Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Execute bounded recurring polling loops, CI build babysitting, interval-based status monitors, and self-paced test cycles with explicit timeouts and backoff. Use when monitoring async CI/CD pipelines, polling external service status, running interval test watches, or tracking long-running jobs — even if the user does not explicitly say "fable-loop" (e.g. "babysit this build", "poll until completed", "watch CI status", "wait for deployment"). Do NOT use for synchronous one-shot commands or unbounded infinite polling loops.
Audit and certify repository merge and release readiness against required quality gates, clean git working trees, and verified distribution artifacts. Use when preparing a release tag, validating release checklist criteria, publishing npm/PyPI packages, or certifying a branch for merge — even if the user does not explicitly say "fable-release" (e.g. "prepare the release", "is this ready to merge", "ship to production", "publish the package"). Do NOT use when verification is stale, failing, or missing (use fable-verify first).
A professional solution architect assistant offering guidance across system architecture design, technology selection, architecture review, and performance optimization. Applies to designing new system architectures, reviewing existing architectures, technology selection decisions, architecture refactoring, performance optimization, and microservice design. Combines web search to learn the latest technology trends and provides architecture recommendations based on 2025 best practices, covering modern architecture patterns such as microservices, event-driven, cloud native, and AI architecture.
Automatically detect GPU vendor, find appropriate PyTorch container image, launch with correct mounts, and validate GPU functionality. Supports NVIDIA, Ascend, Metax, Iluvatar, and AMD/ROCm. Use when user says "setup container", "start pytorch container", or invokes /gpu-container-setup.
Use when managing secrets, credentials, encryption keys, certificates, or any sensitive data on Huawei Cloud. Covers CSMS (Cloud Secret Management Service) for secret lifecycle management, KMS (Key Management Service) for encryption key management, rotation diagnosis, and KMS key usage auditing via CTS (Cloud Trace Service). Service keywords: dew, kms, csms, cts, secretsmanager, secrets manager, cloud secret management service, key management service, data encryption workshop, data encryption service, DEW service, KooCLI, 数据加密服务, 密钥管理服务, 凭据管理服务, DEW, KMS, CSMS, CTS, 密钥, 凭据, 加密, 轮转. Provides 10 huawei_* actions: huawei_list_csms_secrets, huawei_describe_csms_secret, huawei_list_csms_secret_versions, huawei_list_kms_keys, huawei_analyze_dew_rotation, huawei_analyze_dew_key_usage, huawei_create_kms_key, huawei_enable_csms_secret_rotation, huawei_update_csms_secret_version, huawei_delete_kms_key. Triggers include: "secret","credential","API key","token","password","encrypt","decrypt","KMS","CSMS","DEW","secretsmanager","certificate","CSR","rotation","密钥","凭据","加密","轮转","数据加密","访问密钥","加密密钥". Activates for ANY task involving secrets or credentials — load this skill before touching secrets.
Kubernetes Cluster API v1.12. Covers clusterctl CLI, ClusterClass, GitOps integration. Scripts for health checks, backup, migration, linting. Templates: clusters, DR, Prometheus. Use when provisioning, upgrading, or operating Kubernetes clusters with CAPI, or running clusterctl and ClusterClass workflows. Keywords: CAPI, clusterctl, kubeadm, cluster lifecycle.
Review Kafka Connect connector configurations for common misconfigurations using the Lenses MCP server. Checks error handling, DLQ setup, converters, transforms, task count and task health. Use when user says "review connectors", "check connector configs", "why is my connector failing" or asks about Kafka Connect configuration. Do NOT use for creating, deploying or controlling connectors.
Diagnoses macOS system-level slowness, heat and fleet-wide timeouts: high load average, leaked per-session child processes (MCP servers, helpers), fork storms, busy loops. Use when the Mac feels slow or hot, fans spin up, or everything times out at once (电脑发烫/卡顿/负载高/全部超时). Not for single-app bugs, network slowness (use tunnel-doctor), launchd watchdog design (use macos-watchdog), or disk-full (use macos-cleaner).
Configures and automates MikroTik RouterOS routers through the terminal, command line interface, .rsc imports, /system script repository, Scheduler, Netwatch, firewall, NAT, DHCP, DNS, bridge, VLAN, routing, VPN, device-mode, backup/export, and RouterOS scripting. Use this skill whenever the user mentions MikroTik, Mikrotik, RouterOS, WinBox terminal, router CLI, router scripts, .rsc files, or configuring MikroTik services from the command line.
No-code data model extensibility for NetBox. Create custom object types with typed fields, relationships to core models and other custom objects, full REST API, and standard NetBox features (tags, change logging, search, bookmarks, journaling).
How to write NetBox custom scripts for automation, data validation, and bulk operations. Use when building scripts that run inside NetBox — covers the Script class, form variables, ORM access, logging, transactions, scheduling, and common patterns.
Use for production Next.js platform work involving Docker or standalone output, static export tradeoffs, self-hosting, deployment adapters, Server Actions encryption keys, shared cache coordination, OpenTelemetry instrumentation, multi-zones, multi-tenant routing, or platform capability reviews.
Kaggle notebook/kernel lifecycle operations. PROACTIVELY activate for: (1) creating Kaggle notebooks or kernels, (2) `kaggle kernels init`, (3) pushing or running notebooks with `kaggle kernels push`, (4) pulling notebooks with metadata, (5) checking kernel status, files, logs, or outputs, (6) downloading output artifacts with file patterns, (7) deleting kernels, (8) Python API kernel operations, (9) auth for notebook CLI workflows. Provides: safe CLI/Python lifecycle commands, run monitoring, output retrieval, destructive-action guardrails.
Application-level OpenChoreo work via the control-plane MCP server — deploying services, configuring workloads, consuming managed-infrastructure Resources, promoting releases, managing secret references, inspecting runtime. Use when the user says 'deploy my service', 'add a component', 'rebuild from source', 'use a database', 'promote to staging', 'rollback', or 'why is my pod crashing'.
Platform-level OpenChoreo work via the control-plane MCP server (plus `kubectl` and Helm) — authoring ProjectTypes / ComponentTypes / ResourceTypes / Traits / Workflows, creating Environments and DeploymentPipelines, registering Planes, configuring secret stores and authorization. Use when the user says 'set up a new environment', 'create a deployment pipeline', 'add a ProjectType', 'add a ComponentType', 'add a ResourceType', 'register a data plane', 'configure auth', or 'install OpenChoreo'.
Optimize your Webshare proxy pool for a specific target website. Tests all proxies against the target, identifies blocked IPs by country/ASN/subnet using data from the webshare CLI, and replaces them via the Webshare MCP. Use when proxies are failing on a site, when setting up a new scraping target, or when you want to tune your proxy pool. Invoke with a target URL as argument.
Build stateless MCP servers with TypeScript on Cloudflare Workers using @modelcontextprotocol/sdk. Provides patterns for tools, resources, prompts, and authentication (API keys, OAuth, Zero Trust). Use when exposing APIs to LLMs, integrating Cloudflare services (D1, KV, R2, Vectorize), or troubleshooting export syntax errors, unclosed transport leaks, or CORS misconfigurations.
Monitor and control an Unraid server via the Unraid Management Agent's MCP server (126 tools, 5 resources, 6 diagnostic prompts) and REST API. Use when: connecting an AI client (Claude, ChatGPT, Cursor, Copilot, Gemini CLI) to Unraid; checking system, array, disk, Docker, VM, GPU, UPS, ZFS, or network status; starting/stopping containers, VMs, the array, or parity checks; diagnosing disk health, performance, or array state; managing alerts, health checks, fan/CPU/tuning, or updates; or choosing between MCP, REST, and WebSocket. Corrects: inventing Unraid tool names or REST paths; running destructive actions (stop array, reboot, delete snapshot) without confirm=true; polling REST in a loop instead of using WebSocket/MCP; dumping full lists instead of search_/get_ tools; and assuming auth the agent lacks by default
6-pillar architecture review framework. Adapted from AWS Well-Architected for use by great_cto's architect agent on every non-nano ARCH document. Forces explicit answers across operational excellence, security, reliability, performance, cost, and sustainability — not just feature design.
Use ado-axi to work with Azure DevOps — work items, pull requests, pipelines, repositories, and raw REST calls — through token-efficient TOON output. Use when the task involves Azure DevOps, ADO, boards, work items, WIQL, pull requests, code reviews, build pipelines, or Azure Repos.
Health inspection for Alibaba Cloud Redis (ApsaraDB for Redis / Tair) instances. Generates HTML reports across 7 dimensions: instance basic info, current sessions, resource usage trends (CPU/memory/connection/bandwidth, last 7 days), big key / hot key analysis, slow log statistics, alert history, and risk-prioritized recommendations. Supports standard / cluster / SplitRW architectures, Tair PENA (persistent memory) and Tair ESSD (disk) types. Single-instance, multi-instance and full-account batch modes are supported. Trigger keywords: Redis inspection, Redis health check, KVStore inspection, Tair inspection, CPU usage, memory usage, connection usage, bandwidth usage, proxy usage, persistent memory, disk usage, slow log, big key, hot key, alert history, instance health report.
Argo Rollouts progressive delivery controller for Kubernetes. USE WHEN user mentions rollouts, canary deployments, blue-green deployments, progressive delivery, traffic shifting, analysis templates, or Argo Rollouts. Provides deployment strategies, CLI commands, metrics analysis, and YAML examples.
Use when the user needs to call management APIs of the AstraFlow platform (AstraFlow / UModelVerse), including scenarios such as creating or managing inference API keys, querying bills and orders, querying model marketplace data, and exporting or querying inference request logs. Provides the complete preparation for UCloud general signature authentication (how to obtain PublicKey/PrivateKey, how to compute the Signature, how to determine Region and ProjectId), and collects the detailed request/response parameter specifications of all 21 known management APIs under the references/ directory.
create and review ci/cd automation for bruno api tests. use when a user asks to run bruno collections in github actions, gitlab ci, jenkins, azure pipelines, bitbucket, kubernetes, or other pipelines; set up the official bruno github action or the official bruno cli docker image; generate junit, json, or html reports; configure environments, tags, secrets, safe mode, developer sandbox mode, workspace paths, or pull request api-test gates for bruno collections.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.