Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements.
Complete FFmpeg video analysis and quality control filters for automation and broadcast workflows. PROACTIVELY activate for: (1) Detecting black frames (blackdetect, blackframe), (2) Finding blurry/frozen frames (blurdetect, freezedetect), (3) Auto crop detection (cropdetect), (4) Scene change detection (scdet), (5) Interlace detection (idet), (6) Quality metrics (PSNR, SSIM, VMAF), (7) Signal analysis (signalstats), (8) Frame information logging (showinfo), (9) QC automation scripts, (10) Broadcast compliance checking. Provides: Detection filters, quality metrics, analysis commands, automation patterns.
Figure things out together — any topic, problem, or idea. Presses relentlessly until shared understanding is reached. Use when understanding is the deliverable rather than a preamble to acting, when figuring it out is the goal, or when the user asks to think through a decision, dig deeper, press an assumption, investigate why something is happening, or work through a problem
Pre-earnings preview workflow for US stocks. Use when asked to: preview upcoming earnings; set expectations for next quarter; build bull/base/bear scenarios ahead of earnings; prepare for earnings release; understand what Wall Street expects. Triggers: "preview AAPL earnings", "what to expect from NVDA next quarter", "earnings preview MSFT", "build scenarios for GOOGL earnings", "prepare for Tesla earnings release". Note: For POST-earnings analysis (after results are out), use earnings-analysis skill instead.
Stress-tests predictions by assuming failure and working backward to identify blind spots, tail risks, and overconfidence. Applies Gary Klein's premortem technique to probabilistic forecasting. Use when confidence is high (>80% or <20%), need to identify tail risks and unknown unknowns, want to widen overconfident intervals, or when user mentions premortem, backcasting, what could go wrong, stress test, or black swans.
Make a founder video with Pexo — built for solo founders and small teams. Describe your story, product, or pitch (or paste your site) and Pexo writes the script, generates the shots, picks the models, and returns a finished, publish-ready founder video with music — for fundraising, Product Hunt, or your personal brand. Use for founder content: "founder video", "solo founder video", "founder pitch video", "founder story". NOT for paid ad campaigns (use the video-ad skill).
Use when building portal pages, Web Forms, website routes, or configuring themes and SEO in Frappe. Prevents 404 errors from wrong route resolution, broken Web Form submissions, and missing meta tags for SEO. Covers Web Page, Web Form, Portal Settings, Website Settings, website routes, Jinja templates, Blog, Web Template, has_web_view, meta tags, sitemap. Keywords: website, portal, Web Form, Web Page, route, theme, SEO, meta tags, has_web_view, Blog, Web Template, sitemap, customer portal, self-service, public form, web page, website not showing, 404 on portal.
Use when creating print formats or generating PDFs in Frappe v14-v16. Covers Jinja print formats, Print Designer [v15+], Letter Head, PDF generation API (get_pdf, download_pdf), Report print formats ({%= %} syntax), page breaks, and print CSS patterns. Prevents common mistakes with template engine confusion and PDF rendering. Keywords: print format, PDF, get_pdf, Jinja, Letter Head, print designer, PDF not generating, print format broken, custom PDF, letter head, wkhtmltopdf error, wkhtmltopdf, WeasyPrint, page-break, download_pdf.
Use when creating or substantially redesigning web interfaces, landing pages, dashboards, components, or other frontend UI where visual direction and implementation quality matter. Produces subject-specific art direction, accessible code, and rendered visual verification
Generally-applicable frontend/UI best practices. Use whenever building, modifying, or reviewing UI — adding a form/button/dialog/modal, wiring keyboard shortcuts, creating any interactive surface that submits a form, or any time TSX/JSX is being written or edited. Consult BEFORE writing the code so the patterns are baked in, not retrofitted. If a scenario described in the skill body matches the work, apply the pattern — don't ask, just follow it (call out the choice in one line so the user can override).
Expert-level skill for building, debugging, reviewing, and migrating Freshworks Platform 3.0 marketplace apps. REQUIRES Node.js 24.x + FDK 10.x. New UI apps default to React Meta (DEW, metaConfig.framework react); vanilla Crayons is opt-in. Commands: /fdk-react-create, /fdk-react-migrate, /fdk-fix, /fdk-migrate, /fdk-refactor. Does NOT install FDK/Node—use fw-setup.
Applies the user's git defaults: branch from the remote default, merge rather than rebase for ordinary branches, use native GitHub stacks when selected, never amend, squash-merge pull requests, and remove merged worktrees. Use when branching, syncing, committing, pushing, merging, or cleaning up worktrees in the user's repos.
Audit and improve GitHub Codespaces efficiency. Use this skill when a user wants faster Codespaces startup, lower Codespaces spend, slim devcontainers, right-size machines, tune idle timeout, or scope prebuilds to branches with sustained usage.
Implements onboarding and help systems including product tours, interactive tutorials, tooltips, checklists, help panels, and progressive disclosure patterns. Use when building first-time experiences, feature discovery, guided walkthroughs, contextual help, setup flows, or user activation features. Provides timing strategies, accessibility patterns (keyboard, screen readers, reduced motion), and metrics for measuring onboarding success.
Build Solana trading applications combining DFlow trading APIs with Helius infrastructure. Covers spot swaps (imperative and declarative), prediction markets, real-time market streaming, Proof KYC, transaction submission via Sender, fee optimization, shred-level streaming via LaserStream, and wallet intelligence.
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.
Use when users need to diagnose I2C bring-up failures on Arduino or ESP32-class boards, including no devices found, wrong readings, address conflicts, scanner-detects-but-library-fails cases, pull-up problems, or board-family-specific bus quirks.
Use when you need to decide whether a creator partnership is appropriate and prepare a truthful, mutually useful collaboration brief. Trigger phrases include "should we work with this creator?", "evaluate these influencers", "make a creator partnership brief", "how do we structure this collaboration?", and "what should a partner post?". Do not use this to buy followers, conceal sponsorship, automate outreach, or invent a creator's audience fit; use creator-outreach for personalised contact and campaign-brief for the underlying campaign.
Migrate Java code from javax.* to jakarta.* namespace. Use only when the user explicitly asks for a javax to jakarta namespace or framework migration (for example to Tomcat 10+/11 or Jakarta EE), or when java-upgrade or spring-boot-4-migration delegates it. Finding javax imports alone does not authorize a migration.
Knative serverless platform for Kubernetes. Use when deploying serverless workloads, configuring autoscaling (scale-to-zero), event-driven architectures, traffic management (blue-green, canary), CloudEvents routing, Brokers/Triggers/Sources, or working with Knative Serving/Eventing/Functions. Covers installation, networking (Kourier/Istio/Contour), and troubleshooting.
Knip reference for detecting unused code in TypeScript and JavaScript. Detects unused files, exports, dependencies, types, enum members, and circular dependencies; supports auto-fix, monorepos (workspaces), catalogs (pnpm / Yarn / Bun catalogs), knip.json / knip.config.ts, plugins, ignore, reporters (SARIF), first cleanup, gradual adoption, and how Knip works
Use when an AI agent generates, reviews, or revises any legal text (including but not limited to contracts, pleadings, legal opinions, judicial documents, statutory interpretations, legal memoranda, etc.) and must ensure the legal terminology used is precise, unambiguous, and compliant with legal style requirements. Triggered when: 1. drafting or revising legal documents and needing to choose the correct legal terms; 2. reviewing legal text and finding nonstandard, confusing, or ambiguous terminology; 3. converting everyday language into legally standard expressions; 4. translating or comparing legal terms across languages; 5. the user explicitly requests terminology standardization of legal text; 6. precisely defining or explaining legal concepts. This skill is a foundational atomic capability for legal writing and runs through every stage of legal text production.
This skill bridges the current host coding agent (Claude Code, Codex, or Gemini CLI) to IM platforms (Telegram, Discord, Feishu/Lark, QQ, or WeChat). Use for: setting up, starting, stopping, or diagnosing the IM bridge daemon; forwarding agent replies to a messaging app. Trigger on: "link-to-im", "start bridge", "stop bridge", "bridge status", "消息推送", "消息转发", "桥接", "连上飞书", "手机上看claude", "启动后台服务", "诊断", "查看日志", "启动桥接", "停止桥接", "配置", or any mention of IM bridge management. Subcommands: setup, start, stop, status, logs, reconfigure, doctor. Do NOT use for: building standalone bots, webhook integrations, or coding with IM platform SDKs — those are regular programming tasks.
Use when a founder, operator, or subject-matter expert needs a credible LinkedIn point of view based on work they can genuinely explain. Trigger phrases include "turn this lesson into a LinkedIn post", "what should I say on LinkedIn?", "build a founder point of view", "make this insight useful for buyers", and "plan a LinkedIn series". Do not use this to fabricate personal experience, create generic motivational posts, or run paid LinkedIn ads; use social-proof-mining for approved proof, campaign-brief for a launch message, and paid-social-brief for media.
Search global patents through the Google Patents public patent database, with multi-dimensional filters for keywords, inventors, assignees, countries, dates, patent status and more, returning core bibliographic data such as patent publication numbers, titles, inventors, application/publication/grant dates, assignees, CPC classifications and PDF links. Trigger this skill when the user mentions Google Patents, patent search, patent lookup, patent infringement prevention, FTO checks, prior art search, or patent infringement screening. Even if the user does not explicitly mention "Google Patents", trigger this skill whenever they want to search patent literature by keywords or bibliographic criteria.
Operate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems. Use when installing or building llama.cpp, selecting or inspecting GGUF models, running llama-cli or bounded llama-completion, serving an OpenAI-compatible API with llama-server, tuning memory and performance, or diagnosing backend, context, template, and API failures. Do not use for model training or fine-tuning, general inference-framework selection, llama-cpp-python or other bindings, LlamaIndex, Ollama, or LM Studio operation.
Reviews LLM-powered applications against the OWASP Top 10 for Large Language Model Applications (2025 edition). Auto-invoked when reviewing code that integrates LLM APIs, builds RAG pipelines, or deploys AI-powered features. Produces a structured findings report mapped to LLM01-LLM10 with severity ratings, CWE mappings, and prioritized remediation guidance.
Analyze and reclaim macOS disk space through intelligent cleanup recommendations. This skill should be used when users report disk space issues, need to clean up their Mac, or want to understand what's consuming storage. Focus on safe, interactive analysis with user confirmation before any deletions.
Makes a 3D map animation for a reel. A clean white city with parks and a river, a coloured route that draws itself from start to destination while the camera follows, a red pin that drops with a bounce, an ETA card that counts down and a destination card. Use when the user runs /map-route or asks for an animated route, a "from A to B" map, a journey or a commute animation.
Creates visual maps that make implicit relationships, dependencies, and structures explicit through diagrams, concept maps, and architectural blueprints. Guides through identifying nodes and relationships, choosing visualization approaches, and validating completeness. Use when complex systems need visual documentation, mapping component relationships and dependencies, creating hierarchies or taxonomies, documenting process flows or decision trees, understanding system architectures, visualizing data lineage or knowledge structures, or when user mentions concept maps, system diagrams, dependency mapping, relationship visualization, or architecture blueprints.
Read BEFORE writing any code that adds Additive White Gaussian Noise (AWGN) to signals and converts between SNR, Eb/No, Es/No, and per-subcarrier SNR for communications simulations, using awgn(), convertSNR(), berawgn(). The default MATLAB patterns for AWGN (e.g., 'measured' option, manual SNR formulas) produce subtly incorrect results. This skill specifies the correct calling conventions, required function usage, and critical anti-patterns that must be avoided.
Converts MCP servers into on-demand skills to cut context window usage, classifying each tool by replacement strategy and generating the skill package. Triggers on: "convert MCP", "MCP to skill", "reduce context size", "too many tools", "tool token bloat", "MCP migration".
Plan and execute safe cross-system migrations, including service extraction from monoliths. Use when moving data, schemas, interfaces, infrastructure, or service ownership through compatibility windows, dual-running, reconciliation, cutover, recovery, or deprecation. Do not use for deciding whether decomposition is justified, designing a target architecture, or implementing one named technology; route those to the relevant architecture or specialist skill.
Use when the user asks to build Android screens, Jetpack Compose layouts, Material components, or any Android app UI. Also use when styling, redesigning, or beautifying any Android interface. Covers Material 3 Expressive for Android 16, spring motion, shape variety, and platform-native patterns.
Read-only retrieval of entity information from the FIWARE Orion Context Broker (NGSIv2). Proactively use when you need GET queries to data-integration platforms, city OS, smart city platforms, sensor data or IoT platforms, to check entity lists and counts, or to investigate the NGSIv2 API. Triggers on requests involving Orion / NGSIv2 / Context Broker / entity retrieval / q queries / geospatial queries / platform access with the Fiware-Service header.
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.