Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
Twitter/X research via paid API: search tweets with 50+ operators, fetch tweets with threads/replies/quotes, get user profiles with tweets/followers/following. Uses x_payment tool for automatic USDC micropayments ($0.003/call). Use when: (1) searching tweets by keyword, user, or advanced operators, (2) fetching specific tweets by ID/URL with context, (3) looking up user profiles and their activity.
Guides hands-on development of agentic AI systems—agent loops (plan → act → observe), tool and MCP schemas, multi-agent orchestration and handoffs, state/checkpointing, HITL gates, agent prompts, reliability (retries, idempotency, cancellation), observability, trajectory evaluation, tool sandboxing, injection awareness, and deployment (API, queue, durable workflows). Framework-agnostic with optional LangGraph, Deep Agents, and Cursor SDK pointers—not full framework docs. Use for agentic AI, build an agent, agent loop, tool use, MCP integration, multi-agent, agent orchestration, LangGraph, agentic workflow, AI agent developer, agent handoff, agent memory, HITL agent, evaluate agent, or agentic application—not model training (ai-engineer), ML research (ai-researcher), product strategy only (cpo-advisor), architecture whiteboard only (agent-designer, external), generic backend without agent loops (senior-software-engineer), or red-team only (ai-redteam).
Use when the user wants tool use, MCP access, HTTP or streaming API exposure, auto-function helpers, wait-for-key behavior, or optional `agently-devtools` observation, evaluation, and playground integration through Agently-native extension surfaces rather than custom wrappers first.
Use when the user wants stable structured fields, required keys, reliable machine-readable sections, or downstream-consumable output from one model request, including prompt-config-owned output contracts, `.output(...)`, field ordering, `ensure_keys`, and structured streaming.
Create, review, rewrite, or enforce a high-quality AGENTS.md (the open “README for coding agents” format). Use when the user invokes $agents-md, says AGENTS.md, agents.md, agent instructions, project agent context, nest AGENTS.md, or asks to scaffold, audit, improve, or standardize repository guidance for AI coding agents. Always include the ASD-STE100 Communication block and the Testing block (no post-hoc unit tests, prefer E2E and integration tests only when the repo already has those setups, E2E artifacts, failure modes before isolated tests) in root AGENTS.md files.
Pre-deployment privacy compliance checklist for AI/ML systems covering DPIA completion, lawful basis verification, transparency notices, human oversight mechanisms, bias testing, and post-deployment monitoring setup. Keywords: AI deployment, privacy checklist, go-live, model deployment, compliance gate.
Design and audit AI eval regression operations, golden datasets, prompt/model release gates, rubric governance, judge drift, safety cases, quality monitoring, cost/latency guardrails, failure triage, provider/model changes, human review, and rollback. Use when AI features, agents, copilots, recommendations, or automation need reliable improvement without silent regressions.
Use this skill when the user wants to give feedback on, collect, organize, categorize, or template issues encountered while using AI tools — in any scenario such as coding agents, chat assistants, office assistants, search, writing, data analysis, or internal AI systems. The skill turns free-form descriptions into structured feedback reports and outputs clear issue categories, labels, severity, scenario, impact, and suggestions for additional information.
Generate working Java boilerplate for SAP GenAI Hub using the SAP AI SDK for Java (com.sap.ai.sdk). Covers chat completion, streaming, multi-turn conversations, prompt templates, content filtering, data masking, embeddings, RAG/grounding, prompt registry, and Spring Boot streaming. WHEN: user asks for Java or Kotlin code that calls a GenAI Hub model, wants a Java starter project, asks how to use com.sap.ai.sdk in their app, or asks how to integrate AI Core into a Spring Boot or plain Java application. DO NOT USE FOR: JavaScript/TypeScript code — use `aicore-sdk-js`.
Integrate, build, extend, or review web interfaces with the brand-adaptive ak-ui design language and CSS foundation. Use when a user asks to install ak-ui, create an Arknights-inspired interface without copying game assets, style native or unstyled headless components such as Reka UI, convert an existing page to ak-ui, or audit whether an implementation follows ak-ui tokens, geometry, interaction states, responsiveness, and accessibility.
Build ARIMA models for time series forecasting with trend and seasonality decomposition. Use this skill when the user needs to forecast future values from historical sequential data, test for stationarity, or select ARIMA parameters — even if they say 'time series forecast', 'predict next month sales', or 'ARIMA model'.
Direct ALGOPACK FUTOI API workflows for futures-only open interest, FIZ/YUR segmentation, long and short participant counts, raw futoi endpoints, browser URLs, curl, JSON/CSV handoff, simple HTML output, ISS columns/data normalization, start pagination, and aggregation caveats without Python setup.
Alibaba Cloud OOS ChatOps Agent for natural-language cloud resource management and O&M operations. Supports querying ECS/RDS/VPC/SLB resources, executing operations (start/stop/restart), viewing monitoring and billing data, and batch O&M via OOS. Use when users ask about Alibaba Cloud resources, instance management, cloud operations, or O&M automation. Triggers: “查看实例”, “ECS”, “RDS”, “管理资源”, “运维”, “OOS”, “ChatOps”, “阿里云资源”, “实例列表”, “帮我操作”, “重启”, “停止实例”, “resource management”, “cloud operations”, “list instances”, “batch ops”.
Orchestrate deploying frontend static build artifacts to Alibaba Cloud (OSS + CDN). **Domains and Buckets must be specified by the user**; the agent only queries and displays options for the user to choose. Supports full deployments and incremental updates (upload + refresh). Defaults to the "OSS private Bucket + CDN private origin" secure mode. The flow covers CNAME/TXT DNS records, Let's Encrypt certificate configuration, and cache refresh. Depends on the aliyun-domain/oss/cdn skills; stop immediately on insufficient permissions.
Operate Alibaba Cloud OSS via Python (alibabacloud_oss_v2): list Buckets (ListBuckets), create a Bucket (PutBucket), set Bucket ACL (PutBucketAcl), upload an Object (PutObject). For scenarios such as "list OSS Buckets", "create a storage space", "change Bucket access permissions", and "upload files to OSS". Public read is disabled by default and the Bucket stays private, so access requires CDN or another authorization method. See reference/*.yml for the API contracts, scripts/ for runnable examples, and scripts/requirements.txt for dependencies.
Look up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), score variants or scan windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and build Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool.
Read-only ClickHouse security audit of users, roles, grants, row policies, settings profiles, quotas, named collections, table functions and engines, executable UDFs, TLS and network exposure, Keeper and interserver security, audit logging, password hash hygiene, and SQL SECURITY DEFINER. Use when assessing security posture or finding over-privileged or exposed access.
Read and reason about Altium Designer projects and schematics using structured data from .PrjPcb and .SchDoc files. Use when the user asks an AI to understand, explain, review, debug, summarize, inspect, or query an Altium circuit design, including components, nets, pin-level connectivity, BOMs, variants, sheet hierarchy, power rails, or questions like what is connected to a pin.
Researches Amazon.jobs postings via the Crawlora API — search Amazon's public careers site by keyword and/or job category, then pull any single posting's full description and qualifications by job id — returning clean JSON. Use when the user wants to search Amazon job openings, browse a specific Amazon job category, or fetch the detail for one Amazon job posting.
Researches products, prices, availability, and search suggestions on Amazon (amazon.com) using the Crawlora API, returning clean JSON. Use when the user asks to find a product on Amazon, look up an ASIN's price/details, or pull Amazon autocomplete/keyword suggestions — instead of scraping Amazon pages.
Analyzes business models including revenue models, unit economics, competitive moats, scalability, and value creation/capture mechanisms using frameworks like Business Model Canvas and strategic analysis. Use when the user requests business model analysis, unit economics review, moat assessment, or wants to understand how a company creates and captures value.
Inspect and compare offline AI evaluation experiments, diagnose case-level regressions, and follow scorer history across application, model, or prompt changes. Use when a user asks whether an offline run improved, why a case failed, how scores changed between runs, or how to publish externally computed offline results. Covers immutable scorer versions, comparable dataset cohorts, incomplete coverage, and selective payload reads.
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Run protected AAS maintainer sweeps, PR merge batches, resumable review, immutable distribution, Core checks, and scripted releases. Use for repository maintenance, main alignment, CLI/MCP/Workbench changes, or release work; not ordinary contribution tasks.
Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state. Aomi turns prompts ("swap 1 ETH for USDC", "open a 3x GMX long", "bet $100 on Polymarket") into wallet-signed transactions on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. Use when the user wants a crypto/DeFi agent, AI trading/wallet assistant, or on-chain execution against Uniswap, Aave, Lido, GMX, Hyperliquid, Polymarket, Binance, OKX, or 40+ other protocols. Trigger with prompts about swaps, lending, bridging, staking, perps, prediction markets, or any DeFi/CEX action needing a wallet signature. Account-abstraction aware with EIP-7702/4337 in the backend lane; local CLI signing is EOA. MUST NOT fabricate or echo credentials; values reach the CLI only when the user explicitly supplied them.
This skill should be used when the user requests to add a new third-party API service to the AWS billing/quota monitoring system. It handles the complete onboarding process including adapter creation, Lambda deployment, CloudWatch alarms, Dashboard updates, and verification. Triggers on requests mentioning "add service monitoring", "monitor API balance", "setup quota alerts", "add to billing dashboard", or similar service integration requests.
API gateway patterns and implementations. Kong, AWS API Gateway, NGINX as gateway, rate limiting, request routing, authentication offloading, and request/response transformation. USE WHEN: user mentions "API gateway", "Kong", "AWS API Gateway", "NGINX gateway", "gateway pattern", "request routing", "BFF" DO NOT USE FOR: reverse proxy basics - use infrastructure skills; service mesh - use `service-mesh`; rate limiting in app - use `rate-limiting`
Retrieve and investigate API metrics, request logs, and traces from Apitally. Fetches aggregated metrics, request logs, traces, consumers, and app metadata via the CLI, stores data in a local DuckDB database, and runs SQL queries to investigate issues or answer questions. Use when the user mentions Apitally, the Apitally CLI, API metrics, request logs, traces, or API consumers.
End-to-end pipeline for releasing an iOS / watchOS app to TestFlight and the App Store. Use when the user wants to publish, ship, or release an iOS/watchOS app, get a build onto TestFlight, archive and upload via xcodebuild, deploy a CloudKit schema to Production, set App Privacy or export compliance, mint a Distribution certificate, or work through App Store Connect / Apple Developer portal steps. Triggers on 'continue publishing', 'ship the app to TestFlight', 'release the iOS app', 'upload a build', 'deploy CloudKit to production', 'App Privacy labels', 'distribution signing', or any cryptic Apple upload error (cloud signing, 90057 missing CFBundleShortVersionString, 90474 orientation). macOS and Xcode only.
Execute Shopify Admin API calls via GraphQL in Shopify Remix apps. Use when querying or mutating Shopify data (customers, orders, products, shop, segments, subscriptions), when writing GraphQL for the Admin API, or when handling throttling and retries.
Researches Apple job postings via the Crawlora API — searches jobs.apple.com and pulls full posting detail (description, qualifications, location, team) — returning clean JSON. Use when the user wants to search Apple careers listings, check what a specific Apple team/location is hiring for, or pull the full detail of a specific Apple requisition or pipeline role.
Generate comprehensive App Store listing documentation for iOS/macOS apps with multilingual support. Use when (1) Creating App Store listing content for a new app, (2) Generating multilingual App Store descriptions (English, Simplified Chinese, Traditional Chinese), (3) Preparing app metadata (title, subtitle, keywords, description), (4) Writing release notes or promotional text, (5) User asks to "generate appstore info", "create app listing", or "write app description".
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
Use when a business transaction spans multiple services or aggregates and no distributed-transaction primitive is available — phrases like "saga pattern", "distributed transaction", "compensating action", "choreographed saga", "orchestrated saga", "process manager", "should we use a saga here", "how do we roll back across services". Defines a saga as a sequence of local transactions tied together by compensating actions, with two implementation styles (choreography and orchestration).
Use when discussing object-oriented design principles or component-level structure — phrases like "SOLID", "Single Responsibility", "Open-Closed", "Liskov Substitution", "Interface Segregation", "Dependency Inversion", "SRP", "OCP", "LSP", "ISP", "DIP". Defines the five SOLID principles, with the honest caveats Uncle Bob's original treatment glosses over and the cases where they shouldn't be applied dogmatically.
(forwward) Designs system architecture, selects databases, structures projects, plans APIs, and defines caching strategies with scale-appropriate defaults. Triggers on system design, database selection, project structure, tech stack, API design, caching, or codebase organization.
Must use when scanning or reviewing OpenHarmony ArkWeb/Chromium C++ single files for thread-safety violations involving PostTask, BindOnce, base::Unretained(this), WeakPtr, scoped_refptr, mojo::Connector, GPU/Audio/DrDC threads, NDK/UI callbacks, NWeb, WebContents, Profile, BrowserContext, NavigationController. Enforces false-positive control and outputs strict JSON schema violations for standard_rule1-standard_rule10 only.
When the user wants to calculate Asset Retirement Obligations (ARO) for long-lived assets. Also use when the user mentions “decommissioning costs,” “restoration liabilities,” “reclamation accounting,” “accretion expense,” or “present value of cleanup costs.”
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.