Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Geophysical equations and rock physics calculations for seismic analysis. Use when the agent needs to: (1) Calculate AVO responses (Zoeppritz, Shuey, Aki-Richards), (2) Perform Gassmann fluid substitution, (3) Generate seismic wavelets (Ricker, Ormsby), (4) Compute reflectivity and synthetic seismograms, (5) Calculate elastic moduli from velocities, (6) Apply Gardner/Castagna empirical relations, (7) Model rock physics effects.
Constructs secure, efficient CI/CD pipelines with supply chain security (SLSA), monorepo optimization, caching strategies, and parallelization patterns for GitHub Actions, GitLab CI, and Argo Workflows. Use when setting up automated testing, building, or deployment workflows.
Author a PostHog canvas with semantic HTML, CSS, and direct browser APIs — documents, articles, generative graphics, 2D canvas and WebGL experiences, and focused experiments where React components add no useful structure. Use after building-canvases has routed a canvas request to a plain-HTML/browser-API implementation. Covers the thin component wrapper the current runtime requires, styling and theming without Quill, drawing surfaces, and animation/cleanup patterns.
Use the CanAI MCP server exclusively for live CanAI site data; never substitute WP-CLI, REST/curl, or wp-content edits. FluentSnippets belongs to the opt-in canai-yolo skill. Store work reads references/WOOCOMMERCE.md or references/FLUENTCART.md. Triggers on: “/canai-mcp”, “wpcanai mcp”, “canai mcp”, “canai-mcp”, “wpcanai remote”, “canai remote”, “remote wpcanai”, “remote canai”, “staging”, “production”, “remote site”, “mcp”, “api key”, “deploy template”, “purge cache”, “page cache”, “tool labels”, “translate”, “translation”, “translate the site”, “i18n”, “multilingual”, “string translation”, “native translation”, “/canai-mcp translate”, “translate content”, “translate cpt”, “content translation”, “optimize production”, “compile tailwindcss”, “compile tailwind”, “build css”, “tailwind build”, “sideload”, “upload”, “upload image”, “upload media”, “media library”, “attach image”, “attachment”, “image to media”, “blog post”, “write a blog post”, “write post”, “wpcanai-write-post”, “chart”, “bar chart”, “line chart”, “graph”, “data visualization”, “chart.js”, “menu”, “nav menu”, “primary menu”, “footer menu”, “set up the menu”, “wpcanai-write-menu”, “turl”, “mega menu”, “dropdown menu”, “menu icon”, “menu per language”, “wpcanai-assign-menu”, “translate this page”, “translate strings”, “parent page”, “child page”, “subpage”, “nested page”, “move a page”, “rename a page”, “wpcanai-update-page”, “reading mode”, “reader mode”, “reader view”, “safari reader”, “preview link”, “preview the draft”, “check the page in a browser”, “screenshot the page”, “wpcanai-preview-link”, “woocommerce”, “woo”, “wc_”, “shop template”, “product template”, “checkout template”, “wpcanai-get-wc-css-reference”, “fluentcart”, “fluent cart”, “fluentcart store”, “fct_”, “wpcanai-get-fluent-cart-pages”, “fluentcart product”, “create a product”, “shipping zone”, “store currency”, “wpcanai-write-fluent-product”, “wpcanai-get-fluent-cart-store”, “attribute colour”, “color swatch”, “wpcanai-write-fluent-attribute-group”, “buy now only”, “checkout mode”, “reprice”, “convert prices”, “subscription product”, “stock”.
Create beautiful visual art in .png and .pdf documents using design philosophy. Use when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Use when writing Python application code that connects to a data source through a CData driver — after the connection and SQL have been validated with the cdata-cli discovery skill. Covers mapping the language to the CData Python Connector edition, downloading the connector wheel from CData's Python repository, activating its license, and connecting via DB-API 2.0 (cdata.<source>.connect). This is the Python build-phase companion to cdata-cli; invoke it whenever the target application language is Python (Salesforce, Snowflake, Jira, Gmail, etc.).
Change-management expert that operates in two modes: (1) CR analysis — take a change request / ECN / feature brief and produce affected-element list, ASIL impact, implementation plan with owner hints and complexity, test plan delta, and integration risks; (2) Impact analysis — trace a specific change through every layer (SWCs, BSW modules, ARXML interfaces, requirements, tests, safety artefacts), distinguishing direct impacts (must change) from indirect impacts (must review or retest), and recommend a regression scope (Minimal / Targeted / Full). Applies ASPICE SWE.6 and ISO 26262-6 §7.4 / -8 §8.4 change practices. Traces the full ripple in a single pass, returns a decision-ready plan/scope with a built-in self-check and explicit confidence/gaps, and can optionally emit a self-contained HTML report under analysis/.
Change analysis, once the observations are comparable. Not for cases whose blocker is comparability itself: mixed sensors, product levels or processing baselines to remote-sensing-analysis, undocumented vertical datums to point-cloud-lidar, multi-decade archive trends over large areas to google-earth-engine. Matching product level does not prove comparability. Otherwise invoke for what, where or how much changed: two-scene comparison, deforestation, urban growth, disaster damage, parcel-change audits, bi-temporal differencing, post-classification comparison, adjusted area, break detection in a series in hand (BFAST/LandTrendr/CCDC). Seasonal mismatch is this skill's own confounder; a documented datum with a stated accuracy budget is settled comparability. Keep both.
Retrieve normalized OFAC sanctions pressure — designation summaries, recent additions, and per-country/per-program aggregates including sanctioned vessels and aircraft. Use when the user asks which countries or programs face sanctions pressure, or what was recently designated.
Build a TYPED citation/reference graph over an ingested corpus — not just embeddings. Flat similarity retrieval cannot tell you that document A *overrules* B, *distinguishes* C, or *relies_on* D. This skill extracts every inter-document reference, classifies the edge TYPE with LLM judgment, and writes first-class typed edges via `gbrain link`, so `gbrain graph-query --type` can walk the argument (“everything this brief relies on, minus anything overruled since”). Every cite-heavy corpus is the same shape: law, academic papers, patents, regulatory filings, a book's bibliography.
Video editing operations using FFmpeg: trimming, cutting, splitting, concatenation, speed changes, cropping, scaling, rotation, overlays, picture-in-picture, green screen removal, video stabilization, transitions, fades, privacy blur, LUT color grading, and motion tracking text. Use when user says "trim", "cut", "split", "merge", "concat", "speed up", "slow down", "crop", "scale", "rotate", "overlay", "watermark", "pip", "green screen", "stabilize", "transition", "fade", "blur face", "privacy", "censor", "LUT", "color grade", or "tracking text"
Guidelines for clinical decision support (CDS) documents: biomarker-stratified cohort analyses and GRADE-graded treatment reports. Covers structure, executive summaries, evidence grading (1A–2C), stats (HR, CI, survival), and biomarker integration. Use for pharma research docs, clinical guidelines, regulatory submissions.
Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation.
Cloud infrastructure security checklist and best practices. Use when: deploying to a cloud platform, configuring IAM, setting up CI/CD pipelines, implementing IaC, configuring monitoring, or managing secrets. Applies whether these needs are raised in Chinese or English.
Provides comprehensive guidance for Tencent Cloud CVM including instance creation, configuration, security groups, and CVM management. Use when the user asks about Tencent Cloud CVM, needs to create CVM instances, configure CVM, or manage Tencent Cloud compute resources.
Add bot protection with Turnstile (CAPTCHA alternative). Use when: protecting forms, securing login/signup, preventing spam, migrating from reCAPTCHA, integrating with React/Next.js/Hono, implementing E2E tests, or debugging CSP errors, token validation failures, or error codes 100*/300*/600*.
Diagnose and create Cloudflare VPC Services for Workers to access private APIs in AWS, Azure, GCP, or on-premise networks. Use when troubleshooting dns_error, configuring cloudflared tunnels, setting up VPC service bindings, or routing Workers to internal services.
Orchestrator drives, Codex codes. Execute an approved plan one task at a time: your agent (Claude Code, etc.) sequences the work, briefs OpenAI Codex to write ALL product code, reviews every diff, runs the test gate BEFORE each commit, commits one task per commit, and opens exactly ONE PR at the end. Use when the user says 'codex-build', 'have codex code it', 'you orchestrate, codex codes', or hands over a plan for step-by-step implementation.
Single "start here" orchestrator for new cold email operators. Asks infrastructure-status questions first, then runs /icp-onboarding → /lead-magnet-brainstorm → /campaign-strategy in sequence, producing a consolidated campaign-plan.md. Ends with an interactive menu of next skills branched on whether the user already has domains/inboxes. Use as the very first invocation on any new repo checkout or when onboarding someone to cold email from zero.
Build or refine UI color systems, warmth, semantic color, and color-based hierarchy in designs that are too gray, monochromatic, or missing color meaning. Use when the user mentions dull colors, gray UI, missing warmth, weak semantic color, or a need for stronger color hierarchy.
Refactor high-complexity React components in Dify frontend. Use when `pnpm analyze-component --json` shows complexity > 50 or lineCount > 300, when the user asks for code splitting, hook extraction, or complexity reduction, or when `pnpm analyze-component` warns to refactor before testing; avoid for simple/well-structured components, third-party wrappers, or when the user explicitly wants testing without refactoring.
Operate native macOS apps via screenshots, mouse, and keyboard. Use only when a task cannot be completed through APIs, dedicated Skills, or file tools and requires real desktop interaction. For web tasks, prefer browser tools; for file reading/writing and code execution, use the corresponding tools; do not expand the scope of screen access on your own.
Visualize and diagnose OpenClaw context window usage. Generates a terminal-rendered breakdown showing workspace files (status, chars, tokens), installed skills inventory, and token budget allocation across bootstrap components. Use when: (1) user asks about context window health or token usage, (2) debugging agent quality degradation ("agent got dumber"), (3) after editing workspace files to verify impact, (4) auditing bootstrap overhead. NOT for: conversation history analysis, model selection, or cost tracking.
Configure session keys and policies for Cartridge Controller to enable gasless, pre-approved transactions. Use when defining contract interaction policies, setting spending limits, configuring signed message policies, or implementing error handling for session-based transactions. Covers SessionPolicies type, policy definitions, verified sessions, and error display modes.
Generate a SoundDefinition for @web-kits/audio from any input - a natural-language prompt, an audio file the user shares, or both. Use when the user says "create a sound", "/create-sound", "design a sound for X", shares a WAV/MP3/sprite, or asks to reverse-engineer a sample. Optionally renders a WAV preview and round-trip-validates the result.
Best practices for using Cursor—rules, commands, skills, subagents, ignore files, Agent security, workflows, and community resources. Use when setting up Cursor, initializing or creating the .cursor folder, writing .cursor/rules or AGENTS.md, creating commands or skills, configuring .cursorignore, working with Agent, discovering rules or MCPs (e.g. cursor.directory), making codebases cursor-compatible, or asking about Cursor workflows, TDD, git commands, or large codebases.
Write, restructure, and organize technical documentation around reader tasks and a verifiable throughline, handling doc types, paths, file names, frontmatter, indexes, and lifecycle per project conventions. For technical docs it also protects facts, commands, paths, and identifiers in mixed Chinese-English content and applies the core principles of ASD-STE100 to English explanatory text; when the user provides both a legitimate standards PDF and a local checker, it can assist with checking automatically. Use this skill whenever the user wants to add or substantially rewrite plans, investigations, analyses, research, progress reports, guides, operations manuals, tutorials, reference material, explanations of principles, decisions, incidents, meeting notes, changelogs, or specifications; it also applies when organizing a docs directory and topic indexes. Do not use it for plain translation, polishing a short passage, changing only code, or looking up a single fact.
Analyze tooling overlap and optimization opportunities in AI-assisted development projects. Use when: (1) auditing project tooling ecosystem, (2) identifying duplicate or redundant tools, (3) finding consolidation opportunities, (4) generating tooling health reports.
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.