Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Search YouTube, read your own channel and uploaded videos (stats, comments), and upload new videos via the YouTube Data API v3. Use when the user mentions YouTube, "my channel", "my videos", searching YouTube, video views / likes / stats, uploading a video to YouTube, or checking how a published video is doing.
DEPRECATED — prefer the official zentao-cli (https://github.com/easysoft/zentao-cli) and its skills (https://github.com/easysoft/zentao-skills) for new setups. This skill still works for existing @leeguoo/zentao-mcp users and remains useful for its bug resolution stats command. Use the zentao CLI to query and operate ZenTao bugs, tasks, stories, todos, products, programs, projects, executions, plans, releases, test cases, test tasks, test suites, docs, users, departments, issues, and risks. Use when the user mentions 禅道 or ZenTao, wants bug/task/story/todo/project/test/doc lookups or updates, wants bug resolution rate stats or reports (bug 解决率统计/解决数量统计/bug statistics/bug report) by product or person, or needs login / whoami / self-test for a 禅道 instance. ZENTAO_URL usually includes /zentao
Turn user-provided requests, drafts, or prompt text into clearer, more executable prompts without performing the underlying task. Use when the user explicitly wants to improve, rewrite, optimize, tighten, clarify, structure, or adapt a prompt, when they have an idea but do not know how to phrase it, or when the prompt is missing audience, constraints, format, execution context, or success criteria. Also use for system prompts, meta-prompting, prompt frameworks, Claude Code prompts, and batch or API prompt design. Do not use when the user mainly wants the task executed, researched, or implemented rather than the prompt improved.
Analyze paid advertising performance across channels and recommend budget reallocation to maximize ROAS and minimize CAC. Use when: planning quarterly ad budget allocation, diagnosing underperforming ad channels, deciding whether to scale spend on a channel, calculating marginal ROI across Google Ads, Meta, LinkedIn, or TikTok, rebalancing media mix after performance shifts, or setting up a test-and-scale framework for new channels.
Use when auditing an agent codebase against the 12-Factor Agents methodology, reviewing LLM-powered system architecture, or assessing agentic app compliance. Triggers on "analyze agent architecture", "12-factor audit", "how compliant is this agent", or "evaluate this LLM app". Also applies when comparing frameworks or planning agent improvements. Not for quick checklists — this performs deep per-factor codebase analysis with file-level evidence.
Investigate an onchain entity, protocol, market, or wallet question with Allium. Use when the task needs a defensible analytical answer rather than a one-off lookup: check Terminal for existing coverage, select the right source, build the method from a small test to production, validate the result, make calibrated claims, and save reproducible Explorer queries (with an optional dashboard hand-off prompt for Allium Assistant). Chains after `data-matching` (source selection) rather than repeating it
Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scroll-depth data for a URL, names the hot elements by cross-referencing autocapture events on the same page, and can create a saved heatmap the user opens in PostHog, then summarizes the behavior and proposes improvements. TRIGGER when: user asks what a heatmap shows, why people aren't clicking something, where users rage-click, how far they scroll, what to change on a page based on heatmap/click data, or to 'analyze/assess/review the heatmap' for a URL. DO NOT TRIGGER when: the user only wants to create a saved heatmap screenshot with no analysis (use heatmaps-saved-create directly), or is asking about session replay in general (use investigating-replay).
Use this skill when the user asks to “pentest AWS,” “test AWS security,” “enumerate IAM,” “exploit cloud infrastructure,” “AWS privilege escalation,” “S3 bucket testing,” “metadata SSRF,” or “Lambda exploitation,” or needs guidance on Amazon Web Services security assessment.
Expert knowledge for Azure Cache for Redis development, including troubleshooting, best practices, decision-making, architecture and design patterns, security, configuration, and deployment. Use when configuring geo-replication, persistence, private endpoints, Entra auth, or ARM/Bicep-based deployments, and for other Azure Cache for Redis-related development tasks. Not for Azure Managed Redis (use azure-managed-redis), Azure Virtual Machines (use azure-virtual-machines), Azure Kubernetes Service (AKS) (use azure-kubernetes-service), or Azure App Service (use azure-app-service)
Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style × Palette three-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图"
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
AI image generation with OpenAI GPT Image 2.5, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
Parse cyber threat intelligence reports (Mandiant, CrowdStrike, Talos, Microsoft) with stix2, mitreattack-python, and spaCy to extract adversary behaviors, map them to MITRE ATT&CK technique IDs, and build a searchable STIX 2.1 attack-pattern library with detection templates. Use when cataloging attack patterns from CTI reports for threat-informed detection engineering, or generating Sigma/YARA templates from documented behaviors.
Scaffold complete Canvas LMS course structures from specs, templates, or existing courses. Creates modules, pages, assignments, and discussions in bulk. Use when asked to "build a course", "scaffold modules", "create course structure", "set up a new course", or "copy course structure".
Senior CAPA Officer specialist for managing Corrective and Preventive Actions within Quality Management Systems. Provides CAPA process management, root cause analysis, effectiveness verification, and continuous improvement coordination. Use for CAPA investigations, corrective action planning, preventive action implementation, and CAPA system optimization.
Python code quality anti-patterns and review checks: exception hierarchy correctness, singleton identity comparison, narrow exception handling, wildcard import avoidance, magic number naming, and dead local removal. Use when reviewing or self-reviewing Python code for correctness and readability defects that linters and reviewers should catch.
Perform spatial and temporal convergence analysis for solution verification — compute observed convergence orders from grid or timestep refinement studies, apply Richardson extrapolation to estimate discretization error, and calculate the Grid Convergence Index (GCI) per ASME V&V 20 standards. Use when verifying that a numerical solution converges at the expected rate, estimating the error on the finest mesh, checking whether grids are in the asymptotic range, or preparing formal verification reports, even if the user only asks “is my mesh fine enough” or “how accurate is my solution”
Copywriting toolkit for product and web: persuasion-driven copy for landing pages, feature pages, pricing pages, email sequences, and CTAs, with a built-in anti-AI-pattern layer and reference files for hooks, proof, and concision. The repo also bundles SEO, social (LinkedIn and X), French, career, and tone-of-voice sub-skills. Works with Claude Code, Cursor, and Windsurf.
Expert guidance for creating Claude Code skills and slash commands. Use when working with SKILL.md files, authoring new skills, improving existing skills, creating slash commands, or understanding skill structure and best practices.
Use only when the user asks to write, revise, or review a development plan, technical design, project proposal, or implementation roadmap. Do not use for direct implementation, following an existing plan, goal execution, continuing work, or updating progress. Deliver an actionable plan that can be resumed across conversations, based on requirements, repository rules, and code facts.
DingTalk group chats and messages. Use for sending, receiving, or searching messages; creating groups; group administration; Bot/Webhook; files; streaming AI/A2UI cards; or IM-only message predicate filtering. For cross-source topics or behavior traces, use dingtalk-aisearch; for DING/class groups, use dingtalk-misc; for email, use dingtalk-mail
Run a design system multi-point inspection — assess a design system across 10 stations (coverage, best practices, accessibility, shared language, testing, orchestration, governance, feedback, machine-readable docs, agent access) and produce a red/yellow/green inspection report with a prioritized work order. Use when the user asks to inspect, assess, audit, or health-check their design system, run the inspection or a specific station, or asks "why is my design system's check engine light on?"
each::sense is the intelligent layer for generative media. A unified AI agent that generates marketing assets, ads, product images, videos, and creative content. It knows all AI models and automatically selects the best one for your task. Use for any creative content generation request.
Investigate and fix CI failures on a pull request. Use when CI checks fail on a PR branch — covers finding the PR, identifying failed checks, downloading logs and artifacts, extracting the failure cause, and iterating on a fix. Requires the `gh` CLI.
Generate high-CTR YouTube thumbnails using Nano Banana 2 via the Arcads external API. Handles reference image upload, character likeness alignment, proven CTR-tested prompt formulas, and parallel batch generation. Use when the user asks to create a YouTube thumbnail, video thumbnail, A/B test thumbnail variations, or refers to thumbnail design with their face, brand assets, or product photos.
Review AI-generated code changes before committing using GitHuman. Use when reviewing code changes, creating code reviews, checking what the AI agent wrote, preparing to commit, or when the user mentions “review,” “GitHuman,” or “before commit.”
Expert GraphQL developer specializing in type-safe API development, schema design, resolver optimization, and federation architecture. Use when building GraphQL APIs, implementing Apollo Server, optimizing query performance, or designing federated microservices.
Implement real-time Hotwire behavior: Turbo Streams over WebSocket/SSE, custom stream actions, inline stream tags, live list updates, and cross-tab state synchronization. Prefer this skill when the core problem is push-based updates or stream action orchestration. Use hwc-navigation-content for pull-based pagination/tab/lazy-navigation flows, hwc-forms-validation for form lifecycle and validation, hwc-media-content for media upload/playback behavior, hwc-ux-feedback for generic loading/progress/transitions, and hwc-stimulus-fundamentals for non-stream Stimulus fundamentals.
Pick and fetch icons through the Icons8 MCP so a project ends up with one consistent set instead of a pile of mismatched icons. Locks the whole project to one pack, rejects wrong metaphors (settings is a plain gear, not an Apple logo), previews with free PNG URLs and pulls SVG only for the final set. Use whenever a UI, prototype, landing page, slide deck or doc needs icons, when the user mentions Icons8, an icon set or a specific icon, when replacing or auditing icons already in a file, and when an icon should move on hover, click or while loading
UX and visual design consultant for iOS apps using Apple's Liquid Glass design system (iOS 26+). Use when asking about element positioning, layout decisions, visual hierarchy, or whether a design choice is "Apple-approved." Provides design rationale and guidance—not code. Helps create apps worthy of an Apple Design Award.
Convert a grover_base checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a randomly-initialized cMIM decoder + latent_dist, then continue pretraining on the user's corpus as hybrid (vocab + contrast). Effectively kermt-continue-pretrain with a one-time ckpt-conversion step prepended.
Implements knowledge graphs for AI-enhanced relational knowledge. Covers ontology design, graph database selection (Neo4j, Neptune, ArangoDB, TigerGraph), entity extraction, hybrid graph-vector architecture, query patterns, and AI integration. Use when implementing knowledge graphs, designing ontologies, extracting entities and relationships, selecting a graph database, or building hybrid graph-vector search. Use for knowledge graph, ontology design, entity resolution, graph RAG, hallucination detection. For architecture selection and governance, use the knowledge-base-manager skill. For document retrieval pipelines, use the rag-implementer skill.
Methodology playbook for analyzing DeFi lending protocol data on Allium—Aave, Morpho, Fluid, Euler, Maple, Compound-style forks, and per-chain lending markets. Use whenever a question touches deposits, borrows, liquidations, collateral swaps, utilization, TVL, or leverage on a lending protocol—even if the user just names a protocol/asset or asks to compare two lending metrics tables. Covers table-per-event-type join gotchas, column-naming inconsistencies, and liquidation-fill double counting that commonly arise before writing SQL
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.