Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Use this skill when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO, and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Use for cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without a local GPU setup.
Authors custom cloud controls and customized frameworks for Assured Workloads when built-in resources cannot satisfy core requirements. Use when creating or synthesizing custom data boundary resources. Don't use for browsing or mapping existing built-in frameworks (use assuredworkloads-frameworks-navigator instead)
Integrate the Dynatrace Flutter Plugin into a Flutter project — dependency setup, config, SDK bootstrap, navigation tracking, and verification. Trigger: "add Dynatrace to Flutter", "Flutter plugin setup", "instrument Flutter app", "integrate Dynatrace Flutter", "mobile observability Flutter", "dynatrace_flutter_plugin". Do NOT use for: querying Flutter RUM data (use dt-obs-frontends), non-Flutter mobile setups, or Dynatrace server-side configuration.
Use the Bailian CLI (`bl`) to complete the full “data → fine-tuning → export → deployment → invocation” workflow, or skip training and deploy a base model directly. Supports fine-tuning text models (SFT/DPO/CPT), audio TTS models (CosyVoice), image generation models (Wan2.7), and video generation models (Wan i2v/kf2v). Covers dataset validation/upload, creating fine-tuning jobs, waiting for training, exporting the best checkpoint, creating inference deployments, waiting for readiness, and providing invocation examples. Activate this skill when the user mentions “training a model,” “fine-tuning,” “fine-tune,” “finetune,” “deploying a model,” “launching a model,” “running/invoking a fine-tuned model,” “training an inference model,” “continued pretraining,” “LoRA/SFT/DPO training,” “speech synthesis model,” “TTS fine-tuning,” “CosyVoice,” “voice cloning,” “image generation fine-tuning,” “text-to-image,” “image-to-image,” “Wan2.7,” “image model training,” “video generation fine-tuning,” “image-to-video,” “first-frame-to-video,” “first-and-last-frame,” “kf2v,” “i2v,” “Wan video,” or “video effects training” on Bailian / DashScope / Alibaba Cloud Model Studio. Use it even if the user does not explicitly say “use bl,” as long as they intend to train or deploy on Bailian; do not assemble commands yourself.
Use the `surreal` command-line binary to run a SurrealDB server (in-memory, RocksDB, SurrealKV, or TiKV), open an interactive or piped SQL REPL, import and export databases, check server readiness, upgrade the binary, repair storage, and manage SurrealML models. Use this skill whenever users run, connect to, back up, restore, or operate SurrealDB from the terminal. Triggers: surreal start, surreal sql, surreal import, surreal export, surreal isready, surreal upgrade, surreal fix, surreal ml, SurrealDB CLI, surreal server.
Expert knowledge for Azure DevOps development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when managing org/projects, repos, pipelines, work items, dashboards/analytics, or Azure DevOps Server deployments, and other Azure DevOps related development tasks. Not for Azure Boards (use azure-boards), Azure Pipelines (use azure-pipelines), Azure Repos (use azure-repos), Azure Test Plans (use azure-test-plans).
Implement, review, or improve CloudKit and iCloud sync in iOS/macOS apps. Use when working with CKContainer, CKRecord, CKQuery, CKSubscription, CKSyncEngine, CKShare, NSUbiquitousKeyValueStore, or iCloud Drive file coordination; when syncing SwiftData models via ModelConfiguration with cloudKitDatabase; when handling CKError codes for conflict resolution, network failures, or quota limits; or when checking iCloud account status before performing sync operations.
Handles Depot CLI installation, authentication, login, project setup, organization management, and API access. Use when installing the Depot CLI, logging in with `depot login`, creating or managing Depot projects, configuring API tokens or OIDC trust relationships, setting up depot.json, managing organizations, resetting build caches, or using the Depot API/SDKs. Also use when the user asks about Depot authentication methods, token types, environment variables, or general Depot platform setup that isn't specific to container builds, GitHub Actions runners, or Depot CI.
Provision, connect, and operate Sealos object storage through the sealos-cli s3 commands added in zjy365/sealos-cli#28. Use when the user needs S3-compatible storage for uploads, assets, backups, presigned URLs, bucket policy management, access credentials, quota checks, or wants to replace local MinIO/S3-compatible services with Sealos object storage in local development, Devbox, or app setup.
Perform a full AWS Well-Architected Framework review evaluating all 57 questions across 6 pillars by analyzing code, IaC, and configurations to produce evidence-backed findings with Eisenhower-prioritized remediation.
DigitalOcean platform overview for account setup, projects, tooling (Control Panel, doctl, API, Terraform), and service selection across compute, storage, databases, networking, management, and teams. Use when onboarding or planning DigitalOcean usage.
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
Authors and validates render.yaml Blueprints for Render infrastructure. Use when the user needs to write or edit a render.yaml, wire services together with fromDatabase/fromService/fromGroup, set up projects and environments for multi-service apps, configure preview environments, validate against the schema, or fix immutable field errors. Trigger terms: render.yaml, Blueprint, IaC, fromDatabase, fromService, envVarGroups, previews, projects, environments
Upload files or directories to Volcano Engine TOS (Torch Object Storage) and download files from URLs. Use this skill to (1) upload Agent-generated files or directories (such as videos, images, reports, and output folders) to TOS for sharing, and (2) download files from URLs before Agent processing.
Alicloud Service Scenario-Based Skill. Use for auto-deploying the "Build AI Animation Story Creation App" solution. Automatically creates OSS Bucket, deploys FC application via Devs template, and stops at the experience page. Triggers: "AI动画创作", "animation creation", "动画故事部署", "deploy animation story app".
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time, or missing outputs after a cache hit. Also covers pipeline hangs, tasks that only work in CI but not locally (or vice versa), tasks skipped by --affected, and task inheritance not applying to a project. Activate on any mention of "moon run" or "moon task" combined with a problem — errors, stale cache, missing outputs, wrong results, "nothing to do", or unexpected behavior. Also use for task options (persistent, runInCI, allowFailure, expectFailure, envOverride, affectedFiles, mutex, timeout, outputStyle, cacheLifetime), task checks, cleanup and wait dependencies, and project-level taskOptions. Not for creating new tasks, setting up workspaces, configuring toolchains, or learning moon concepts.
Build, modify, debug, test, and deploy Railcode apps end-to-end. Use when creating a Railcode app from an idea, scaffolding with the Railcode CLI, writing a backend worker with @railcode/sdk, wiring a frontend to worker routes, declaring app authority, testing with railcode dev, migrating a legacy v1 app to apps v2, maintaining an existing v1 browser-SDK app, adding to a v1 app something it cannot do (a secret, a backend, a cron, authorization that must hold), or deploying. Do not use for managed-agent authoring or general organization administration.
Build with D1 serverless SQLite database on Cloudflare's edge. Use when: creating databases, writing SQL migrations, querying D1 from Workers, handling relational data, or troubleshooting D1_ERROR, statement too long, migration failures, or query performance issues. Prevents 14 documented errors
Guidance for the Turborepo monorepo build system. Covers turbo.json, task pipelines, dependsOn, caching, remote cache, the “turbo” CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure and best practices, and boundaries. Use when configuring tasks/workflows/pipelines, creating packages, setting up a monorepo, sharing code between apps, running changed/affected packages, debugging cache, or working with apps/packages directories.
This skill should be used when the user asks about "Cloudflare Workers with Bun", "deploying Bun to Workers", "wrangler with Bun", "edge deployment", "Bun to Cloudflare", or building and deploying applications to Cloudflare Workers using Bun
Deploy and manage Fusion Roles V2 configuration using the fusion-roles-cli (froles). USE FOR: deploy role config from a JSON file, create roles/bindings/assignments, export current role state, inspect role assignments. DO NOT USE FOR: database provisioning, application code changes, Azure AD group management outside role bindings, or Roles V1 management.
Saleor Configurator patterns for managing store configuration as code. Use when writing config.yml, running deploy/introspect/diff commands, understanding entity identification (slug vs name), deployment pipeline order, or debugging sync issues.
Upload images to any GitHub repo as a figure bed and get CDN/markdown links (jsdelivr/jsdmirror/raw). One-time setup.sh guides gh login, auto-detects the owner, creates the default repo (img.shenzjd.com) if missing, and syncs config with the img.shenzjd.com web app via the repo's .img.shenzjd.com/config.json — upload with zero manual configuration. Use for uploading images to GitHub, generating CDN links, deleting/listing hosted images, or setting up a figure bed. Keywords: github figure bed, image host, CDN link, jsdelivr, jsdmirror, upload image to GitHub, 图床, 上传图片, CDN 链接, 初始化图床.
Terraform and Infrastructure as Code optimization guidelines from Terramate. This skill should be used when writing, reviewing, or refactoring Terraform/OpenTofu code to ensure optimal patterns for security, maintainability, and reliability. Triggers on tasks involving Terraform modules, infrastructure provisioning, state management, or IaC optimization
Use this skill for proactive backend health audits in an InsForge project — security misconfigurations, performance regressions, and system health issues surfaced by `diagnose advisor`, plus the backend-side deep-dives that pair with each advisor issue. Also use this skill when a user reports backend-wide performance degradation (high CPU/memory, all responses slow, connection pool exhaustion, lock contention) without a single failing request. Trigger on requests like "health check", "audit my backend", "review security", "check RLS policies", "find slow queries", "backend performance review", "high CPU/memory", "everything is slow", "EC2/database/system health", or pre-launch readiness audits. For reactive runtime errors with a single concrete failing request (SDK error objects, HTTP 4xx/5xx, function failures, deploy failures), use `insforge-debug` instead.
Deploy, scale, and manage Kubernetes workloads. Create deployments, services, and configurations, manage cluster resources, troubleshoot pods, and implement production-ready Kubernetes patterns. Use when working with Kubernetes clusters, K8s deployments, or container orchestration
Configures and manages Depot CI, a drop-in replacement for GitHub Actions that runs workflows entirely within Depot. Use when migrating GitHub Actions workflows to Depot CI, running `depot ci migrate`, managing Depot CI secrets and variables, running workflows with `depot ci run`, debugging runs with `depot ci run list`, `depot ci status`, `depot ci logs`, `depot ci diagnose`, or `depot ci ssh`, inspecting test results with `depot tests` or run artifacts with `depot ci artifacts`, checking workflow compatibility, or understanding Depot CI capabilities. Also use when the user mentions the .depot/ directory or depot ci commands, or asks about running GitHub Actions workflows on Depot's infrastructure without GitHub-hosted runners.
Structured logging with proper levels, context, PII handling, and centralized aggregation. Use for application logging, log management integration, distributed tracing, or when encountering log bloat, PII exposure, or missing-context errors.
Comprehensive Cloudflare account management for deploying Workers, KV Storage, R2, Pages, DNS, and Routes. Use when deploying cloudflare services, managing worker containers, configuring KV/R2 storage, or setting up DNS/routing. Requires CLOUDFLARE_API_KEY in .env and Bun runtime with dependencies installed.
Selects and implements NestJS runtime features, error and API contracts, security, testing, DevOps, performance, and safe scale. Use for middleware, guards, pipes, interceptors, exception filters, typed failures/results, Problem Details, validation errors, HTTP/GraphQL/RPC/gRPC/WebSocket error mapping, deadlines, cancellation, retry classification, fatal process errors, authentication, authorization, caching, queues, schedulers, CI/CD, containers, Kubernetes, configuration and secrets, migrations, supply-chain controls, health probes, logs/metrics/traces, SLOs and alerts, incident recovery, rollout and rollback, event-loop or database bottlenecks, load tests, horizontal scaling, idempotency, backpressure, and graceful shutdown. Do not use for frontend-only performance or non-NestJS services. When other skills also apply, reconcile ownership before mutation.
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.