Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Discover code by MEANING and DEPENDENCY structure, not by matching text — with the `codemap` CLI: hybrid vector+BM25 semantic search, symbol lookup, incoming/outgoing dependency tracing, file summaries, PageRank importance, afferent/efferent coupling, and cycle detection over an indexed repo. Only authoritative when the index exists and is fresh — a stale or empty index is called out, not trusted. Use for architecture-aware code discovery instead of plain text search.
Generate accessible color palettes: OKLCH shade scales (50-950), tinted neutrals, semantic colors, WCAG contrast checks, dark-mode color remaps, gradients, and CSS/Tailwind color output. Use when the task is ONLY about color. Trigger phrases: "color palette", "color scheme", "generate colors", "shade scale", "color tokens", "color system", "accessible colors", "contrast ratio", "semantic colors", "palette from hex". For logo + fonts + guidelines use brand-identity; for full token/component systems (spacing, radius, components) use design-system; for complete dark themes use dark-mode.
Run a structured, critique-driven brand-identity process from any starting point — a company website, a written brief, a list of products, or just a name and concept — through to a complete packaged brand kit and design system: logomark, outlined wordmark, lockups, round-safe icons, self-theming favicon, PNG rasters, a generated guidelines page, a README, and optional AI merch mockups (shirts, caps, business cards). Use this whenever the user wants a logo, a brand, a visual identity, a rebrand, a logomark, brand assets, a favicon/icon set, or says things like "design a logo for my company", "we need branding", "make us a brand kit", or shares a company site asking for identity work. Even if they only ask for "a logo", use this skill — a logo that ships without its variants, small-size testing, and guidelines is not done
Analyze datasets to answer defined questions through statistical methods, trend identification, hypothesis testing, and correlation analysis. Use when the user needs evidence-backed findings or decisions from data; use exploratory-data-analysis instead for open-ended first-pass profiling before questions are defined.
ADF + Databricks 2025 integration patterns. PROACTIVELY activate for: (1) Databricks Job activity in ADF, (2) DatabricksJob (preview) vs DatabricksNotebook activity, (3) ServiceNow V2 connector, (4) ADF managed identity authentication for Databricks, (5) Databricks serverless linked services, (6) Snowflake V2 connector, (7) Databricks job parameters and outputs, (8) MFA enforcement and authentication updates, (9) Unity Catalog integration, (10) Delta Live Tables orchestration from ADF. Provides: Databricks linked service templates (PAT, MSI, serverless), DatabricksJob activity examples, parameter passing recipes, and authentication migration guidance.
Configure a DataHub instance to load and display a Micro Frontend (MFE) app. Use when the user wants to register an MFE with DataHub, add an MFE to the nav sidebar, set up MFE config for local dev or production/k8s, or troubleshoot MFE loading issues.
Use when turning a requirement, spec, or feature brief into a single self-contained HTML design document in a fixed house style — one styled HTML page with a table-of-contents, architecture/sequence SVG diagrams, code/SQL/YAML blocks, callout boxes, an aligned-decisions (已对齐结论) panel, test cases, and a code index. Reuse for any new 需求/设计文档 that should look identical every time.
Specialized Preact development skill for standards-based web applications with a native-first architecture and minimal dependency footprint. Use when building Preact projects, particularly those involving data visualization, interactive applications, single-page apps with HTM syntax, Web Components integration, CSV/JSON data parsing, WebGL shader visualizations, or zero-build solutions with vendored ESM imports.
Provides Elastic Docs syntax guidance, troubleshoots markup issues, and helps write directives correctly. Use when writing or editing documentation that uses MyST Markdown with Elastic extensions, or when troubleshooting build errors related to syntax.
Product and technical document creation through guided discovery, including project PRDs, feature PRDs, feature design docs, audit reports, positioning docs, Design Docs, and ADRs, plus archiving of feature folders. Use when defining requirements, consolidating findings from external audits, feature proposals, strategy, trade-offs, or architecture decisions, or when archiving a feature. Not for running audits, UI design, implementation, or meeting notes.
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin/web surface — desktop sessions otherwise ship their own instructions and tools. Export or deliver a ChatCut project through the hosted connector, including video, audio, subtitles, XML, and render-status checks.
Record a video walkthrough of a feature and add it to the PR description. Use when a PR needs a visual demo for reviewers, when the user asks to demo a feature, create a PR video, record a walkthrough, show what changed visually, or add a video to a pull request.
Lint a Figma node tree for WCAG 2.2 accessibility AND design-system quality — contrast, target size, focus indicators, color-only signaling, hardcoded colors, missing text styles, detached components, and more. Use when the user wants a design-side audit BEFORE handoff: triggers 'lint this frame', 'check accessibility', 'WCAG audit', 'is my design accessible', 'find contrast issues', 'check color contrast', 'find hardcoded colors', 'are my components using tokens', 'design QA', 'a11y check on this page', 'audit my design for issues'. Walks the tree from a node (or the whole page) and returns findings with severity (critical/warning/info) and WCAG level (A/AA/AAA/best-practice). The native Figma MCP has NO design-side linting — this is unique to this collection. For the deep per-component a11y scorecard use figma-audit-accessibility; for CODE-side (HTML) checks use figma-scan-code-accessibility
Automatically manage focus sessions, breaks, and hyperfocus protection. Uses ADHD-optimized Pomodoro technique with flexible timers, health reminders, and gentle interruptions. Protects against hyperfocus burnout while maximizing productive time.
Build good-looking web interfaces. Use when: - User asks you to build a web app, website, landing page, or HTML page - User asks for a one-off tool, utility, or demo app - User is starting a new frontend project - User wants to improve how something looks - User mentions UI, design, styling, or making something look better This applies to ANY frontend work, not just "design" tasks. Even simple apps benefit from basic design principles.
Exchange listing tracker. Use this skill whenever the user asks about exchange listing, delisting, or maintenance announcements. Trigger phrases include: any new coins listed recently, what did Binance list, new listings, delisted. MCP tools: news_feed_get_exchange_announcements, info_coin_get_coin_info, info_marketsnapshot_get_market_snapshot.
Godot Expert Analyst: Anara. Visionary project scoring and certification for Godot 4.7+ architecture. Use when evaluating project health, modernity, scalability, dependency graphs, or generating Visionary Certificates. Keywords: analyst, Anara, scoring, certification, architecture audit, ResourceLoader.get_dependencies, typed Dictionary, folder-by-feature, Visionary Certificate, Godot 4.7.
Use when the user wants help with negative keyword optimization, reducing wasted ad spend, mining search term reports for irrelevant queries, building negative keyword lists, preventing campaign cannibalization, auditing negative keywords, or cleaning up an underperforming Google Ads account. Triggers include “negative keywords,” “wasted spend,” “irrelevant traffic,” “search term mining,” “negative keyword list,” “campaign cannibalization,” “cross-campaign negatives,” “negative keyword audit,” “reduce wasted budget,” or “irrelevant queries.” For broad keyword strategy and match types, see google-ads-keywords. For search campaign structure, see google-ads-search.
Helps structure the interview process, calibrate the hiring bar, counter interview bias, and decide between promoting internally vs. hiring externally. Also covers evaluating a new hire's fit during their first 90 days. Use when the user says "interview," "hire," "job description," "JD," "interview loop," "debrief," "hiring bar," "offer," "reject," "sourcing," "recruiter," "headcount," "should I hire a junior," "promote from within," or "new hire isn't working out." Do NOT use for ongoing performance management of an established team member (use performance-reviews).
Diagnose HPC runtime and scheduler problems for materials simulations, including MPI/OpenMP/GPU layout, modules, CUDA/Kokkos hints, scratch paths, walltime, job arrays, restart strategy, scheduler portability, and resource mismatch. Use when an already-submitted job failed, ran slowly, was killed, or behaved differently on a cluster than on a workstation. To author or vet a new submission script before running, use slurm-job-script-generator instead.
Converts CSV/TSV inputs into Infrahub object YAML and loads them onto a fresh branch. Handles a single file, a folder of files, an explicit list of paths, and one-big-denormalized-sheet exports. TRIGGER when: importing CSV, loading CSV/TSV into Infrahub, ingesting spreadsheet data, converting CSV to Infrahub objects, splitting a denormalized CSV across multiple kinds, re-running an import after changing a column mapping, debugging why a row fails to convert or load. DO NOT TRIGGER when: running `infrahubctl load` against an LDJSON dump (different format and tool), designing or modifying schemas (this skill is read-only against the schema and fails closed on unmapped columns), exporting data from Infrahub (use `infrahubctl object get -o csv` for single-kind export), or ingesting JSON/XLSX (v1 is CSV+TSV only).
Connect to any external app and perform actions on it. Use when the user wants to interact with external services like Slack, Linear, HubSpot, Salesforce, Jira, GitHub, Google Sheets, or any other app—send messages, create tasks, sync data, manage contacts, or perform any API operation.
Set up an autonomous research loop where an agent iterates on experiments, hypotheses, and code on git branches. Use this skill when the user wants to automate ML experiments, set up a research agent that self-improves, needs to run many variations of an experiment without manual intervention, or says "automate experiments", "agent research loop", "self-improving agent", "run hyperparameter search", "autoresearch". Based on Karpathy 28k-like AutoResearch post.
Decide how much proof a piece of work needs — from just looking at it, to walking the flow, to writing a test, to writing the test first. Use right after a feature works, before changing code that already works, and every time something that used to work breaks. Also use when the builder asks whether they need tests, or when a change touches money, auth, permissions, data they can't get back, or logic with rules and edge cases.
Generate professional engineering documentation from KiCad projects — Hardware Design Descriptions (HDD), CE Technical Files, Interface Control Documents (ICD), Design Review Packages, and Manufacturing Transfer Packages. Auto-runs schematic, PCB, EMC, and thermal analyses; renders schematic and PCB SVGs with subsystem cropping, focus dimming, net highlighting, and pin-net annotation; generates power tree, bus topology, and architecture block diagrams. Produces styled PDF with cover pages, TOC, and vector SVG embedding. Markdown source of truth — human-editable, version-controllable. Use for "generate documentation", "create report", "HDD", "CE technical file", "design review package", "ICD", "render schematic", "render layout", "generate block diagram", "manufacturing package", "generate PDF", or "custom report".
Kinetic typography videos where big words are the visuals - slamming, stretching, stacking, splitting and swapping in time with a voiceover or music beat - rendered to MP4 at 9:16 or 16:9. Use for text-only explainers, hooks and title sequences, quotes, lyric or poem videos, announcements and word-by-word captions as the main design. Not for subtitles over other footage (use the platform's caption tools) or long reading-heavy slides (use data-story-charts or system-diagram-animation).
Guidelines for developing and packaging applications for 懒猫AI算力舱 (AI Pod). Trigger when building an AI app for deployment to the compute pod, writing ai-pod-service's docker-compose.yml, configuring Traefik routing rules, packaging an AI browser extension, or publishing an AI app to the store.
This skill should be used when users need to research leads, find company information, discover contact details, or identify buyer intent signals. It activates when users ask about lead research, company research, contact discovery, buyer intent, or prospect research.
Query and analyze real-time trending topics and searches on Google Trends for a specified time range and country or region. Trigger this skill when users mention Google Trends, hot topics, real-time trending searches, popular trends, current hot topics, recent trends, viral topics, trends over a time period, regional trend analysis, real-time hot topics, trending topics, popular trends, recent trending searches, or trend discovery. Trigger it even if users do not explicitly say “Google Trends” when they want to discover recent or emerging topics and search terms in a specific market.
Image copyright infringement detection and risk analysis. Trigger this skill when the user mentions copyright detection, copyright verification, image infringement checks, image copyright risk, copyright similarity search, TRO risk analysis, rights holder lookup, copyright compliance verification, copyright detection, image infringement, copyright risk, TRO risk, copyright lookup, infringement analysis, or Ruiguan. Even if the user does not explicitly mention “copyright,” trigger this skill whenever their request involves checking whether an image may infringe a registered copyrighted work.
This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal task briefs that define terms and an exact success predicate linguistically, enumerate non-counting outcomes, set persistence rules with explicit stop and return conditions and effort floors, manage a diverse portfolio of parallel approaches with an approach registry and blocked-route bookkeeping, and gate the return on adversarial audit. Route agent topology and coordination protocols to multi-agent-patterns, runtime control surfaces and loop governance to harness-engineering, evaluator and quality-gate construction to evaluation, judge design to advanced-evaluation, and compaction or memory mechanics to context-compression and memory-systems.
Use when asked to compress, tighten, shorten, condense, or de-slop a design doc, PRD, RFC, architecture note, or similar prose "without losing information". Removes only provable redundancy — filler, hedging, LLM-slop, restated content — never a fact, number, decision, or caveat, and flags every judgment call for the author. Returns a compressed document, a categorized removal log, and a shareable scorecard.
Optimize an OpenClaw agent setup (model routing, context management, delegation, rules, memory). Use when asked about optimizing agents, improving OpenClaw setup, agent best practices, heartbeat/cost guardrails, or choosing optimization priorities across cost/quality/reliability.
Batch visual production workflow for campaigns. Accepts a content calendar or campaign brief, produces multiple platform-ready assets with organized bundle output and a machine-readable manifest. Trigger for “batch design,” “content calendar to assets,” “campaign batch,” “produce all campaign visuals,” or “bulk asset generation.”
Turn a scoped learning project into a sectioned build plan with learning as the primary objective, walking through every design decision with understanding checks, and seed the living knowledge graph. Use after /start-project, when the user says "plan my project", "build the learning plan", or invokes /plan-journey.
Use when the user asks to "create a PowerPoint", "generate PPTX slides", "make a PowerPoint presentation", "build a .pptx deck", "create editable slides", "PptxGenJS", "editable presentation", "corporate deck", "slide deck for sharing", or when the output format is PPTX for any presentation task. Also triggers on "export to PowerPoint", "pitch deck PPTX", "offline presentation", or when the context implies an editable/corporate format. Generates OOXML-compliant .pptx files with PptxGenJS, precise layout, text measurement, and overlap validation.
Design and build spectacular, high-impact product launch videos using Remotion (React). Use this skill whenever the user wants to create a product launch video, promotional video, demo video, feature announcement video, brand reveal, or any motion-graphics-driven product showcase. Also trigger when the user mentions "launch video," "promo video," "product trailer," "product intro," "feature reveal," storyboarding for video, or wants to turn a product into a cinematic visual experience — even if they don't explicitly say "launch video."
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.