Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
Implement Litestar authentication with custom authentication middleware, built-in security backends, JWT and session flows, route inclusion and exclusion rules, and typed auth context on `Request` / `ASGIConnection`. Use when establishing identity, issuing or validating credentials, or attaching authenticated user context in Litestar. Do not use for generic request parsing, broad security audits, or unrelated transport concerns.
Design and apply Litestar middleware for cross-cutting concerns such as CORS, CSRF, allowed-host checks, compression, rate limiting, logging, sessions, request enrichment, policy enforcement, and custom ASGI pipeline control. Use when behavior must wrap broad route sets consistently across the ASGI stack. Do not use for route-specific business rules, simple response mutation better handled by lifecycle hooks, or auth/guard policy work that belongs in security-focused skills.
PR reviewer with one binary verdict, where an approval is just 🦎. Sizes the review to the diff, from a quick pass to cross-model, checks claims against tickets, posts inline fixes; --local reviews a branch with no PR. Use when asked to "lizard" a PR or branch, or for a "lizard sweep".
Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) in plain markdown. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki health, auditing article claims against their sources, critiquing a wiki source's reasoning, superseding stale knowledge, 'add to wiki', 'LLM wiki' or 'Karpathy wiki'.
Build and query a local Markdown knowledge base ("vault"). TWO functions — (1) CONVERT raw files (PDF, Word/docx, PowerPoint/pptx, Excel/xlsx, csv/tsv, images, html, md/txt, json/yaml/code, audio/video) into clean Markdown with retrieval-friendly frontmatter; local-first (pandoc / python-pptx / openpyxl / pymupdf4llm / whisper), with cloud OCR (MinerU) only as a fallback. (2) ANSWER questions over the resulting vault with retrieval discipline — self-monitor coverage, flag missing/lossy content, and propose Maps-of-Content (MOCs). Triggers: "build/sync my local knowledge base", "convert these files to markdown for AI", "整理我的资料库", "把文件转成 md 给 AI 读", "本地知识库", "读我的本地 vault 回答", "这个主题我的资料里怎么说". Not for: one-off web research, or files that are already in a single doc you can read directly.
Lumen — project knowledge keeper. Trigger on any /lumen command, on mentions of "lumen", "knowledge base", "wiki", "ADR", "document the project", on broad architectural questions about a codebase ("how does X work", "why did we choose Y"), or when the user pastes a transcript/spec to capture for future sessions.
Skill for generating e-commerce product detail pages in the lyt series. When the user invokes this skill and uploads product images, packaging images, specification images, product information, competitor detail pages, or visual references, generate the information structure, slogan, screen-by-screen copy, visual brief, and image-generation prompts from scratch; when tools are available, also generate individual screen images and a complete long image. During the initial information gathering, let the user choose not to use a slogan, provide existing copy, or have the Agent generate it. Use only facts visible in images and information confirmed by the user; do not invent features, materials, effects, specifications, certifications, reviews, or sales based on appearance. For TikTok Shop and cross-border e-commerce product detail pages; not for diagnosing existing pages, deciding whether a product is worth pursuing, reverse-engineering prompts from a single reference image, or summarizing competitor main images. Trigger with: /lyt-detail-page, /详情页生成, “generate a detail page from product images”, “help me create a product detail page from scratch”, “use this page as a reference to create a detail page for my product”.
A skill for reverse-engineering image prompts and replacing products in lyt-series e-commerce images. Use when the user explicitly invokes this skill and uploads a product image, product hero image, commercial ad, product scene image, selling-point infographic, or 3D product render. Reconstruct an actionable image-generation prompt from the reference image's visible subject, composition, scene, lighting, materials, colors, and commercial expression. The user can also upload their own product image to replace the reference product using their product's appearance, structure, packaging, and brand information, combining these into a new prompt. If the target style is unspecified, ask about it first; if specified, generate directly. Handles only prompt reconstruction and product replacement for a single commercial visual. It does not create complete product detail pages, diagnose product-page conversion, summarize commonalities across batches of competitor hero images, generate images directly, or claim to recover the original prompt, model, seed, or hidden parameters. Triggers: /lyt-image-prompt, /图片提示词, /反推提示词, “根据这张图反推提示词”, “把这张商品图拆成提示词”, “把我的产品合并到这个提示词里”, “用我的产品替换参考图产品”
A lyt-series skill for shooting short e-commerce product videos. Use when the user already has a specific product, product images, a product link, product information, confirmed selling points, or existing product copy and wants a ready-to-shoot TikTok Shop or cross-border e-commerce short-video script, storyboard, UGC script, demo/comparison/review/scene script, ad creative script, or influencer sample-seeding script. It can also turn existing product copy into shootable storyboards or generate target-market-language versions with Chinese back-translations. Not for selecting products from scratch, judging whether a product is viable, diagnosing published video metrics, directly generating or editing videos, or handling non-product personal IP content. Triggers: /lyt-video-script, /产品视频脚本, /拍摄脚本, /商品短视频脚本, “这个产品怎么拍”, “根据这个产品写一份脚本”
ACTIVATE when evaluating acquisition targets, conducting M&A due diligence, planning integration strategy, analyzing synergies, preparing sale materials, assessing culture fit, valuing targets, creating merger checklists, or managing M&A transactions. Critical for executives involved in buy-side or sell-side M&A, from initial target evaluation through post-acquisition integration.
Manage up effectively and produce a Managing Up Operating System Pack (manager profile, comms cadence, weekly updates, escalation/ask plan, expectation & boundary script, and exec-ready decision/tradeoff memo). Use for managing up, managing your boss, working with your manager, exec communication, stakeholder updates, and escalation. Category: Leadership.
Demo manufacturing knowledge base for Taylored Systems. Shows how tribal knowledge gets captured and made queryable. USE WHEN user wants a manufacturing demo OR demonstrating to potential clients OR asks about CNC setup, machine error codes, quality inspection, startup procedures, troubleshooting, or safety OR says 'manufacturing demo', 'show me an example', 'how does it work', 'Taylored Systems demo'.
Guide medical manuscript writing with argumentation-driven structure, section-by-section best practices, and sentence-level craft. Use when writing, revising, or reviewing original research manuscripts for biomedical journals, or when a draft reads flat or reviewer comments cite structural issues.
Use on a brownfield codebase that needs a CONTEXT.md hierarchy. After intake, reverse-engineers the system and component architecture from existing code to produce root and component CONTEXT.md files. Use when that context would materially help; architect and triage do not require it. Also use when CONTEXT.md files are severely out of date.
Add concise, useful JSDoc where IDE hover help or a generated API reference needs a non-obvious contract. Use for exported JavaScript or TypeScript APIs, components, hooks, classes, complex types, or package publishing. Not for internal code, narrating comments, prose docs or behaviour changes
Diagnose and improve marketplace liquidity (match rate/fill rate, time-to-match, reliability) by segment. Produces a Marketplace Liquidity Management Pack: liquidity definition + metric tree, fragmentation map, segment scorecard, supply/demand bottleneck diagnosis, experiment backlog, measurement plan, and operating cadence. Use for Growth teams running two-sided marketplaces.
Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when - (1) building agents that use tools and loop until task complete, (2) creating multi-step workflows with conditional branches, (3) adding persistence/memory across turns with checkpointers, (4) implementing human approval with interrupt(), (5) debugging via time-travel or LangSmith. Covers StateGraph, nodes, edges, add_conditional_edges, MessagesState, thread_id, Command objects, and ToolMessage handling. Examples include chatbots, calculator agents, and structured workflows.
Discover OPC UA servers and create client connections in MATLAB using opcuaserverinfo, opcua, connect, setSecurityModel, and certificate trust functions. Use when discovering OPC UA servers on the network, connecting to OPC UA servers, authenticating with username/password or certificates, configuring security modes, handling certificate trust errors, fixing hostname mismatch warnings, troubleshooting connection failures or empty discovery results, or inspecting an OPC UA certificate (.der or .pem) for compliance issues. Trigger on: opcuaserverinfo, OPC UA discovery, find OPC UA servers, LDS setup, opcua, opc.ua.Client, connect OPC UA, OPC UA client, OPC UA security, OPC UA certificate trust, OPC UA certificate inspection, setSecurityModel, opc.ua.trustServerCertificate, opc.ua.exportClientCertificate, Industrial Communication Toolbox, OPC UA server connection, OPC UA server discovery.
Create an experiment for the MATLAB Experiment Manager app from user code, script, or problem description. TRIGGER when: user asks to create an experiment from a script/function, wants to sweep parameters or hyperparameters, asks to compare configurations, or describes a problem suitable for experimentation. DO NOT TRIGGER when: user is debugging an existing experiment, wants to run/resume trials, or already has a working experiment set up.
Use when driving mc, the MinIO AIStor command-line client for S3-compatible object storage, from a shell — connecting to a server with an alias, listing/copying/moving/removing objects and buckets, or configuring versioning, replication, lifecycle, encryption, policies, events, cluster administration, and AIStor Tables. Covers how an agent should authenticate non-interactively, get machine-readable JSON-lines output, build ALIAS/BUCKET/PREFIX paths, discover any command's exact flags, and stay clear of the irreversible destructive operations
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Plan and execute earned media outreach and journalist relationships by producing a Media Relations Pack (newsworthiness brief, media list, exclusive/embargo plan, pitch templates, outreach tracker, interview prep, press materials checklist). Use for PR, media outreach, press pitch, embargo, exclusive, press release, and journalist pitching. Category: Marketing.
Prepare structured briefings for meetings with legal relevance and track resulting action items. Use when preparing for contract negotiations, board meetings, compliance reviews, or any meeting where legal context, background research, or action tracking is needed.
File-scan review feature of the AI personal memory system. Scan files modified this week in the Obsidian vault (excluding the AI_MEMORY directory) and identify potentially important events and decisions. Use cases: (1) when the user says "file scan", "check this week's files", or "scan file changes"; (2) before supplementing L1 records during a weekly review; (3) when the user wants to review this week's activity in Obsidian. The skill lists the modified files, asks the user which ones need to be recorded in L1, and assists with the recording.
Monthly review feature of the AI personal memory system. Analyze this month's L2 behavior-layer updates, distill thinking patterns into the L3 cognition layer, and check whether the L4 core layer needs recalibration. Use cases: (1) when the user says "monthly review"; (2) for regular reviews at the end of each month; (3) when you need to distill a cognitive framework from behavior patterns. The skill analyzes whether multiple behaviors point to the same thinking principle, tries to distill them to L3, and guides the user to reflect on the L4 core layer.
Weekly review feature of the AI personal memory system. Analyze this week's L1 situational-layer records, identify recurring patterns, and distill them into the L2 behavior layer. Use cases: (1) when the user says "weekly review"; (2) for regular reviews each week; (3) when you need to distill behavior patterns from daily records. The skill automatically counts recurring behaviors (3+ times), generates a candidate list, and updates the L2 behavior layer after user confirmation.
Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.
Calculate and diagnose Overall Equipment Effectiveness (OEE) by decomposing into Availability, Performance, and Quality rates. Use this skill when the user needs to measure production line efficiency, identify equipment losses, benchmark manufacturing performance, or justify capital investment — even if they say 'why is our output low', 'machine utilization report', 'production efficiency', or 'how much capacity are we losing'.
Safe migration workflows for EF Core database migrations, .NET version upgrades, and NuGet dependency updates. Includes rollback strategies and verification steps. Load when: "migration", "add migration", "ef migration", "update database", "upgrade nuget", "update packages", "dependency update", "version upgrade".
Refactor a growing WeChat Mini Program whose top-level navigation has become scattered across tabs such as home, profile, inbox, integrations, or settings into a clearer hub or center structure. Use when Codex needs to regroup top-level tabs, separate high-frequency action flows from low-frequency settings, define internal hub sections, or migrate detailed pages without collapsing everything into one long page.
Use host-side WeChat DevTools automation to inspect GUI-only runtime and interaction failures that do not show up in CLI `preview`. Trigger when page entry, taps, websocket-based DevTools automation, or run-directory evidence such as `report.json` and `trace.log` are needed to separate repo bugs from IDE session problems, local service blockers, or remaining visual-only issues.
Run a scenario-based DevOps, SRE, Cloud, or Platform Engineering mock interview, then deliver a brutally honest analysis and a tailored prep plan. Pulls questions configured by topic (Kubernetes, AWS, Docker, Terraform, CI/CD, Linux, Monitoring/Observability, System Design, Networking, Security, mixed), difficulty (junior 0-2y / mid 2-5y / senior 5-8y / staff 8+y), and target company tier (Service like TCS/Infosys/Wipro/Capgemini, Product like Razorpay/Zerodha/Swiggy/PhonePe/Atlassian, or MANG/FAANG like Meta/Apple/Netflix/Google/Amazon/Microsoft). Conducts the interview question-by-question in interviewer voice (no hints, no mid-interview praise), then flips to coach mode for per-question analysis, pattern detection across the session, a tier-by-tier verdict, and a 7-day prep plan. Trigger AGGRESSIVELY on: /mock-interview, "mock interview", "interview prep", "interview practice", "DevOps interview", "SRE interview", "cloud interview", "Kubernetes interview", "AWS interview", "scenario question", "system design interview", "interview me", "test me", "quiz me on K8s/AWS/etc", "help me prepare for an interview", or anytime the user expresses they have an upcoming DevOps/SRE/Cloud/Platform/Infra interview, even if they don't use the word "mock" — interview readiness is the trigger, not the exact phrasing.
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.