Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Create outcome-based roadmaps using Now/Next/Later instead of Gantt charts. Use when asked to create a roadmap, plan quarterly, organize milestones, or figure out what to build over the next few months. Anti-date, anti-feature-list, pro-outcome.
Run technical quality checks on an existing deck. Finds and fixes font size violations, shape overlaps, contrast issues, missing sources, and layout compliance problems. Use when the user says “check the deck for issues”, “run QA”, “lint the slides”, “are there any formatting problems”, “audit the presentation”, or wants to verify visual quality before sharing.
Rebuild an approved source HTML application as a real, high-fidelity UI in the target repository. Use for source-to-app design tasks requiring interactive source discovery, authored routes and components, local UI behavior, responsive/theme adaptation, and paired Playwright evidence.
Re-inject Synapse A2A initial instructions after context has been cleared. Use this skill when the agent has lost its identity, A2A communication protocol, or configuration after /clear or context reset, when synapse send/reply commands stop working, or when the agent no longer recognizes its SYNAPSE_AGENT_ID. Triggered by /synapse-reinst command.
Build, review, and audit technical docs and agent instruction files. Applies Simplified Technical English (ASD-STE100) to prose, scales to huge docs trees with sharded audits and ledgers, and runs as Claude Workflows or sub-agents when available.
Automate TikTok + Instagram slideshow marketing for any app or product. Researches competitors, generates AI images, adds text overlays, posts via Upload-Post (multi-platform in one API call), tracks analytics, and iterates on what works. Use when setting up TikTok marketing automation, creating slideshow posts, analyzing post performance, optimizing app marketing funnels, or when a user mentions TikTok growth, slideshow ads, or social media marketing for their app. Covers competitor research (browser-based), image generation, text overlays, multi-platform posting (Upload-Post API — TikTok + Instagram + more simultaneously), analytics tracking, hook testing, CTA optimization, conversion tracking with RevenueCat, and a full feedback loop that adjusts hooks and CTAs based on views vs conversions.
Translate free-text tumor descriptions to OncoTree codes and resolve cancer subtypes/tissue hierarchy. Cross-references UMLS/NCI vocabularies. Use for standardizing cancer-type nomenclature in EHR free-text, building cohorts in OncoKB or GDC, mapping tumor-board notes to ontology codes, and ensuring consistent terminology across cancer-genomics pipelines.
HLA gene-family analysis and MHC-peptide binding for transplant compatibility, vaccine epitope coverage, and cancer immunotherapy. Uses IMGT (HLA polymorphism), IEDB (epitope-MHC binding), UniProt (annotation), DGIdb (druggability). Use for HLA typing/imputation review, vaccine HLA coverage, and immunotherapy prediction biomarkers (HLA-LOH, neoantigen presentation).
Use this skill when writing, designing, or optimizing Trigger.dev background tasks and workflows. This includes creating reliable async tasks, implementing AI workflows, setting up scheduled jobs, structuring complex task hierarchies with subtasks, configuring build extensions for tools like ffmpeg or Puppeteer/Playwright, and handling task schemas with Zod validation.
TypeScript strict mode patterns including schema-first development, branded types, type vs interface guidance, and tsconfig strict flags. Use when writing TypeScript code, defining types or schemas, or reviewing type safety. For immutability and pure function patterns, see the functional skill.
Orchestrates reliable multi-step workflows with the Upwork MCP server for clients, freelancers, and agencies. Use when a task requires selecting an account, discovering tools, chaining reads and writes, handling drafts and confirmation, paginating results, uploading files, or recovering from Upwork tool errors.
دليل شامل لكتابة تجربة المستخدم (UX Writing) والتصميم المحتوى العربي. Use when writing Arabic content for apps, websites, error messages, buttons, labels, notifications, empty states, confirmation dialogs, success messages, form fields, help text, and any user-facing Arabic text. Also use for content strategy, copywriting, microcopy, and Arabic tone/voice guidelines.
Turn wiki golden pages into a CI-blocking eval suite with a cheap→expensive assertion cascade plus a committed regression baseline. Goldens are md files under llmwiki/wiki/sources/evals/ with YAML frontmatter (input, expected, optional rubric, asserts). The engine runs deterministic tier-1 asserts (equals/contains/regex/is-json/is-sql-ish) in pure code, an optional tier-2 similarity, and reports tier-3 (LLM-rubric judge) as the quarantined adapter — never calling a model. Candidate outputs come from --outputs outputs.json so the suite is fully runnable without any model. Trigger when the user says "wikieval", "eval suite for the wiki", "regression gate for goldens", "assertion cascade", "block CI on eval drop", or invokes /wikieval.
Generate on-brand ad creatives — visuals + copy — for Google, Meta (Facebook / Instagram), and other paid platforms via the Hyper MCP. Extracts brand identity from a website, writes ad copy variants, and produces brand-consistent images using reference-based image generation. Use when the user asks for ad creative, ad copy variants, RSA headlines, Meta ad creative, display ads, carousel ads, or A/B test variants.
Fit a Datadog LLM-Obs evaluator to human labels. Takes an annotation queue, works out where in the trace the labelled property actually lives, drafts an LLM-judge that predicts the human label, scores that judge against the already-labelled rows with a metric agreed with the user, then hill-climbs it — inspect the errors, make one focused change, re-score, keep it only if it beats the best — for a bounded number of iterations, and finally publishes the winner to Datadog as a DISABLED evaluator (not a Datadog draft — a real evaluator with `enabled: false`). Use when the user says "build an eval from my annotations", "build an evaluator from the annotation queue", "turn my annotations into an evaluator", "learn an evaluator from my labels", "fit a judge to the annotation queue", "auto-label", "auto labelling", "automate this annotation queue", "scale up my human labels", or wants the rest of a queue graded the way the humans graded the first rows. Needs an annotation queue with at least two classes present in the human labels (e.g. one true and one false for a boolean).
Generate professional AI product photography and commercial images. Models: FLUX, Imagen 3, Grok, Seedream for product shots, lifestyle images, mockups. Capabilities: studio lighting, lifestyle scenes, packaging, e-commerce photos. Use for: e-commerce, Amazon listings, Shopify, marketing, advertising, mockups. Triggers: product photography, product shot, commercial photography, e-commerce images, amazon product photo, shopify images, product mockup, studio product shot, lifestyle product image, advertising photo, packshot, product render, product image ai
Expert iOS App Store submission and approval system. 9 specialized agents provide senior App Review Team-level expertise across compliance, design, privacy, monetization, metadata, technical requirements, timing, rejection recovery, and learning. Triggers on keywords like app store, iOS submission, apple review, app rejection, aso, privacy manifest, privacy labels, ATT, iap, in-app purchase, subscription, storekit, review guidelines, HIG, testflight, app store connect.
Use when implementing Liquid Glass effects, reviewing UI for Liquid Glass adoption, debugging visual artifacts, optimizing performance, or requesting expert review of Liquid Glass implementation - provides comprehensive design principles, API patterns, and troubleshooting guidance from WWDC 2025. Includes design review pressure handling and professional push-back frameworks
Expert knowledge for Azure AI Search development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when configuring indexes, vector/semantic search, indexers and skillsets, RBAC/ACL security, or deployment automation, and other Azure AI Search-related development tasks. Not for Azure Cosmos DB (use azure-cosmos-db), Azure Data Explorer (use azure-data-explorer), Azure SQL Database (use azure-sql-database), or Azure Synapse Analytics (use azure-synapse-analytics).
Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-commerce, transparent PNGs, photo editing. Triggers: remove background, background removal, remove bg, transparent background, cut out image, background remover, rembg, product photo editing, cutout, transparent png, bg removal, photo cutout
Comprehensive book writing assistant and memory maintainer. Use when tasked with: - Writing books, novels, fiction, non-fiction, or any long-form manuscript - Creating characters, outlining chapters, building worlds - Drafting, reviewing, or revising chapters - Writing children's books, picture books, rhyming stories, or songs for ages 2–9 - "initialize memory bank", "update memory bank", "start a new book", "let's start building" - Planning book structure (MVB, short book, full book, literary novel, picture book) - Checking continuity or consistency across chapters - Any request involving book chapters, manuscripts, or story development Provides specialized guidelines to write like a master author while maintaining an automated book memory bank to preserve context across sessions. Includes children's book writing, parallel chapter workflows, and multi-genre support.
Foundation skill for working with Box. Use this whenever the user mentions Box — authentication and MCP/CLI setup, choosing between MCP/CLI/REST, rate-limit and pacing guidance, troubleshooting Box errors (401/403/404/409/429), or working with Box MCP tools (files, search, collaboration, AI, hubs, doc gen). Route general Box requests to the right reference. For explicit CLI requests, use box-cli when installed.
Inspect public page links or a supplied crawl report for confirmed broken links and redirect issues. Report source URLs, evidence, and coverage limits; no crawler is bundled. Use for broken-link checks, 404 diagnosis, link audits, or website health reviews.
Maps and documents codebases of any size by orchestrating parallel subagents. Creates docs/CODEBASE_MAP.md with architecture, file purposes, dependencies, and navigation guides. Updates CLAUDE.md with a summary. Use when the user says "map this codebase", "cartographer", "/cartographer", "create codebase map", "document the architecture", "understand this codebase", or when onboarding to a new project. Automatically detects if map exists and updates only changed sections.
Troubleshoot and resolve common issues with the ClickHouse Node.js client (@clickhouse/client). Use this skill whenever a user reports errors, unexpected behavior, or configuration questions involving the Node.js client specifically — including socket hang-up errors, Keep-Alive problems, stream handling issues, data type mismatches, read-only user restrictions, proxy/TLS setup problems, or long-running query timeouts. Trigger even when the user hasn't precisely named the issue; vague symptoms like "my inserts keep failing" or "connection drops randomly" in a Node.js context are strong signals to use this skill. Do NOT use for browser/Web client issues.
When a founder needs to write cold emails or LinkedIn messages to prospects, partners, or investors. Activate when the user mentions cold email, outbound, prospecting, LinkedIn outreach, or needs help getting replies from people who don't know them
End-to-end Proteina-Complexa design pipeline driver. Reach for this skill whenever the user wants to "design a binder", "design binders for X", "run complexa design", "de novo binder", "PDL1 binder", "TrkA binder", "design proteins for target", "protein binder design", "ligand binder", "design a small-molecule binder", "ATP-binding protein", "AME motif scaffolding", "scaffold a motif near a ligand", "motif + ligand design", "enzyme scaffolding", "flow matching protein design", "beam-search binder", "FK steering", "MCTS protein design", "refold with AF2", "refold with RF3", or wants success rates, interface pAE, scRMSD, or FoldSeek diversity from a single command. This is the scientific anchor of the skill set: it drives `complexa design <pipeline>` from target picking to manifest emission and tells the user how many designs passed
Comprehensive customer success and retention expertise combining onboarding, health scoring, churn prevention, retention strategies, and LTV maximization. Use when designing customer onboarding flows, reducing churn, building health scores, creating retention systems, designing upsells, or improving customer lifetime value. Covers proactive engagement, cancel flows, dunning, re-engagement, and the full customer lifecycle.
Use this skill for any Yandex DataLens automation task through the Python package `datalens-sdk`. Trigger on: DataLens, datalens, даталенс, chart, чарт, график, dashboard, дашборд, dataset, датасет, connection, подключение, workbook, воркбук, collection, коллекция, wizard chart, QL chart, editor chart, BI automation, автоматизация DataLens, "create a dashboard", "построй дашборд", "создай чарт", "export dataset", or "clone dashboard"; entity ids such as dataset_id, chart_id, dashboard_id, or workbook_id; and requests to create, update, inspect, import, export, copy, or diagnose DataLens objects with code. NOT for: business questions about metric values; viewing or screenshotting the DataLens web UI; embedding or iframes; raw SQL/YQL analysis that does not manage DataLens entities; raw HTTP API calls; standalone HTML pages or reports, except publishing or managing them through this SDK
Root-causes AI agent failures from MLflow traces without requiring a code change, regression suite, scorer, or evaluation run. Use when the user asks to debug, investigate, explain, or determine why an agent produced an output. Prefer an existing matching trace; reproduce only when no usable trace exists.
Expert product demonstration specialist for SaaS and B2B software. Use when preparing demos, structuring demo presentations, tailoring to stakeholders, handling objections during demos, managing live vs sandbox environments, or improving demo conversion rates. Covers remote and in-person demos, multi-stakeholder presentations, technical deep-dives, and executive briefings.
Trigger when the user provides dream-related text, a diary excerpt, or a spoken account of a dream and wants to generate a video. Trigger phrases include “dreamed of,” “dreamt about,” “I had a dream,” “dream material,” “generate a video for me,” “turn it into a video,” and “dream to video.” Also applies when the user pastes a dream description and expects a video file. This skill converts the text into video prompts, submits them to the 即梦 platform for generation, and downloads the video file.
Register AI agents on Ethereum mainnet using ERC-8004 (Trustless Agents). Use when the user wants to register their agent identity on-chain, create an agent profile, claim an agent NFT, set up agent reputation, or make their agent discoverable. Handles bridging ETH to mainnet, IPFS upload, and on-chain registration.
Measures whether Claude uses an MCP server's tools correctly—tests tool selection accuracy, analyzes schema quality, and iteratively optimizes descriptions. Triggers when the user asks to evaluate MCP tools, test tool selection, improve tool descriptions, check MCP schema quality, or evaluate their MCP server. Companion to build-mcp-server.
Identify and analyze A-share company events that may create pricing disparities, including mergers and restructurings, asset injections, buybacks and share purchases, management changes, and index adjustments. Use this skill when users ask about merger and restructuring opportunities, asset injections, share buyback analysis, state-owned enterprise reform, index-adjustment trading, special-situation investing, or event-driven strategies.
Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the Figma screen to match code', 'convert this modal/dialog/drawer/panel to Figma'. This is the preferred workflow skill whenever the user wants to build or update a full page, modal, dialog, drawer, sidebar, panel, or any composed multi-section view in Figma from code or a description. Discovers design system components, variables, and styles from Code Connect files, existing screens, and library search, then imports them and assembles views incrementally section-by-section using design system tokens instead of hardcoded values.
Transcribe audio or video files into timestamped Markdown files using the local FunASR service. Supports common formats such as mp4, mov, mp3, wav, and m4a. Use this skill when the user needs speech-to-text, meeting notes, video subtitles, or podcast transcription.
Use when you need a deep, implementation-ready engineering plan for a code change — built from GitNexus graph intelligence, statement-level PDG analysis, and targeted source verification, compact enough for an implementation agent to start without re-investigating. Also strengthens existing plans via Deepen mode. Examples: "/gitnexus-plan Add retry support to the ingestion pipeline", "/gitnexus-plan deepen docs/plans/<plan>.md", "plan this change using the knowledge graph".
Expert blueprint for sports games (FIFA, NBA 2K, Rocket League, Tony Hawk) covering physics-based ball interaction, team AI formations, contextual input, and match umpire/score authority. Broadcast framing routes to godot-camera-systems. Use when building soccer, basketball, hockey, racing sports, or arcade sports games. Keywords ball physics, magnus effect, formation AI, team tactics, contextual controls, steering behaviors.
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.