 15 Days" mdBook series (math/15-day-*, sat/15-day-*, aerospace, darwin). Use when asked to review, check, proofread, audit, or QA a 15-day book or one of its days for correctness of text and problems/answers, coverage, reading level and pacing, plagiarism, or AI-sounding prose, or when a book is finished drafting and needs its adversarial review round before deploy.

ligenjian001-ai Bundle

Manage Jenkins CI/CD jobs — trigger, monitor, configure, and troubleshoot. Use for any Jenkins-related operation.

ligenjian001-ai Skill

MANDATORY when user sends a GitHub issue URL or says '处理 issue'. AG confirms the problem, then delegates design and implementation to CC through multi-round dialogue. Covers hft_build C++/Python SDK, scripts, CMake.

ligenjian001-ai Bundle

MANDATORY when filing infra requests. Covers Python API-first deliverable priority, GitHub Issues submission, idempotency guard, post-submit verification, project-aware labeling, and Self-Verification Guide.

opendcai Bundle

DataFlow 开发专家上下文加载器。当用户在 DataFlow 仓库中进行开发时触发， 涵盖：新建算子/Pipeline/Prompt、诊断报错、规范审查、 以及感知仓库变更并建议更新知识库。 Trigger: user is developing in DataFlow repo, asks to create operator/pipeline/prompt, encounters errors, wants code review, or asks about operators.

opendcai Bundle

Reasoning-guided pipeline planner that generates standard DataFlow pipeline code

opendcai Bundle

Reference documentation for the GeneralFilter operator. Covers the constructor, rule-based filtering logic, and pipeline usage notes. Use when: filtering rows based on column value conditions that can be expressed as lambda functions without LLM calls.

opendcai Bundle

Reference documentation for the PromptedFilter operator. Covers the constructor, actual scoring and filtering behavior, and pipeline usage notes. Use when: filtering rows based on LLM semantic quality judgment rather than simple rule-based conditions.

opendcai Bundle

Reference documentation for the KCenterGreedyFilter operator. Covers the constructor, K-Center Greedy algorithm behavior, embedding serving requirements, and pipeline usage notes. Use when: downsampling a large dataset by semantic diversity using embedding vectors.

opendcai Bundle

Reference documentation for the PromptedGenerator operator. Covers constructor parameters, run() signature, actual row-processing behavior, and pipeline usage notes. Use when: integrating PromptedGenerator into a DataFlow pipeline for single-field LLM generation.

opendcai Bundle

Reference documentation for the BenchDatasetEvaluator operator. Covers the constructor, two comparison modes (match/semantic), and pipeline usage. Use when: comparing predicted answers against ground truth answers in benchmark evaluation.

opendcai Bundle

Reference documentation for the EmbeddingGenerator operator. Covers the constructor, embedding serving requirements, actual dataframe flow, and runnable pipeline usage. Use when: converting one text column in a dataframe into embedding vectors for retrieval, clustering, similarity search, or downstream vector-based operators.

orcasecurity Skill

CDR-powered incident investigation — traces actor activity, builds session timelines, maps MITRE ATT&CK techniques, and assesses blast radius from cloud audit logs. Use when user asks to investigate activity, trace an actor, or analyze an incident (e.g., "investigate bastion-admin", "trace activity", "what did anika do", "incident investigation").

orcasecurity Skill

Cloud account coverage and sync-health audit — lists every connected cloud account, sync status, scanner deployment, integration health, and flags blind spots before any audit, investigation, or security review. Use when user asks about coverage, account health, sync status, scanner deployment, "are we monitoring X", or "do we have full coverage" (e.g., "account health", "are all accounts connected", "is everything synced", "coverage audit").

orcasecurity Skill

Analyzes any cloud identity for overprivileged access, actual usage patterns, lateral movement risk, and least-privilege recommendations. Use when user asks about identity permissions, overprivileged access, or IAM review (e.g., "identity review for anika", "is this role overprivileged", "review permissions", "IAM analysis").

orcasecurity Skill

Cloud cost optimization analysis using Orca Security asset data. Discovers all cloud assets (AWS, GCP, Azure) through Orca MCP tools, compares current configurations against cheaper alternatives using live public pricing, and produces a prioritized cost reduction report with exact asset evidence. Use when the user asks about cloud cost optimization, reducing cloud spend, rightsizing instances, saving money on cloud infrastructure, cost reduction opportunities, unused resources, oversized VMs, reserved instances, storage tiering, or wants to know what changes would lower their cloud bill.

orcasecurity Bundle

Admin access grouping - fetches Orca's pre-computed admin clustering (IAM Policy Optimizer) for AWS, Azure, and GCP, groups every admin identity into a small number of shared least-privilege policies that replace blanket AdministratorAccess / Owner, and drives the swap through a staged, confirmation-gated apply. Use when the user wants to group or tier their admins, cut down how many people hold full admin, replace AdministratorAccess with role-based policies, or see how few policies their admin population actually needs. Scoped to grouping the admin population org-wide into shared policies - it takes no account, business unit, or tag as scope. Right-sizing individual identities within an account, business unit, or tag belongs to orca-overprivileged-identities-rightsizing; a single named identity's permission review belongs to orca-identity-review.

orcasecurity Skill

Diagnoses Kubernetes Connector (K8s Tunnel Client / Helm chart `orca-tunnel`) install and connectivity failures from raw customer input — error text, `helm status`, `kubectl describe`, or pod logs — and walks through step-by-step remediation. Use when a user reports the K8s Connector won't install, won't connect, keeps disconnecting, or the cluster shows connected but no scan data appears.

orcasecurity Skill

Inactive-identity cleanup - finds inactive identities (users, groups, and non-human identities) across an account, business unit, or tag in every cloud provider Orca supports (AWS, Azure incl. Entra ID, GCP incl. Google Workspace, Alibaba Cloud, OCI, Tencent Cloud), ranks them by identity risk score (highest risk first), and drives remediation through a non-destructive path (disable) or a destructive path (delete) that always requires explicit confirmation. Asks for the inactivity time frame (e.g. last 60 days) when the user hasn't given one. Use when the user wants to clean up inactive or dormant identities, offboard unused users or service accounts, delete stale groups, or shrink the identity attack surface (e.g. "clean up inactive identities", "find dormant users", "disable unused service accounts").

orcasecurity Skill

Over-privileged identity right-sizing - finds identities holding more permissions than they use, per Orca's pre-computed PoLP (Principle of Least Privilege) recommendations, across an account, business unit, or tag in AWS, Azure, and GCP. Use when the user wants to right-size over-privileged identities, reduce excess permissions across an account, or apply Orca's PoLP / least-privilege recommendations.

microsoft Bundle

Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.

microsoft Bundle

Plan, create, and configure production-ready Azure Kubernetes Service (AKS) clusters. Covers Day-0 checklist, SKU selection (Automatic vs Standard), networking options (private API server, Azure CNI Overlay, egress configuration), security, and operations (autoscaling, upgrade strategy, cost analysis). WHEN: create AKS environment, provision AKS, enable AKS observability, design AKS networking, choose AKS SKU, secure AKS, optimize AKS, AKS spot nodes, AKS cluster-autoscaler, rightsize AKS pod, pod rightsizing, over-provisioned AKS pod, pod resource requests and limits, Vertical Pod Autoscaler, VPA recommendations.

microsoft Bundle

Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, troubleshoot functions, troubleshoot AKS, VM RDP, Linux SSH, VM black screen, can't connect to VM, reset VM password, NSG or firewall blocking, kubectl cannot connect, kube-system/CoreDNS failures, pod pending, crashloop, node not ready, upgrade failures, analyze logs, KQL, insights, image pull failures, cold start issues, health probe failures, resource health, root cause of errors, troubleshoot event hubs, troubleshoot service bus, messaging SDK error, AMQP connection failure, message lock lost, service bus dead letter.

microsoft Bundle

Assess and improve the reliability posture of PaaS Applications (Azure Functions and Azure App Service). Scans deployed resources for zone redundancy, ZRS storage, health probes, and multi-region failover. Presents a feature-pivoted checklist, then drives staged remediation (CLI or IaC patches) end-to-end with user confirmation. WHEN: "assess reliability", "check reliability", "zone redundant", "multi-region failover", "high availability", "disaster recovery", "single points of failure", "reliability posture", "resiliency".

microsoft Bundle

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, create agent, update agent, add tool to agent, invoke agent, agent.yaml, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

microsoft Bundle

Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: "setup AI Runway", "onboard AKS cluster", "install AI Runway", "airunway setup", "deploy model to AKS", "GPU inference on AKS", "KAITO setup on AKS", "run LLM on AKS", "vLLM on AKS", "set up model serving on AKS", "AI Runway controller".

microsoft Bundle

Deploy Python (Flask/Django/FastAPI) code to Azure App Service Linux. WHEN: "Flask App Service", "Django App Service", "FastAPI App Service", "deploy Python to App Service". DO NOT USE FOR: Container Apps, Functions, non-Python, Terraform/Bicep/IaC, full infra — use azure-prepare.

microsoft Bundle

Architect and provision enterprise Azure infrastructure from workload descriptions. For cloud architects and platform engineers planning networking, identity, security, compliance, and multi-resource topologies with WAF alignment. Generates Bicep or Terraform directly (no azd). WHEN: 'plan Azure infrastructure', 'architect Azure landing zone', 'design hub-spoke network', 'plan multi-region DR topology', 'set up VNets firewalls and private endpoints', 'subscription-scope Bicep deployment', 'Azure Backup for VM workloads'. PREFER azure-prepare FOR app-centric workflows.

greenmamba29 Skill

| name | description | license | tags |

joaquimscosta Bundle

Spring Boot 4 observability with Actuator, Micrometer, and OpenTelemetry. Use when configuring health indicators, health checks, custom metrics, distributed tracing, production endpoint exposure, Kubernetes probes, Cloud Run probes, logging, or monitoring. Covers Actuator endpoint security, Micrometer Timer/Counter/Gauge patterns, OpenTelemetry span customization, liveness/readiness probe setup, and metric tag best practices.

matrixx0070 Bundle

YouTube Shorts Pipeline v1.0\n\n## Inputs\n- storySeed: string\n- scenes: array<Scene>\n\n## Outputs\n- videoPath: string\n- uploadUrl: string\n\n## Steps\n1. Generate 8 images (Grok/OpenAI)\n2. Voice (ElevenLabs TTS Hinglish)\n3. Music+SFX\n4. Assembly (FFmpeg 1080x1920)\n5. Quality gate\n6. Upload\n\n## Quality Gate\n- 25-35s duration\n- 8 scenes exact\n- Subs present\n- <500MB\n\n---\nStatus: compiling implementation

fndlalit Bundle

Orchestrate quality engineering across CI/CD pipeline phases. Use when designing test strategies, planning quality gates, or implementing shift-left/shift-right testing.

outlinedriven-odin-claude-plugin Bundle

Use when the user says deslop, debloat, tidy, simplify, clean a diff, or deslop branch diff, or remove dead code or config. Not for remote, credential, publish, deploy, or irreversible changes.

outlinedriven-odin-claude-plugin Bundle

Use when asked to save a URL, file, or pasted text as a .md file with frontmatter, without summarizing. Not for remote, credential, publish, deploy, or irreversible changes.