Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Continuous security vulnerability scanning for OWASP Top 10, common vulnerabilities and insecure patterns. Use when reviewing code, before deployments or on file changes. Scans for SQL injection, XSS, secrets exposure and auth issues. Triggers on file changes, security mentions and deployment prep
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions.
Monsters, dragons, world reveals. Each entity gets its own definition block, the shots are cut by timecode, and scale is bought with reference objects and low angles rather than words like massive. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Epic fantasy and sci-fi spectacle; 中文触发词: 奇幻科幻大场面, 奇幻, 科幻, 巨龙, 怪兽, 史诗), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
Create Sentry alerts using the workflow engine API. Use when asked to create alerts, set up notifications, configure issue priority alerts, or build workflow automations. Supports email, Slack, PagerDuty, Discord, and other notification actions.
Generate visual SEO analysis reports using Google PageSpeed Insights API. Use when user asks to analyze website performance, SEO scores, Core Web Vitals, or page speed. Outputs an interactive HTML report with charts and actionable recommendations.
This skill MUST be used for service innovation case studies (服務創新案例分析), complete classroom-format reports, or research combining frameworks such as PESTEL, Five Forces, SWOT, STP, BMC, persona, service blueprints, and CJM. It SHOULD also be used when researching a 品牌、App、平台或服務 to understand its innovation, business model, customer experience, or outcomes, even without naming a framework. Match the analysis scope to the request.
Use to enable Command Center for Service V2 and configure its supported supervisor controls through the OmniChannel Settings Metadata API while preserving unrelated settings. Requires explicit consent to apply, refuses production customer orgs, and verifies the seeded V2 page and tab. Trigger when enabling Command Center V2, configuring conversation monitoring, enabling agent sneak peek or customer sneak peek, configuring whisper messaging, or enabling queues and skills actions. Do not use to assign supervisor permissions or configure classic OmniSupervisorConfig metadata
Move unlabeled and needs-triage issues through inbox states and write agent-ready briefs, on GitHub, Linear, Jira, or local files. Use when asked to sift the inbox, triage issues, show what needs attention, list the shortcuts or deferred limits marked in the code and file them as tickets, or /sift. Pass you-pick to triage without waiting for answers
Signals scout for warehouse imports. Watches external data sources, sync schemas, webhook push channels, and materialized views for failures, silent staleness, and row-volume cliffs, and suggests materialization candidates from recurring query-log hot spots.
Signals scout for PostHog MCP tool calls. Watches `$mcp_tool_call` telemetry for tools that need improvement — broad-reach failure rates, retry hammering, slow or context-bloating responses — grouped by owning product category, each with a fix suggestion.
Signals scout for the parts of a product people barely use. Measures each clickable element and page against the reach of where it lives, gives each barely used one a likely cause, and reports the ones that are reachable and still not used.
Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes", or "run simplify".
Agent behavioral profiles that standardize how different LLMs behave. Load this skill when you need to: (1) adopt a specific behavioral mode for a task, (2) switch between creative/strict/talkative modes, (3) ensure consistent behavior across different models. Profiles define personality, decision heuristics, communication style, and quality standards.
Generate HTML slide presentations (1 slide = 1 HTML file, 1280x720px) using Tailwind CSS, Font Awesome, and Google Fonts. Use when the user asks to create a new presentation deck or slide HTML files. Covers design guidelines, 43 layout patterns, component library, and PPTX conversion compatibility rules. Supports style selection (creative, elegant, modern, professional, minimalist) and theme selection (marketing, portfolio, business, technology, education).
Use this skill when working with Slidev presentations. Helps with slide syntax, frontmatter configuration, layouts, animations, code highlighting, diagrams, themes, and exporting. Prevents common mistakes like incorrect asset paths, deprecated features, and non-existent layouts.
Upload a CSV of leads + a variants YAML (produced by /campaign-copywriting) to Smartlead as a DRAFT campaign. Handles tag-scoped inbox selection, A/B/C variant assembly, custom field mapping, schedule config, and batch lead upload. ALWAYS creates in DRAFT — you review in Smartlead UI and hit Start manually. Use after /campaign-copywriting, just before the campaign goes live.
Every task that touches a project—implementing, refactoring, diagnosing failed checks, running a project command, or writing a pull request body. The baseline discipline underneath specialized skills: keep changes scoped, run the format and lint loop, map what the change puts at risk, and find out how the project is actually run. Applies even when the request never mentions formatting, linting, comments, dependencies, docs, or descriptions, and when you need one of the project's operations—tests, dev server, build, lint, deploy—and must find it documented or ask. Change-loop practices own progression after results; the conduct baseline applies when a session touches nothing.
Run a staged software-engineering delivery feedback loop from bootstrap through investigation, requirements, design, runtime review, implementation, API/E2E and executable validation, code review, docs sync, and final handoff with durable artifacts and explicit re-entry.
Corrects the wrong defaults a model has when standing up self-hosted SonarQube Server as a continuous gate on AI-generated code, verified against docs.sonarsource.com in July 2026 (Server 2026.3, LTA 2026.1). Use when configuring SonarQube, designing a quality gate, or wiring a scan step into CI for AI-assisted work. Covers the setups that run green while measuring almost nothing — the fudge factor skips duplication and coverage conditions below 20 new lines and is on by default; duplication is never measured on test code; no `new_cognitive_complexity` metric exists to gate on; `sonar.host.url` now defaults to sonarcloud.io rather than localhost; a shallow clone degrades new-code attribution to timestamps. Also covers AI Code Assurance — the project flag, gate qualification, the deprecated Copilot autodetection — and that Community Build cannot analyze pull requests at all. NOT for SonarQube Cloud, IDE connected mode, or authoring custom analyzer rules.
Xiaohongshu viral title generator. Input a topic, a draft note, or an existing title; it first builds a content brief, then batch-produces candidates using 15 title methods specific to Xiaohongshu, scores each one (including search-term coverage, audience targeting, and save motivation), flags compliance risks, recommends titles by role and use case, and gives A/B testing suggestions. Triggers when the user says "小红书标题", "起个笔记标题", "帮我想小红书爆款标题", "这条笔记叫什么好", "标题优化/改写", "标题没人点", "怎么让人搜到我", "标题评分". Differs from WeChat Official Account titles: shorter, more colloquial, strong search, strong audience tags, emoji as standard.
Use when working with general SpacetimeDB client SDK concepts: generated bindings, connection lifecycle, identity, local cache, subscriptions, subscription semantics, reducer invocation, and update callbacks. Triggers on: client SDK, codegen, generated bindings, DbConnection, subscribe, local cache, reducer invocation, update callback.
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation. Use when a Spec Kit workflow calls for this step (based on the official GitHub Spec Kit template).
Run `specify check` to verify that Spec Kit required tools (git, claude, gemini, code, cursor-agent, windsurf, qwen, opencode, codex, shai, qoder, etc.) are installed and available; interpret results and suggest next steps. Use when the user says "check Spec Kit environment", "specify not working", or "slash commands not showing".
Verifies whether code follows Spring Modulith code structure or not. Show list of violations along with recommendations on how to fix them. Use this skill: * When reviewing Spring Boot applications which uses Spring Modulith * When verifying whether Spring Boot application code follows Spring Modulith package structure
Choose the right statistical test, compute effect sizes, design power analyses, and report statistics correctly in ML and AI research papers. Use whenever the user asks how to compare two models statistically, whether results are significant, how many seeds to run, how to report variance, which test to use for non-normal data, how to handle multiple comparisons, or how to answer a reviewer challenging statistical validity. Also use when planning an evaluation and needing to decide the number of seeds/trials before running, or when results are borderline and the user needs to know if they can claim significance. Prevents the most common statistical mistakes in ML papers: reporting only means without variance, choosing seeds post-hoc, and conflating statistical significance with practical significance.
Set up Superagent Context Guardrails at coding-agent tool boundaries, configure and safely use the remote MCP server, and manage signed webhooks for findings, security reports, Contributor Trust, and Runtime Guardrails. Use when the user asks to enable context scanning before an agent consumes URLs, files, email, skills, or MCP repositories; integrate coding-agent hooks; or install, connect, configure, troubleshoot, or operate Superagent from Cursor, Claude Code, Codex CLI, or another MCP client.
Query and analyze large Swagger/OpenAPI JSON documents on-demand to extract endpoint details and schemas without loading the entire spec. Use for API discovery, searching by tag/keyword, understanding request/response structures, and tracing data models. Invoke when user asks to "find an endpoint", "search for login/upload/user APIs", or "explain a schema". Use --spec to specify document path if not in current directory, and --format json for structured output.
Tmux workspace manager — invoke to set up workspace layout, manage panes, or update MOTD status. Creates layout presets (review, browse, focus), opens editor/browser/shell panes, and runs an animated MOTD status panel. Use when the user says 'set up workspace', 'open layout', 'start MOTD', 'split pane', 'open file browser', or 'open review pane'. Only activates in tmux sessions.
Implements Syncfusion Blazor PDF Viewer (SfPdfViewer) for viewing and editing PDF documents in Blazor applications. Use this when working with PDF rendering, annotation, text search, form filling, or document navigation in Blazor.
Implement Syncfusion Dropdown Tree control to display hierarchical data in dropdown format. Use this skill when implementing single or multiple value selection from hierarchical data, enabling checkboxes with dependent parent-child states, lazy-loading large datasets, customizing tree items with templates, and configuring multi-language support. Comprehensive coverage of properties, methods, events, data binding modes, checkbox selection, templates, and accessibility features.
Build file management interfaces with Syncfusion JavaScript FileManager component. Use this when creating file browsers, implementing file operations, enabling upload/download functionality, customizing toolbars and context menus, configuring drag-and-drop, and implementing data binding for file systems. Covers virtualization, access control, localization, and enterprise-grade file operations.
Implement the Syncfusion Vue Chat UI component for Vue chat interfaces, messaging applications, conversational UI, chat widgets, real-time messaging, user-to-user communication, bot integrations, customer support chat, collaborative messaging, instant messaging features, chat rooms, or when user mentions "chat ui", "chat component", "messaging interface", "conversation view", or @syncfusion/ej2-vue-interactive-chat package.
Implements Syncfusion Vue DataManager for local/remote binding, CRUD, querying, caching, and middleware. Supports JsonAdaptor, ODataAdaptor, ODataV4Adaptor, UrlAdaptor, WebApiAdaptor, WebMethodAdaptor, RemoteSaveAdaptor, GraphQLAdaptor, CustomDataAdaptor, and CustomAdaptor. Covers Query class, filtering, sorting, paging, grouping, persistence, offline mode, caching, and error handling.
Use this skill when users need to apply themes, customize appearance, switch dark mode, use CSS variables, configure icons, or modify visual styling for Syncfusion Vue components. Covers icon library, size modes, and Theme Studio integration.
Styles applications using Tailwind CSS v4 utilities. Activates when adding styles, restyling components, working with gradients, spacing, layout, flex, grid, responsive design, dark mode, colors, typography, or borders; or when the user mentions CSS, styling, classes, Tailwind, restyle, hero section, cards, buttons, or any visual/UI changes.
Manage server state in React with TanStack Query v5. Set up queries with useQuery, mutations with useMutation, configure QueryClient caching strategies, implement optimistic updates, and handle infinite scroll with useInfiniteQuery. Use when: setting up data fetching in React projects, migrating from v4 to v5, or fixing object syntax required errors, query callbacks removed issues, cacheTime renamed to gcTime, isPending vs isLoading confusion, keepPreviousData removed problems.
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.