Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Assistant for newapi (new-api), an open-source unified AI gateway platform (https://github.com/QuantumNous/new-api). Use when the user asks about New API, managing models, groups, balance, or tokens, or securely copying keys, applying them to config files, or using them in commands without exposing secrets.
In-depth persona design for Agentforce agents with 50-point scoring. Trigger when the user designs agent personas, defines agent personality or identity, creates persona documents, encodes a persona into Agentforce Builder fields or Agent Script, translates brand guidelines into an agent voice, or asks about agent tone, voice, or register. Do not trigger when building agent metadata (use sf-ai-agentforce), testing agents (use sf-ai-agentforce-testing), or working with Agent Script DSL (use sf-ai-agentscript).
Read the user's local TradingView desktop app through opencli: quotes, options chains with greeks and per-strike IV, options expiries, screener results across stocks, crypto, forex, futures, and bonds, gainers and losers, news headlines and full stories, alerts (active, fired, offline fires), watchlists including colored flag lists, symbol search, chart state, and chart screenshots. Use this skill whenever the user asks for any of these from TradingView ("TV") — for example an options chain, puts, or IV skew for a ticker, an oversold-stock screen, their red flag list, which alerts fired, or a screenshot of their chart. For plain quotes, TA readouts, scans, or futures without the desktop app, prefer tradingview-mcp. Read-only: it never places trades or edits watchlists, alerts, or layouts.
Use when the user needs full UI/UX design intelligence — styles, palettes, fonts, UX guidelines, chart selection, and accessible, performant implementation across any supported stack. Triggers: user says "design", "UI", "UX", "color palette", "typography", "accessibility", "responsive design", "chart type", "style guide", building any user-facing interface.
Upgrades an MWAA environment to a newer Airflow version — within 2.x, within 3.x, or across the 2.x-to-3.x boundary. Computes the version-jump path, inserting the 2.11.x stepping-stone and Python-transition step when needed. Chooses an approach by whether run history and the same environment (URL/ARN) must be kept: a new-environment upgrade (blue-green), a rehearsed in-place upgrade validated on a test copy, or a direct in-place upgrade. Runs Ruff scanning and deprecation-warning log scans for 3.x moves, plus Docker validation, batched deployment, and switchover. Saves a resumable upgrade plan for multi-session work. Triggers on: upgrade MWAA, upgrade Airflow, migrate to Airflow 3, MWAA Airflow 3, Airflow 2 to 3, preserve Airflow history, keep same MWAA environment, blue-green cutover, validation environment before cutover. Not for authoring new DAGs (authoring-mwaa-workflow), debugging unrelated DAG failures (debugging-mwaa-workflow), or MWAA Serverless YAML workflows (provisioned Python DAGs only).
Configure or troubleshoot the hosted AgentMail MCP server for Codex, Claude Code, Cursor, Claude.ai, ChatGPT, or another Streamable HTTP MCP client. Use for installation, OAuth, API-key headers, connection failures, or MCP tool discovery. Do not use when the connection already works and the user just wants to send, check, or manage mail—use the sibling action skills for that
Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and more. Use this skill when users want to: - Find proven image generation prompts (any model) - Get prompt inspiration for portraits, products, social media, posters, etc. - Create illustrations for articles, videos, podcasts, or marketing content - Browse categorized prompt templates with sample images - Translate and understand prompt techniques
Use this skill for Interactive Media Ads (IMA) SDK client-side ad insertion when requesting video ads client-side on websites, apps, TVs, or other platforms with VAST or VMAP. Do not use for Dynamic Ad Insertion (DAI), SSAI, or SGAI (use the `ima-sdk-dai-basics` skill instead).
Apply when choosing which VTEX IO authentication token should back a request from a backend app. Covers `ctx.authToken`, `ctx.storeUserAuthToken`, `ctx.adminUserAuthToken`, `authMethod`, and how requester context should determine the identity used by VTEX clients. Use for deciding which identity talks to VTEX endpoints in storefront-backed requests, Admin actions, or app-level integrations that should avoid hardcoded VTEX credentials
Audit and fix duplicate-page canonicalization across protocol, host, slash, default-document, extension, case, and tracking-parameter URL variants. Use for canonical URLs, duplicate content, preferred URLs, URL consolidation, or conflicting canonical signals. For URL naming and hierarchy design, use url-structure.
AI-assisted pair programming with multiple modes (driver$navigator$switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.
Agent spawning, lifecycle management, and coordination patterns. Manages 60+ agent types with specialized capabilities. Use when: spawning agents, coordinating multi-agent tasks, managing agent pools. Skip when: single-agent work, no coordination needed.
Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.
Build agents for legal document analysis, contract review, and compliance checking. Handles document parsing, risk identification, and legal research. Use when creating contract analysis tools, legal research assistants, compliance checkers, or document review systems
Apply when defining or changing the contract of a VTEX IO app through manifest.json, builder declarations, dependencies, peerDependencies, billingOptions, and app identity. Covers how the app declares capabilities and integration boundaries. Use for scaffolding apps, splitting responsibilities across apps, or fixing contract-level link and publish issues.
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests); use `write-code-eval`. To validate an existing judge, use `validate-evaluator`.
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit," "first 30 days," "QA mentorship," "joining QA team." Not for: setting up QA on a brand-new project from scratch — use `qa-start`. Related: qa-start, qa-project-context, shift-left-testing, ai-qa-review.
Applies QML best practices when producing or working with QML source code. Use whenever QML code is the primary subject: writing, reviewing, fixing, refactoring, optimizing, or debugging QML files, components, or bindings. Do NOT trigger for purely conversational QML questions where no code is produced or examined (e.g. "explain how anchors work").
Configure the embedded Agentforce Employee Agent to reply inside the Microsoft Teams ITSM custom client ('Salesforce Employee Assist' / 'Ask AI Agent'). Use for: 'set up employee agent in Teams', 'embed Agentforce agent in Teams', 'make the IT Service Employee Agent reply in Teams', 'Teams Ask AI Agent not responding', 'agent joins then leaves without replying', 'configure MIAW deployment for Teams employee agent', 'Teams embedded messaging agent setup'. Builds the whole stack headlessly (zero Setup-UI clicks): the Web messaging channel with User Verification ON, the required Enhanced Chat User Verification Key Set (JWKS_URL), the Teams_AgentForce custom-client deployment, the routing flow to the agent, and the Agent Access permission set that lets the portal user reach the agent. DO NOT TRIGGER for enabling the Teams feature Salesforce Go page toggle (service-itsm-teams-configure) or for configuring notification preferences.
Move quality earlier in the development lifecycle. Covers dev/QA pairing patterns, Three Amigos sessions, TDD facilitation (Red-Green-Refactor), PR review checklists for testability, and Definition of Done with quality gates. Includes shift-left maturity model for team assessment. Use when: "shift left," "TDD," "dev-QA pairing," "definition of done," "testability," "quality culture," "QA in sprint planning." Not for: writing the unit tests themselves — use unit-testing; automated PR test-quality review at scale — use ai-qa-review; multi-quarter QA direction or roadmap — use test-strategy. Related: unit-testing, ai-qa-review, test-strategy.
Apply when deciding where and how a VTEX IO app should store and read data. Covers when to use app settings, configuration apps, Master Data, VBase, VTEX core APIs, or external stores, and how to avoid duplicating sources of truth or abusing configuration stores for operational data. Use for new data flows, caching decisions, refactors, or reviewing suspicious storage and access patterns in VTEX IO apps.
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, “model-check this race”, “prove this invariant”, or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.
Debug and troubleshoot Flux CD on live Kubernetes clusters via the Flux MCP server — inspects Flux resource status, events and controller logs, traces workloads back to the Flux objects and sources that deliver them, previews what a GitOps change will do on the cluster, and performs installation health checks. Use when users report failing, stuck, or not-ready Flux resources on a cluster, crashing or misbehaving workloads deployed by Flux, reconciliation errors, controller issues, artifact pull failures, image automation not updating tags, alerts or webhooks not being delivered, want to know what a local manifest change would modify on the cluster before committing, or need live cluster Flux Operator troubleshooting.
Top-level interactive coordinator for Employee Service (ITSM) channel setup. Presents menu of channel setup options (Portal, Teams, Slack) and delegates to the corresponding skill. Use for: “setup ITSM channels”, “configure employee service channels”, “set up service cloud communication channels”, “I want to configure ITSM integrations”, or any general request for ITSM channel/integration setup where the user hasn't specified exactly which channel they want. DO NOT TRIGGER for requests that already name a specific channel or child skill (e.g. “configure Teams”, “set up Slack”, “create an employee portal”, “configure ITSM notifications”) — route directly to the matching child skill instead
Safe-release techniques DURING rollout: feature flags, progressive rollouts, canary analysis, guardrail metrics, production smoke tests, and synthetic users. Bridges QA and SRE practices. Use when: "feature flag testing," "canary deploy," "progressive rollout," "guardrail metrics," "dark launch," "safe rollout." Not for: scheduled probes that run continuously after release — use `synthetic-monitoring`. Not for: designing tests from prod telemetry — use `observability-driven-testing`. Related: release-readiness, synthetic-monitoring, observability-driven-testing, qa-metrics.
Use for any code review: a pull request, a diff, a commit, or a pasted function, handler or file in TypeScript, JavaScript, Python, Go, Swift, Kotlin, C#/.NET, Java, C, C++, Rust, Ruby, PHP or Dart/Flutter. Applies per-language rule packs (security such as SQL injection and missing auth, async and resource handling, error handling, performance) and scripts that score a PR’s risk and complexity, then gives a merge verdict with blocking and non-blocking findings. Use whenever the user asks to review, check or look over code, says “code review”, “review this PR”, “review this diff” or “is this safe to merge”, or asks what is wrong with a snippet, even a single function.
Debug and diagnose Microsoft Teams for Employee Service (ITSM) configuration failures — run a pass/fail validation checklist against the org and report exact remediation. Use this for: 'IT Desk login not working in Teams', 'UEL/CCP user can't log in to IT Service', 'Teams feature not showing / not enabled', 'CI Hub / Service Catalog / My Assets tab not loading', 'Teams Agentforce agent not responding', 'Teams swarming not working', 'Teams SSO failing', or any request to troubleshoot a Teams ITSM setup. Routes the problem to the right checklist (login, feature enablement, tab loading, Agentforce, swarming, SSO) and checks the exact CORS, External Client App, feature toggle, PSL, profile, auth-provider, named-credential, and messaging-channel settings each requires. DO NOT TRIGGER for first-time enablement (service-itsm-teams-configure / -itservice-configure / -itdesk-configure) or building the embedded agent from scratch (service-itsm-teams-employee-agent-configure).
Apply when designing or implementing the runtime structure of a VTEX IO backend app under node/. Covers the Service entrypoint, typed context and state, service.json runtime configuration, and how routes, events, and GraphQL handlers are registered and executed. Use for structuring backend apps, defining runtime boundaries, or fixing execution-model issues in VTEX IO services.
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use for semantic search, pattern matching, similarity queries, and knowledge retrieval. Skip for exact text matching, simple lookups, or when no semantic understanding is needed.
Create structured change proposals and specification deltas using an OpenSpec specification-driven approach. Use for feature planning, proposal creation, specification writing, introducing new capabilities, or starting a development workflow. Trigger phrases include "openspec提案", "规划", "创建提案", "规划变更", "规范功能", "新功能", "新特性", "新需求", "添加功能规划", "设计规范".
Enable Swarming for Employee Service (ITSM) in Salesforce — the Salesforce Go feature service-cloud-swarming that lets IT Desk agents pull in subject-matter experts to collaboratively resolve incidents in real time. Use this for: 'turn on swarming', 'enable service-cloud-swarming', 'set up swarming for IT Desk', 'set Teams as collaboration tool for swarming', 'enable collaborative incident resolution', or any request to enable/verify this Salesforce Go feature. DO NOT TRIGGER for the base Microsoft Teams ITSM integration toggle (service-itsm-teams-configure) or for configuring notification-channel preferences.
SPARC development workflow: Specification, Pseudocode, Architecture, Refinement, Completion. A structured approach for complex implementations that ensures thorough planning before coding. Use for new feature implementation, complex implementations, architectural changes, system redesign, integration work, or unclear requirements. Skip for simple bug fixes, documentation updates, configuration changes, well-defined small tasks, or routine maintenance.
Static source-code vulnerability scan. Reads a target directory (and THREAT_MODEL.md if present), spawns parallel review subagents per focus area, and writes VULN-FINDINGS.json + .md for /triage to consume. Read-only — no building, running, or network. For execution-verified crashes, use vuln-pipeline instead. Use when asked to “scan for vulns”, “review this code for security issues”, “find bugs in <dir>”, or as the step between /threat-model and /triage.
Best practices for analytics, data analysis, and visualization using Python, pandas, matplotlib, seaborn, and Jupyter notebooks. Use when performing exploratory data analysis, building data pipelines, creating statistical visualizations, writing Jupyter notebooks, cleaning and transforming datasets, or implementing analytics dashboards.
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.