Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
MLIR skill for multi-level intermediate representation. Use when writing custom dialects, defining ops with ODS, writing lowering passes, running mlir-opt, or building ML compilers with Torch-MLIR/IREE. Activates on queries about MLIR, dialect, ODS, mlir-opt, linalg, lowering pass, or Torch-MLIR.
NocoBase 2 only; never use in a NocoBase 3 project. Task-driven ACL governance through nb CLI for role lifecycle, global role mode, permission policy, Portal entry access, user-role membership, and risk assessment. Use when users describe business permission outcomes instead of raw command arguments, including which roles may enter a Portal.
Use when making or fixing Roblox visual effects or game audio: ParticleEmitter, Beam, Trail, flipbook sprite sheets, slash, hit, impact, explosion, fireball, aura or projectile VFX; effects only one player sees, effects that lag or pile up, particles invisible, popping or too bright; the Audio API (AudioPlayer, Wire, AudioEmitter, AudioListener, AudioDeviceOutput, effects), "no sound", "3D sound not working", music, ducking, footsteps, SoundGroup volumes; or importing Scenario-generated sound effects, music, voice or VFX sheets into a Roblox game.
Recover lost Claude Code session context by merging duplicate project directories. Finds session/memory dirs under ~/.claude/projects/ that point at the same logical project from different cwd-encoded paths (e.g. /mnt/work/foo vs ~/Projects/foo cwd produces two separate namespaces). Unifies memory into the canonical dir, archives orphaned jsonl transcripts, and captures the lesson as a feedback memory so the split doesn't repeat. Use when: 'merge sessions', 'recover lost context', 'fix duplicate session dirs', 'session memory split', 'memory dir is empty but I added things', 'two project dirs', 'recover legacy memories from before a folder move', 'stale orphan memory namespace', or any time you find a populated memory dir at the "wrong" path and an empty one at the canonical path.
Build, integrate, review, migrate to, and answer how-to questions for Stream Chat, Video, and Feeds in Flutter / Dart apps. Supports stream_chat_flutter (pre-built Chat UI), stream_chat_flutter_core (custom Chat UI), stream_video_flutter (calls, ringing, audio rooms, livestreaming), and stream_feeds (Activity Feeds v3, no pre-built UI). Routes each request to the exact official Flutter docs page, fetches it live, and applies it - with a curated setup flow, a push / ringing runbook, design-matching and custom-UI runbooks, a Sendbird -> Stream Chat migration runbook, a read-only integration review before going live (including livestream launches), and Flutter-specific pitfalls.
Implement Syncfusion Blazor RangeNavigator for interactive data range selection and chart navigation. Trigger when users mention range selector, range navigator, SfRangeNavigator, Syncfusion.Blazor.Charts.RangeNavigator, time-series filtering, date range picker for charts, data zooming, slider navigation, thumb-based range selection, period selector, or chart data range selection for large data
Design a staged profit-taking plan, rules for moving stops up to break-even, and conditions for continuing to hold profitable positions, balancing realized gains with retaining trend profits. For managing profitable positions, taking profits on strong stocks, and planning swing-trade exits.
Use simplicity-cli to autofill PDF forms from local files or URLs, monitor async task execution, and download filled PDFs. Use when a user asks to fill forms with AI, run form autofill from context/source documents, check task status, wait for completion, or debug CLI workflow/auth behavior.
Audits macOS AppKit interfaces for VoiceOver, keyboard navigation, focus order, and semantic structure issues. Use when reviewing or fixing AppKit accessibility — returns P0/P1/P2 findings with patch-ready fixes and manual verification steps.
Use this skill when the user asks what tax filings they need, whether they must file a tax return (確定申告), asks about consumption tax obligations (消費税), or needs help understanding their filing requirements. Trigger phrases include: "確定申告が必要か", "申告の種類", "消費税の届出", "課税事業者かどうか", "何を申告すればいい", "申告要否", "税金の申告", "住民税の申告".
This skill should be used when building the async job workflow, implementing polling loops, handling job status transitions, processing rich data, managing conversation threads, or understanding the full submit-poll-complete lifecycle of the Bankr Agent API.
Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions. Covers extension architecture, manifest v3, content scripts, popup UIs, monetization strategies, and Chrome Web Store publishing. Use when: browser extension, chrome extension, firefox addon, extension, manifest v3.
Add headless Chrome automation with Puppeteer/Playwright on Cloudflare Workers. Use when: taking screenshots, generating PDFs, web scraping, crawling sites, browser automation, or troubleshooting XPath errors, browser timeouts, binding not passed errors, session limits, page.evaluate __name errors, or waitForSelector timeout issues.
Build durable workflows with Cloudflare Workflows (GA April 2025). Features step.do, step.sleep, waitForEvent, Vitest testing, automatic retries, and state persistence for long-running tasks. Prevents 12 documented errors. Use when: creating workflows, implementing retries, or troubleshooting NonRetryableError, I/O context, serialization errors, waitForEvent timeouts, getPlatformProxy failures.
Expert copywriter and copy editor combining David Ogilvy's clarity, Ann Handley's warmth, and modern conversion science. Full copy lifecycle: writing new copy and editing existing copy. Grounded in positioning-first thinking, voice-of-customer research, and the Seven Sweeps editing framework. Use when writing or editing any copy: copywriting, write copy, headlines, taglines, email copy, ad copy, landing page copy, product copy, UX writing, CTAs, value proposition, microcopy, sales copy, conversion copy, SaaS copy, startup copy, positioning, messaging, voice-of-customer, landing page, copy editing, edit copy, review copy, proofread, polish copy, tighten copy, copy sweep, copy feedback, sharpen messaging
Create or refine a creative brief that bridges discovery and execution. Use this skill whenever the user is starting a new project, kicking off a website, beginning a brand build or redesign, briefing a designer or developer or AI agent, or trying to align a team before building. Triggers on creative brief, design brief, brand brief, project kickoff, kicking off, briefing the team, project intake, design direction, brief the designer, brief the dev, where do we start, how do we start, write a brief, project overview, scope this project, align on direction. Also triggers when the user has a vague idea and needs to make it concrete enough to hand off, even if they do not say 'brief' explicitly.
Surface what customers are actually saying about a topic across call transcripts and email across your accounts, with direct attributed quotes. Use when the user asks “what are customers saying about [topic]”, “pull quotes on [objection/feature/competitor]”, “voice of customer on [X]”, or “what's coming up in calls”.
Train ML models on Databricks. Use for: classification/regression/deep-learning (XGBoost, scikit-learn, LightGBM, PyTorch) with Optuna, @prod/@challenger aliases, batch scoring (spark_udf for plain models, fe.score_batch for feature-store-backed), custom PyFunc, custom ResponsesAgent (LangGraph + UC Function/Vector Search); UC feature tables + FeatureLookup + point-in-time joins + Lakebase online store; declarative Feature Views (create_feature, DeltaTableSource, RollingWindow/SlidingWindow/TumblingWindow, materialize_features, streaming Kafka features). NOT for: endpoint ops (databricks-model-serving), MLflow evaluation (databricks-mlflow-evaluation).
MLflow GenAI evaluation and agent improvement on Databricks. Use when running mlflow.genai.evaluate(), building scorers or datasets, aligning judges with MemAlign, optimizing prompts, or monitoring production quality.
Implement Datadog monitoring and APM for infrastructure and applications. Configure agents, create dashboards, set up alerts, and implement distributed tracing. Use when implementing enterprise monitoring, APM, or unified observability platforms
Unified Aura design guidance — components and tokens, page layouts, UX copy, forms and async feedback, and accessibility. Use when building or styling customer-facing UI, structuring pages, writing interface text, or implementing validation, loading, errors, and a11y.
Export PostHog events, persons, sessions, or the results of a HogQL query on demand and download the resulting files. Use when the user asks to download/export raw PostHog data, export HogQL query results, create a one-off file export, fetch a Parquet or JSONLines export, or use the file_download_batch_exports API. Covers starting the export with MCP, polling completion, and downloading via the existing REST redirect endpoint.
Generate new images from text prompts using EachLabs AI models. Supports text-to-image with multiple model families including Flux, GPT Image, Gemini, Imagen, Seedream, and more. Use when the user wants to create new images from text. For editing existing images, see eachlabs-image-edit.
Web page and website scraping with Firecrawl API. Use this skill when scraping web articles, blog posts, documentation pages, paywalled content, or JavaScript-heavy sites. Triggers on requests to scrape websites, extract article content, convert pages to markdown, or handle anti-bot protection.
Compatibility alias for `design-system`. Use when an existing workflow, setup script, or user explicitly asks for `frontend-design-system`; route ordinary UI system, design-token, landing-page, dashboard, and component-library work to `design-system` instead. Triggers on: legacy skill name, frontend-design-system alias, exact-folder compatibility, migration-safe UI system routing.
Audits, preserves and recovers local Git state before cleanup: unpushed or wrong-branch commits, dirty worktrees, duplicate clones, stashes, dangling commits, squash-merge uncertainty. Use when the user fears lost work, wants to recover a commit, asks if a branch is actually merged, asks whether a branch, worktree or clone is safe to delete, or wants one clean main (误删分支 / 还有没有丢的东西). Not for GitHub PR operations.
Convert documents and text to audio using Google Cloud Text-to-Speech. Use this skill when the user wants to: narrate a document, read aloud text, generate audio from a file, convert text to speech, create a recording of documentation or analysis, create a podcast from a document, or use Google TTS/text-to-speech. Trigger phrases: "read this aloud", "narrate this", "create a recording", "text to speech", "TTS", "convert to audio", "audio from document", "listen to this", "generate audio", "google tts", "create a podcast".
Use when asked about “marketplace strategy,” “chicken and egg problem,” “liquidity,” “two-sided market,” “tipping a marketplace,” “GMV growth,” or “Sarah Tavel marketplaces.” Helps founders and product leaders build defensible marketplace businesses by sequencing supply and demand. The Hierarchy of Marketplaces framework (created by Sarah Tavel / Benchmark) provides a progression from focused launch to market dominance.
One-time GTM setup: paste one LinkedIn URL and Crustdata enriches it into a persona profile — who you are, what your company sells, your inferred ICP, your writing voice — saved as config/gtm-config.md and config/persona-profile.md, the files the sales-prospecting, account-research, sales-outreach, and meeting-prep skills read at startup. Use when someone says "build my ICP", "set up my GTM config", "create my persona profile", "onboard me", "get me started", or when another GTM skill reports the config is missing.
Look up Amazon product offers and competitive pricing. Retrieve product prices, competitor prices, Listing Offers, Item Offers, batch offers, Featured Offer Expected Price (FOEP), and competitive summaries by ASIN or seller SKU. Trigger when users mention Amazon pricing, product offers, competitor prices, lowest offers, cart prices, Buy Box, Featured Offer, listing offers, item offers, batch pricing, FOEP, competitive summary, or Product Pricing API. Trigger even when SP-API is not explicitly mentioned if the user wants to compare Amazon product offers, assess competitiveness, or estimate the price needed to win the Featured Offer. To change Listing prices, use linkfox-amazon-store-listings or a batch Feed.
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to context-compression, and token-efficiency tactics to context-optimization
Expert Mermaid diagram creation, validation, and rendering with dual-engine output (SVG/PNG/ASCII). Supports all 20+ diagram types including C4 architecture, AWS architecture-beta with service icons, flowcharts, sequence, ERD, state, class, mindmap, timeline, git graph, sankey, and more. Features code-to-diagram analysis, batch rendering, 15+ themes, and syntax validation. Use when users ask to create diagrams, visualize architecture, render mermaid files, generate ASCII diagrams, document system flows, model databases, draw AWS infrastructure, analyze code structure, or anything involving "mermaid", "diagram", "flowchart", "architecture diagram", "sequence diagram", "ERD", "C4", "ASCII diagram". Do NOT use for non-Mermaid image generation, data plotting with chart libraries, or general documentation writing.
Use when working with multi-item data, batches, paginated APIs, rate-limited APIs, fan-out across multiple branches, anything that needs to "do this for each", or any time the user mentions looping, iterating, batching, paging, parallelism, or "loop over items". Triggers on "loop", "iterate", "for each", "batch", "page through", "paginate", "rate limit", "process all", "fan-out", "parallel branches", "concurrency", or any node that should run once vs once-per-item.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Instrument any new feature, endpoint, route, handler, worker, job, CLI command, or user-facing flow with OpenTelemetry spans, metrics, and logs before it lands. Triggers on requests like 'add a new endpoint', 'implement X', 'create a handler for Y', 'build a job to Z', 'add this feature', 'wire up a new route', or any code change that introduces a new business operation.
Curated documentation reference for developers building with Pinecone. Contains links to official docs organized by topic and data format references. Use when writing Pinecone code, looking up API parameters, or needing the correct format for vectors or records.
Query and export data from seekdb vector database. Supports two search modes: (1) Scalar search - metadata filtering only, (2) Hybrid search - fulltext + semantic search combined. The --query-text parameter is used for BOTH fulltext ($contains) and semantic (query_texts) search simultaneously. Can export results to CSV/Excel.
Find focused, runnable Deepgram recipes for a specific feature and language. Use whenever someone wants a minimal working code snippet for one feature (transcribing a URL, diarization, smart formatting, connecting a voice agent, etc.) rather than a full starter app. Recipes are under 50 lines, read DEEPGRAM_API_KEY from the environment, and include a runnable example_test. Covers Python, JavaScript, Go, .NET, Java, Rust, and the Deepgram CLI
Detect users’ writing style requirements and load the corresponding documentation. Activates automatically when users mention keywords such as AI-like writing, removing the AI feel, naturalness, feel-good fiction, fast pacing, satisfying moments, no frustrating elements, no dumbing down, serious literature, depth, strong emotions, emotionally moving writing, sweet romance, romantic moments, tragic romance, heartbreak, or BE. Use when discussing writing requirements, removing an AI feel, pacing, or emotional expression.
Score Russian text 0.0–10.0 across five dimensions: typography, clean language, grammar, structure, precision for the reader. Triggers: оцени текст, ru-score, оценка качества текста, насколько хорош текст, балл за текст. Use when the user wants a number rather than a list of findings. Never edits a file.
Scan project dependencies for known vulnerabilities (CVEs). Use when reviewing dependency files (package.json, requirements.txt, go.mod, pom.xml, Gemfile, Cargo.toml, etc.), triaging Dependabot/Renovate alerts, or performing pre-deployment security checks.
Find a time, draft the invite, and book the meeting on Google Calendar or Outlook — then log it to the CRM as an event on the right account and opportunity. Use when the user says "schedule a follow-up with [contact]", "book the demo with [account]", "find time with [name] next week", "send my Calendly link", or "get the QBR on the calendar".
Quick, professional single-slide PowerPoint creator for concept visualization, comparisons, feature showcases, and decision frameworks. Use when users need to create “one-page PPT”, “single slide presentation”, “快速做个PPT”, “做一页PPT”, or want to visualize concepts like “before/after”, “problem/solution”, “feature grid”, or “process flow” in presentation format. Ideal for visual summaries, product pitches, architecture diagrams, or comparison slides.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch for Claude Code or Cursor, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
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.