Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
All
An interactive course tutor for the AI Engineering from Scratch course. Reads LEARNING.md, finds the next lesson, teaches it section by section in the terminal, then quizzes you and records progress. Works in a cloned repository or entirely through raw.githubusercontent.com — no setup required. Trigger phrases: “下一课”, “教我”, “继续课程”, “我们来学习”, “继续学习”, or “next lesson”, “teach me”, “continue the course”, “let's learn”, “resume learning”.
When the user wants to account for leases under IFRS 16 or ASC 842. Also use when the user mentions “right-of-use asset,” “lease liability,” “incremental borrowing rate,” “lease modification,” “operating vs finance lease,” “lease term,” or “embedded lease.”
Lightweight research workflow step 8: paper writing. Organizes the work around “how to convince reviewers that the work merits publication,” iterating from a draft through the reviewer’s perspective. Every claim must have evidence, wording strength must match evidence strength, and overclaiming is never allowed. Use after experiments and analysis are complete and a paper needs to be written; to write or revise an abstract, introduction, contribution statement, or conclusion; when concerned about unsupported claims or exaggerated wording; to align contributions across the abstract, introduction, and conclusion; to use the four-paragraph introduction structure (problem → gap → insight → contribution); to review the draft as a reviewer; or to polish a draft for AI-like phrasing, passive voice, or grammar. Triggers: 写论文 / 论文写作 / 写摘要 abstract / 写引言 introduction / 贡献句 contribution / 写结论 / 润色 polish / 改写 / 措辞 / 过度宣称 overclaim / claim 无证据 / 审稿人视角 / 自我审稿 / 贡献一致 / hedge / 学术腔 / AI 腔 / 被动语态 / paper writing / draft. Core discipline: an unsupported claim is a critical integrity gate (spec §4.2, STAGE_GATES[8]=[claim_evidence,overclaim]); overclaiming or inconsistent contributions across the three sections are warnings (the critical wording red line is at the research-ethics delivery gate). Wording strength must match evidence strength; when results are not significant, report only “no significant difference observed,” and never overclaim. Automated wording checks have limits; final judgments on logic, novelty, and argumentation still require a person or reviewer. This skill initiates rework from 8→7 (unsupported claim → result-analysis) and 8→6 (implementation gap → experiment-coding).
Use when a loop needs scholarly literature — paper discovery, novelty checks, full-text snippet search, citation-graph traversal, single-paper reads, or experimental-result extraction. A shared, stdlib-only CLI (`tools/lit_search.py`) over Semantic Scholar + arXiv (plus optional OpenAlex, Perplexity Sonar, bgpt.pro), all JSON. Not a loop itself: install it alongside the loops and let any of them call it instead of vendoring their own copy. Degrades to the caller's WebSearch/WebFetch.
Configure Litestar logging with `LoggingConfig`, `queue_listener`, exception logging policy, selective stack-trace suppression, standard logging, picologging, Structlog, and custom logging config subclasses. Use when establishing or refactoring application logging behavior, request-level logs, or production-safe error logging in Litestar. Do not use for metrics/tracing instrumentation or exception-response contract design.
Build voice AI agents with LiveKit Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Covers both LiveKit Cloud and self-hosted deployments using lk CLI.
Run WP-CLI commands against any Local by Flywheel site. Use when the user says 'wp-cli', 'run wp', 'use wp-cli', 'activate plugin', 'deactivate plugin', 'flush cache', 'wp option', 'wp transient', 'wp db', 'wp eval', 'wp cron', 'wp rewrite', or any request involving WordPress CLI commands.
Build a tiered target-account list by analyzing Epiphan's best customers (pulled live from HubSpot + customer-orders MCP), deriving an ICP across firmographics/tech/growth, and scoring 100+ net-new lookalike companies 0-100. Gates every surfaced company through Golden Rules + qualify_lead so existing customers/channel/AE-owned accounts are excluded. Use when: "find companies like [customers]", "build a lookalike list", "who else looks like [account]", "lookalike target account list", "companies similar to our best customers", "expand into [vertical]", expanding into a new vertical. Not for timing signals (intent-signal-aggregator-skill) or single-contact lookups (contact-hunter-skill).
Review a LookML codebase or file to confirm its compliance with official best practices and style guidelines using the Looker CLI (looker-cli). Use this skill whenever the user asks to review, audit, check, or critique LookML code or a LookML project.
Review Chinese-to-English translations for accuracy, grammar, terminology, and consistency. Produces a structured review report with prioritized issues. Trigger when: user provides a Chinese document and its English translation for review/checking/proofreading, or mentions "翻译检查", "翻译审校", "translation review", "translation check", "proofread translation".
Microsoft 365 / Entra ID red-team attack chain — current 2026 reality. Includes AADSTS code reference, user enumeration vectors (with hardening status), Smart Lockout math, Conditional Access bypass options, ROPC + SAML SSO browser flow, and Burp/Playwright templates. Built from authorized red-team work where ROPC spray surfaced pre-existing lockouts and CA-blocked credentials, plus real-time external attacker activity correlation. Use for any M365/Entra credential attack, password spray, user enumeration, CA-bypass exploration, or active-attacker-detection scenario.
Build professional native macOS apps in Swift with SwiftUI and AppKit. Full lifecycle — build, debug, test, optimize, ship. CLI-only, no Xcode. Use when asked to: create macOS apps, build Swift apps, develop SwiftUI interfaces, fix macOS app issues, add macOS app features, or when user says “build a Mac app”, “create a Swift project”, “develop for macOS”
Implement Okta as a centralized cloud identity provider: configure SSO with AWS, Azure, and GCP, deploy phishing-resistant MFA with Okta FastPass, automate user provisioning/deprovisioning, and enforce adaptive access policies on device posture and risk signals. Use when standing up Okta SSO, rolling out FastPass MFA, automating identity lifecycle, or building risk-based conditional access for cloud environments.
Software development engine for coding. A production-grade skills system for web apps and mobile architecture, APIs, databases, web, mobile, AI, security, UX, SaaS, and ERP engineering. Encodes reusable engineering judgment through layered baseline and specialist skills to help generate secure, scalable, maintainable, high-performance software systems
Crypto market-structure research agent — 24+ indicators across derivatives, options (gamma wall, skew), on-chain (MVRV, smart money signals, DEX hot tokens), and macro sentiment. Powered by OKX CeFi CLI + OnchainOS + direct HTTP for options chain. Use this skill whenever the user asks about: derivatives data, gamma wall, options skew, funding rates, open interest, put/call ratio, MVRV, cost basis, realized price, exchange flows, CEX inflows/outflows, liquidation pressure, whale tracking, smart money flows, fear/greed index, BTC dominance, stablecoin flows, taker volume, basis/backwardation, or any request like "what does the market structure look like", "give me a macro overview", "how are derivatives positioned", "is the market overleveraged", "should I be bullish or bearish based on data", "are whales accumulating or distributing", "show me exchange flows". Also trigger when users mention specific tokens and want deeper analysis beyond simple price action — e.g., "what's going on with ETH right now", "is BTC about to move", "analyze SOL market conditions".
Identifies a product's marketing advantages and develops strategies to leverage them for growth. Use when the user wants to identify marketing advantages, asks 'what are my marketing advantages,' mentions PLG, virality, network effects, distribution strategies, or wants to know how to market based on product strengths.
Use this skill WHEN monetizing AI agents with autonomous payments, listing agents on decentralized marketplace, or deploying at scale. OUTCOMES: agents earning revenue automatically (50+ USDM/day), trustless escrow protection (95%+ success rate), marketplace discovery (50+ available agents), scalable execution (1000+ concurrent jobs). Triggers on: 'monetize my agent', 'setup agent payments', 'list on marketplace', 'A2A transactions', 'deploy agent at scale', 'MIP-003 implementation'. NOT for: general chatbots, simple REST APIs, centralized payments. Framework-agnostic (CrewAI, AutoGen, PhiData, LangGraph), self-hosted, MiCA compliant.
Process, clean, compare, and search tandem mass spectra with matchms. Use for MS/MS file I/O, metadata harmonization, peak filtering, spectral similarity, library matching, score matrices, and molecular-similarity networks. Use pyopenms instead for LC-MS feature detection or proteomics pipelines.
Generate, verify, refine, and accelerate C/C++ or CUDA code from MATLAB with MATLAB Coder, Embedded Coder, GPU Coder, or MATLAB Test. Also covers writing codegen-ready MATLAB code: language constraints, coder.* directives, and optimization patterns. Triggers on: codegen, MEX, deploy MATLAB as C/C++, GPU Coder, coder.screener, coder.config, coder.gpuConfig, coder.typeof, coder.runTest, matlabtest.coder.TestCase, SIL, embedded config, no dynamic memory, EnableMexProfiling, coder.timeit, coder.perfCompare, %#codegen, writing codegen-ready MATLAB, code generation readiness, coder.varsize, coder.unroll, coder.noImplicitExpansionInFunction, coder.ceval, coder.inline, coder.extrinsic, coder.const, coder.classSignature, class codegen limitations, temporal types codegen, DMA-off, stack-only, host-target InstructionSetExtensions, SIMDAcceleration, OptimizeReductions, host SIMD tuning, host OpenMP, codegen performance
MatrixScan Batch (MatrixScan, BarcodeBatch, legacy BarcodeTracking) — tracking and scanning multiple barcodes at once in iOS (Swift, UIKit/SwiftUI) projects. Use for integration, settings and symbologies, tracked-barcode handling, basic/advanced overlay customization, lifecycle, or troubleshooting.
Catppuccin-themed live-reloading Markdown viewer with multi-tab support, margin annotations, sidebar TOC, and Chrome --app mode. This skill should be used when previewing .md files in a polished editorial reader, adding AI or human annotations to documents, or launching a collaborative document review session.
Build automated pipelines for medical imaging data: format conversion (DICOM to NIfTI, PNG, HDF5), batch processing, ML dataset preparation, research data export, and imaging ETL workflows. Use when converting DICOM to other formats, preparing imaging datasets for machine learning, building research data pipelines, batch processing medical images, extracting imaging features, or automating imaging workflows.
Review a solution before approving it, like a GitHub changes tab: show a file tree of red and green pseudo-code for inline comments, then respond with Approve, Commented, or Rejected. Use when the user wants to see what would change, a git-like diff, or the PR as if it were ready.
Solana memecoin launch strategy and execution. Use when planning token launches, designing tokenomics, building pre-launch hype, deploying on pump.fun/Raydium, or optimizing launch mechanics. Covers: token creation, bonding curves, liquidity strategy, community building, anti-rug best practices.
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.