Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Rewrite a vague request into a precise EARS-format specification (event/state/optional/unwanted-behavior clauses, domain theories, concrete examples, enhanced prompt). Use when a feature request has no measurable outcome or trigger conditions (「ダッシュボード作って」「リマインダーアプリ」), when a prompt for AI-generated code/docs needs tightening before implementation, or when asked to 「プロンプト最適化」「要件を精緻化」「仕様に落として」. Do NOT use for: defining done-criteria / stop conditions for an autonomous run (goal-prompt-crafter), or tasks whose scope is already one clear sentence.
Python backend testing patterns with pytest for FastAPI applications. Use when writing Python tests: unit tests for services and repositories, integration tests for API endpoints with httpx.AsyncClient, fixture creation, factory setup with factory_boy, async testing with pytest-asyncio, mocking strategies, and parametrized tests. Covers test organization (tests/unit, tests/integration), conftest hierarchy, and coverage requirements. Does NOT cover frontend tests (use react-testing-patterns) or E2E browser tests (use e2e-testing).
React useEffect anti-pattern detection and correction guide. Use this skill whenever writing, reviewing, or modifying any React component that contains useEffect, or when about to add a useEffect hook. Also trigger when you see patterns like "setState inside useEffect", "effect chains", "derived state in effect", or "notify parent in effect". Covers 12 specific scenarios where Effects are unnecessary or misused, with correct alternatives. Even if the useEffect looks reasonable at first glance, consult this skill to verify it's truly needed.
Publish the next nightly build by the project's own nightly process — check that the main branch is green and the nightly tag is current, write the one notes file the build needs (through write-release-notes), commit it, move and push the tag once the user has the notes, then watch the build and check what it published. Use when the user asks to release, cut, publish or update the nightly, to move or update the nightly tag, or invokes /release-nightly. Stops at a red main branch or a missing instruction instead of guessing; never force-pushes anything but the nightly tag.
Report a Decentraland SDK bug, engine/Explorer runtime limitation, or documentation gap to the SDK team BEFORE applying a workaround. Use whenever you or the user find that an SDK7 API, component, the Explorer, the Creator Hub, or the `@dcl/sdk` toolchain does not behave as documented, is missing something a scene reasonably needs, or forces a workaround—even when the workaround is easy. Do NOT use for bugs in the user's own scene code, questions about how an API works, or issues a skill already documents as a known limitation.
Research Dream. A memory-consolidation skill for research scenarios. When accompanying a research user long-term in any host environment (OpenClaw, Codex, Claude Code, Cursor, etc.), it gradually updates USER.md, SOUL.md, MEMORY.md and memory/YYYY-MM-DD.md through everyday conversation, and periodically performs a dream-like deep consolidation so that the memory files progressively move toward a Tashan-style research digital twin.
Resend email API for sending transactional and marketing emails. Use when integrating email delivery, managing domains, handling webhooks, building email workflows with React Email, managing contacts, or sending broadcasts. Use for resend, email, transactional, broadcast, contacts, segments, webhooks, domain.
Uses ripgrep (`rg`) for local text and path search: code symbols, literals, regexes, filename discovery, machine-readable matches. Use when searching repository files or local logs. Not for web search, reading a known file, or JSON queries better handled by jq.
Robot and world descriptions (URDF, SRDF, SDF) for ROS, MoveIt and Gazebo. Use for ROS robot_description files (links, joints, limits, inertials, meshes), MoveIt planning groups, end effectors, group states and disabled collision pairs, Gazebo/gz models and worlds (sensors, plugins, physics), and opening or reviewing a `.urdf`, `.srdf` or `.sdf`. Not the 3D CAD part itself, which the `cad` skill makes, nor a part's structural or physics analysis, nor signed-distance fields
Run predefined featured workflows via run-workflow MCP. TRIGGER when user names a featured workflow (retargeting, banners at scale, localization, packaging, banner advertising, etc.) or asks to run a known marketing/production workflow. Requires run-workflow MCP. ALWAYS call get_featured_workflow before compose_workflow. DO NOT TRIGGER for custom one-off workflows with no named template — use run-workflow skill.
Design, implement, review, and validate embedded Rust firmware, including no_std, targets, runtime and startup, embedded-hal drivers, interrupts, DMA, shared state, async executors, hardware mocks, cross-compilation, flashing, and hardware acceptance evidence. Use when users ask about MCU firmware, portable drivers, HAL versions, bare-metal targets, interrupts, Embassy, RTIC, probe-rs, or embedded testing.
Builds and optimize sales funnels — strategy, structure, conversion optimization, A/B testing, and analytics. Use when your funnel isn't converting, you need to build a funnel from scratch but don't know the right structure, upsell/downsell flow is leaving money on the table, you're not sure which funnel builder to use, or a launch needs a funnel strategy. Do NOT use for email marketing sequences (use /sales-email-marketing), checkout-specific optimization (use /sales-checkout), or webinar funnels (use /sales-webinar). For Groove-specific help, use /sales-groove. For SWAI-specific help, use /sales-swai.
Builds targeted B2B prospect lists for outbound campaigns from database providers (Apollo, ZoomInfo, Clay, Cognism). Use when you don't know who to target, your outbound list is too broad and response rates are low, you can't find the right decision-makers at target accounts, your ICP is vague, or your prospect list is full of bad-fit contacts. Do NOT use for enriching existing contacts with emails/phones (use /sales-enrich), interpreting buying signals (use /sales-intent), general Apollo platform help (use /sales-apollo), or hyperlocal / door-to-door / territory / route-based outbound to local SMBs that aren't on databases — restaurants, gas stations, salons, contractors, HVAC — (use /sales-field-sales).
Call or simulate a Deep Research workflow to organize paper retrieval, keyword breakdown, candidate evidence, and the final answer into a verifiable research report. Suitable for competition problem explanations, thesis proposal research, and organizing the rationale for a solution.
Generate AI avatar and digital persona video prompts for Seedance 2.0 on Higgsfield. Use for virtual spokesperson content, digital twin videos, AI presenter clips, avatar-based marketing, virtual influencer content, or any video featuring a digital/AI-generated character as the main subject. Triggers on avatar, digital persona, virtual presenter, AI character, digital twin, virtual influencer, synthetic media, animated spokesperson.
SEO content brief creation with keyword research, search intent analysis, and content structure. Covers SERP analysis, heading hierarchy, word count targets, and internal linking strategy. Use for: content briefs, SEO writing, blog strategy, content planning, keyword targeting. Triggers: seo content brief, content brief, seo brief, keyword research, search intent, content strategy, blog brief, seo writing, content planning, keyword targeting, serp analysis, content outline, seo article, blog seo
Creates isolated container environments for testing local uncommitted changes before pushing. Use when testing library changes, multi-repo coordination, or validating "works on my machine" → "works in CI". Provides git bundle snapshots, embedded git server, selective URL rewriting, and package manager cache isolation. Works with any coding agent via standalone CLI, shell scripts, or Docker Compose.
Evaluate Agent Skills (SKILL.md directories) and answer \"is this skill any good / safe to install\" — spec compliance with security scanning, with/without behavior comparison, and description trigger testing, ending in a clear install / fix-first / reject verdict. Use this skill whenever the user asks to evaluate, audit, test, review, or score an Agent Skill or a skill collection, wants to know whether a skill actually helps or is safe, or wants to check if a skill's description triggers correctly, even if they just ask \"is this skill any good\".
Multi-slide carousel design for Instagram, LinkedIn, and Twitter/X with layout rules and hooks. Covers slide structure, text hierarchy, swipe psychology, and platform-specific specs. Use for: carousel posts, Instagram carousels, LinkedIn carousels, slide posts, educational content. Triggers: carousel, instagram carousel, linkedin carousel, slide post, carousel design, swipe post, multi-image post, carousel template, educational carousel, carousel content, instagram slides, linkedin slides
Inspect, profile, clean, reconcile, analyze, visualize, and verify spreadsheet data while preserving formulas, formatting, types, and source files. Use when working with .xlsx, .xlsm, .xls, .ods, .csv, or .tsv files; answering questions from a workbook; auditing formulas or data quality; comparing sheets or versions; producing pivots, charts, forecasts, or summary workbooks; repairing malformed tables; or validating that spreadsheet edits and calculations are accurate.
Use when the user is customizing the Spree admin (the `spree_admin` gem) — adding a new resource page, registering a sidebar item, customizing a column in an admin table, overriding a view, scaffolding a new admin section. Common phrasings include "add admin page", "Rails admin", "spree_admin", "scaffold admin resource", "admin sidebar", "override admin view", "Hotwire admin", "Turbo admin".
Starter Coach V2 — conversational 6-step skill that guides users to build their own automated DEX spot-trading bot on OKX DEX. Onboard → User Profile → Build Strategy → Paper Trade → Go Live. Uses OnchainOS CLI for all on-chain data, backtesting, and trade execution. No freeform trading code — emits validated JSON strategy specs. Triggers: starter coach, trading bot builder, strategy builder, help me build a bot, vibe trading, paper trade, backtest strategy, go live trading, build trading strategy, 交易机器人, 策略构建, 量化策略, 自动交易, 做单机器人, 帮我建策略
Auto-invoked at session start when swain-preflight detects issues. Also user-invocable for on-demand health checks. Validates project health: governance rules, tool availability, memory directory, settings files, script permissions, .agents directory, and .tickets/ validation. Auto-migrates stale .beads/ directories to .tickets/ and removes them. Remediates issues across all swain skills. Idempotent — safe to run any time.
Use when writing, reviewing, or debugging code that imports @tanstack/vue-form (TanStack Form for Vue). Covers the 1.33.x API, including useForm, form.Field, form.FormGroup, form.Subscribe, form.useSelector, validators with Standard Schema, onDynamic with revalidateLogic, and array fields with mode="array". Result, forms built on current, non-deprecated Vue APIs with correct reactivity.
Generates dynamic videos from plain text descriptions using meitu-cli, covering the high-quality default mode and the high-motion fast mode. Triggers when the user mentions text-to-video, generating video from text, "help me generate a video", "make a video", advertising video, product promo, or short video.
Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows, results display. Use for: showing agent tool calls, human-in-the-loop approvals, tool output. Triggers: tool ui, tool calls, tool status, tool approval, tool results, agent tools, mcp tools ui, function calling ui, tool lifecycle, tool pending
TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling. Use PROACTIVELY for any TypeScript/JavaScript issues including complex type gymnastics, build performance, debugging, and architectural decisions. If a specialized expert is a better fit, I will recommend switching and stop.
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.
