Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use scrapling for web scraping and data extraction. Automatically pick the best Fetcher based on the target site's characteristics, then generate and run a Python script to complete the task. Use when: (1) scraping or crawling web content or data (scrape, crawl, fetch page, extract data) (2) needing to bypass anti-scraping protection such as Cloudflare/WAF (3) scraping protected pages after logging in (4) parsing existing HTML to extract structured data (5) the user provides a URL and asks to get page content or specific elements (6) batch-collecting multiple pages
Security audit covering authentication, SQL injection, secret exposure, CSRF and OWASP Top 10 vulnerabilities. Use when the user wants to audit code security, search for vulnerabilities, check authentication/authorization, detect exposed secrets or injections, or mentions "security review" / "audit de sécurité" / "OWASP".
Review secret detection patterns and scanning workflows. Use for identifying high-signal secrets like AWS keys, GitHub tokens, and DB passwords. Use proactively during all security audits to scan code and history. Examples: - user: "Scan for secrets in this repo" → run high-signal rg patterns and gitleaks - user: "Check for AWS keys" → scan for AKIA patterns and server-side exposure - user: "Audit my .env files" → ensure secrets are gitignored and not committed - user: "Verify secret redaction" → check that reported secrets follow 4+4 format - user: "Scan build artifacts for keys" → search dist/ and build/ for secret patterns
Security-first visual testing combining URL validation, PII detection, and visual regression with parallel viewport support. Use when testing web applications that handle sensitive data, need visual regression coverage, or require WCAG accessibility compliance.
Semantic search in the DDC CWICR construction cost database using vector embeddings (BGE-M3, 1024-dim, per-language Qdrant collections). Find similar work items and resources for cost estimation across 8 national bases and 30 markets in 26 languages.
Instrument an application with Sentry — detect the platform, install and initialize the SDK if needed, and wire up any signal — error monitoring, tracing/performance, logging, metrics, profiling, session replay, user feedback, cron check-ins, uptime monitors for the deployed app, and AI/LLM monitoring (agent runs, token cost, and conversations for OpenAI, Anthropic, Vercel AI, LangChain, Google GenAI, Pydantic AI, Laravel AI, Mastra, Eve, Flue, Pi Durable, the Cloudflare Agents SDK, and Workers AI). Use to add Sentry to a project or to capture more than errors.
Draft and fill services agreement templates — consulting contract, contractor agreement, SOW, statement of work, professional services agreement. Produces signable DOCX files from Common Paper and Bonterms standard forms. Use when user says "consulting contract," "contractor agreement," "SOW," "statement of work," "services agreement," or "freelancer contract." Includes lawyer-reviewed practice guides; see openagreements.org/editors.
Audit Apex code for CRUD/FLS violations, sharing rule compliance, SOQL injection risks, and PII exposure. Scans entire codebases for security issues that cause AppExchange review failures. Use when asked about security review, AppExchange review readiness, CRUD/FLS audit, vulnerability scanning, or code security. Activate on mentions of "security audit", "AppExchange", "CRUD/FLS", "stripInaccessible", "with sharing", or "security review".
Convert between Skill (SKILL.md) and Prompt (chat box instructions) formats. Supports both Skill→Prompt and Prompt→Skill conversion while losing no core information. Use when the user mentions converting Skill to Prompt, Prompt to Skill, converting between formats, or converting SKILL.md.
Search and analyze DealerVision production logs via SolarWinds Observability API. Use when investigating errors, debugging issues, checking system health, or when the user mentions logs, SolarWinds, production errors, or system monitoring. Requires the `logs` CLI tool to be installed.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Analyze startups with Paul Graham mindset (pressure, founder-market fit, brutal validation), Dan Koe discipline (monetization, offer, distribution, sales), and Seth Godin principles (differentiation, narrative, smallest viable audience). Triggers on startup idea, business validation, MVP, first customers, revenue model, GTM, product-market fit, "I have an idea".
Svelte 5 and SvelteKit framework patterns. Covers runes ($state, $derived, $effect, $props, $bindable, $inspect), snippets, fine-grained reactivity, component composition, and event handling. SvelteKit coverage includes file-based routing, server and universal load functions, form actions, hooks, adapters, and error handling. Includes Svelte 4 to 5 migration guidance (stores to runes, on:event to onevent, slots to snippets). Use when building Svelte 5 components, configuring SvelteKit routing, implementing form actions, migrating from Svelte 4, or debugging reactivity issues.
Interact with SwanLab by writing tracking code (init/log/finish/multimedia) and querying experiment data via CLI (`swanlab api`). Use this skill when the user wants to write training tracking code, log metrics or media, manage experiments, inspect metrics/histograms/logs/keys, list projects/runs, filter experiments, manage self-hosted users, automate queries via CLI, or mentions “swanlab,” “experiment tracking,” “log metrics,” “swanlab api,” or “swanlab cli.”
Use when building, auditing or freezing a journal submission package from the canonical manuscript. Detects drift between the source and the per-journal submission copy, builds byte-preserving packages with manifests, and records current, stale or frozen status.
Synchronize test scenarios and cases between a local project and Testomat.io. Use this skill whenever the user wants to pull/export/download tests from Testomat.io; or push/import/sync new or updated test cases back to the TMS in corresponding `*.test.md` format. Supports custom directories, markdown test format and advanced import/export workflows.
Guide for implementing the Syncfusion ASP.NET Core Kanban component using Tag Helper syntax. Use this skill when building task boards, configuring columns and swimlanes, or enabling drag-and-drop. Covers card settings, dialogs, and binding remote data for ASP.NET Core MVC and Razor Pages.
**THEMING & APPEARANCE GUIDE** — Assist with Syncfusion ASP.NET Core EJ2 component theming, customization, size modes, and dynamic theme switching. Use when: applying themes (Bootstrap, Material, Tailwind, Fluent, etc.), customizing theme variables, implementing theme switchers, enabling touch mode, or customizing icons and appearance.
Agent-callable Telegram bot tools — send messages, media, locations, contacts, and polls; edit, delete, forward, copy, and pin messages; resolve chats, members, and files. Use when the user mentions Telegram or wants a bot to post, manage, or look up Telegram content — including requests that don't name Telegram explicitly, e.g. "message the team channel", "post this update to the group".
Builds rich text editors with Tiptap, a headless ProseMirror-based editor framework for React with Tailwind v4 support. Covers SSR-safe setup, image uploads, prose styling, collaborative editing, and markdown support. Use when adding a rich text editor, configuring Tiptap extensions, handling image uploads in editors, or setting up collaborative editing with Y.js. Use for tiptap, rich text, editor, prosemirror, react, tailwind.
When the user wants to write YouTube video titles, optimize existing titles, A/B test title variants, or improve click-through rate. Also use when the user says 'write a title,' 'title ideas,' 'optimize my title,' 'fix this title,' 'title for my video,' 'improve CTR,' 'my titles aren't getting clicks,' 'title A/B test,' 'search vs browse title.' For thumbnail concepts to pair with titles, see thumbnail-design. For video ideas to title, see idea-generation.
Systematic progress tracking for skill development. Manages task states (pending/in_progress/completed), updates in real-time, reports progress, identifies blockers, and maintains momentum. Use when tracking skill development, coordinating work, or reporting progress.
Stretches OpenAI Codex (CLI, IDE extension, cloud) 5-hour and weekly usage limits or credits while keeping output quality. Use when the user hits or nears a Codex limit, sees fast usage in /status, has a long session, asks to audit or tune config.toml (model, reasoning effort, verbosity, compaction, tool output limits, MCP servers, profiles) or AGENTS.md, or asks how to use Codex more efficiently. Triggers include "usage limit", "rate limit", "5-hour limit", "weekly limit", "credits", "token saving", "reduce cost", "使用量", "トークン節約", "節約", "5時間制限", "週間制限", "上限", "クレジット".
TikTok Shop public intelligence via unified host MCP `topview-mcp` (progressive disclosure: use_tiktok_data → get_tool_schema → call_tool; deferred td_* tools). Use when: TikTok Shop market trends, product selection, viral material breakdown, scripts, content calendar, affiliate/creator ops, ads/live ops. NOT for: Amazon, Shopee, YouTube KOL pool, or media generation (use topview-amazon-ops, topview-shopee-ops, topview-youtube-kol-ops, or topview-generate).
Deploy, configure, and troubleshoot Traefik v3 reverse proxy — covers all providers, routing, TLS/ACME, middlewares, and production patterns with YAML examples. Load when setting up or debugging a Traefik instance. Do not use this skill for unrelated requests; route to the nearest named specialist.
Use when writing or reviewing TSDoc doc-comments on a TypeScript codebase — the standardized /** ... */ comment grammar (Microsoft's @microsoft/tsdoc) that TypeDoc, API Extractor, and editors parse. Covers what to document (the exported surface: functions, classes, types, React components and props, hooks) and what to skip (private/internal, generated code, trivial cases, prose restating a type); the tag taxonomy categorized into block tags (@param, @returns, @remarks, @example, @defaultValue, @typeParam, @see, @throws, @deprecated), inline tags ({@link}, {@inheritDoc}, {@label}), and modifier tags (@public, @internal, @beta, @alpha, @readonly, @override); the summary-then-@remarks structure; and the key TSDoc-vs-JSDoc rule — do NOT repeat types in comments (the TS types already have them), document intent/behavior. Enforcement is convention-only by default; eslint-plugin-tsdoc is an optional CI pointer. Not TypeDoc-site or Storybook setup (pointers only).
Implement text-to-speech (TTS) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to convert text into natural-sounding speech, create audio content, build voice-enabled applications, or generate spoken audio files. Supports multiple voices, adjustable speed, and various audio formats.
Use this skill when working on Biome's Salsa-backed JavaScript and TypeScript inference, including type-aware lint rules, raw collection or inferred representations, analyzer requests, tracked queries, import or cycle resolution, profiling, and Salsa invalidation tests. Do not use for standalone CSS/HTML module-graph data unrelated to JS/TS inference or for ordinary semantic binding analysis.
Modernizes UIKit apps for multi-window environments by replacing legacy shared-state APIs with context-appropriate modern alternatives. This includes references to mainScreen, interfaceOrientation, application and scene lifecycle, as well as safe area inset updates.
Use when you need to run the AI SDLC (Spec Pack) workflow in the sdlc-dev repository, select/chain requirements-side (raw/solution/prd/prototype/demo) and implementation-side (plan/execute/finishing) skills, and use gates to prevent context drift, writing to the wrong directory, or skipping critical steps under pressure.
Analyze relationship patterns, emotional needs, partnership capacity, and relationship timing from a verified Vedic/Jyotish chart. Use for 'Vedic love reading', 'relationship patterns in my chart', 'when might a relationship begin', 5th/7th-house, PK/DK, Upapada or D9 questions; Chinese requests such as '感情分析', '恋爱运势', or '桃花时机'; and Japanese requests such as '恋愛運を見て', '恋愛傾向を分析して', or '恋愛のタイミングを知りたい'. / 吠陀占星关系与恋爱时机分析引擎。
Complete YouTube long-form video optimization for maximum watch time, SEO, and viral potential. PROACTIVELY activate for: (1) YouTube video strategy, (2) Long-form content planning, (3) Watch time optimization, (4) YouTube SEO, (5) Thumbnail design strategy, (6) Audience retention techniques, (7) YouTube monetization, (8) Connected TV optimization, (9) YouTube algorithm understanding. Provides: Video length optimization, thumbnail best practices, SEO strategies, retention techniques, monetization guidelines, and analytics interpretation.
Capture a website and create a HyperFrames video from it. Use when: (1) a user provides a URL and wants a video, (2) someone says "capture this site", "turn this into a video", "make a promo from my site", (3) the user wants a social ad, product tour, or any video based on an existing website, (4) the user shares a link and asks for any kind of video content. Even if the user just pastes a URL — this is the skill to use.
When the user wants to analyze why deals were won or lost, find patterns across closed deals, or extract competitive intelligence from deal outcomes. Trigger phrases: 'why did we lose that deal,' 'win-loss review,' 'analyze our closed deals,' 'what are we losing to,' 'deal post-mortem,' 'why do we keep losing to [competitor],' 'deal autopsy,' 'competitive losses,' 'why did we win that deal.' For individual call analysis, see call-debrief. For competitive positioning, see competitive-intel. For buyer understanding, see buyer-persona.
Write, revise, or review software design documents using Malte Ubl's "Design Docs at Google" guidance. Use when Codex needs to draft a design doc, technical design, RFC, engineering review doc, architecture proposal, mini design doc, or design-doc review focused on context, goals, non-goals, trade-offs, alternatives, cross-cutting concerns, review lifecycle, and deciding whether a design doc is warranted.
N-dimensional labeled arrays and datasets in Python. Built on top of NumPy and Dask. It introduces labels in the form of dimensions, coordinates, and attributes on top of raw NumPy-like arrays, making data analysis in physical sciences more intuitive and less error-prone. Use for working with multi-dimensional scientific data, NetCDF/GRIB/Zarr files, climate/weather/oceanographic datasets, remote sensing, geospatial imaging, large out-of-memory datasets with Dask, and labeled array operations.
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.
