Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
ZenTao (禅道) product plan management — list product plans and get product plan details. Triggers when the user says: 'query product plans', 'product plan list', 'what plans are there', 'productplan 列表', 'view product plan', 'plan details', '禅道产品计划'.
Challenges requirements, removes unnecessary work, and simplifies design before writing code. Activates when asked to build, implement, automate, add a feature, create a service, migrate, or replace a process. Does not activate for general code writing, bug fixes, or simple edits.
Actix-web Rust web framework. Covers routing, extractors, middleware, state management, and WebSocket. Use for high-performance Rust APIs. USE WHEN: user mentions "actix-web", "actix", "rust web framework", "rust api", asks about "rust async web", "actix middleware", "actix extractors", "rust websocket", "high performance rust api" DO NOT USE FOR: Axum projects - use `axum` instead, Rocket projects - use `rocket` instead, Warp projects - use `warp` instead, non-Rust backends
Use when the user asks to refactor, clean up, or restructure existing ADVPL/TLPP code on TOTVS Protheus without changing its behavior -- extracting long functions (>100 lines), simplifying deeply nested conditionals, removing dead code, improving variable naming (Hungarian notation), eliminating duplicated logic, or reducing functions with too many parameters. Also triggers on Portuguese phrasing like "refatorar rotina", "melhorar esse fonte", "extrair funcao", "remover codigo morto", "simplificar condicional", "reduzir complexidade", or "God function" complaints.
A design charter for designing, implementing and procuring the harness of AI agents (loop, tool surface, context management, authorization, state, stop conditions, evaluation, observability). Use it for "design the harness", "should we build it ourselves, use an SDK or an off-the-shelf option", "what to put in tool/MCP responses, how much to include and how to truncate", "agent permissions and approval tiers", "compaction and multi-agent", "when real model responses differ from expectations or are unstable", and "the mechanics of verify, eval and LLM judge". On the repository side see agent-native-project-design; on Mastra see mastra-ai-architecture-rules.
A skill for designing, organizing and pruning the repository/project side (CLAUDE.md / AGENTS.md, Agent Skills, hooks, subagents) that runs on off-the-shelf AI agents and harnesses such as Claude Code / Codex. Use it for consultations like "design/organize CLAUDE.md", "I want to hand this work to an agent", "I want to create a skill", or "the agent doesn't follow instructions". For developing the harness/runtime itself, see agent-harness-engineering.
Interfaces with a model in the loop. Streaming text without layout thrash, thinking and reasoning states, tool calls and their status, approvals, citations, the composer, stop and regenerate, scroll pinning, markdown rendering, latency masking, and honesty about what the system is doing. Use when building chat, copilots, agent dashboards, AI features inside a product, or anything that shows model output as it is produced.
Write clear, plain-spoken code comments and documentation that lives alongside the code. Use when writing or reviewing code that needs inline documentation like file headers, function docs, architectural decisions, or explanatory comments. Works well for both human readers and AI coding assistants who see one file at a time.
Use when the user wants to build, initialize, validate, optimize, or refactor a model-powered assistant, internal tool, automation, evaluator, or workflow from a business scenario or common problem statement, including project-structure refactors or starter skeletons that may separate model setup, prompt config, and orchestration, even if the request also mentions a UI, app shell, or local model service such as Ollama, and it is still unclear whether the solution should stay a single request, add supporting capabilities, or become orchestration. The user does not need to mention Agently explicitly.
Analyze PyTorch CUDA memory snapshots from torch.cuda.memory._dump_snapshot(), torch.cuda.memory._snapshot(), or memory_viz artifacts. Use when the user wants to understand GPU memory usage, top allocation sites, deallocation timing, OOMs, allocator fragmentation, inactive cached memory, memory leaks, retained tensors, or Python reference cycles in PyTorch workloads. Supports diffing two snapshots from the same run to pinpoint growing allocation sites.
Reverse engineer Go binaries by recovering function names and types from pclntab and moduledata using GoReSym, redress, and IDA/Ghidra Go plugins, and by reading Go's non-standard calling convention, interface dispatch, and string layout. Use when a binary contains Go runtime strings, when strings show runtime.main or go:buildid, when a stripped binary is unexpectedly large, or when analyzing Go malware or a Go-based service.
Reference for androidx Material3 components in Android Jetpack Compose (Kotlin). Button, IconButton, FloatingActionButton, Checkbox, Switch, Slider, TextField, SearchBar, DropdownMenu, Chip, DatePicker, TimePicker, Card, Scaffold, Dialog, BottomSheet, TopAppBar, NavigationBar, NavigationRail, Tab, Snackbar, ProgressIndicator, Badge, Icon, MaterialTheme, ColorScheme, Typography, Shapes
Animation and drawing reference for Android Jetpack Compose (Kotlin). androidx.compose.animation / graphics APIs. AnimatedVisibility, AnimatedContent, animate*AsState, Animatable, AnimationSpec, Canvas, DrawScope, Brush, Path, Color, Image
Android Jetpack Compose (Kotlin) UI foundation reference. androidx, Material3 foundation. Composable, Modifier, CompositionLocal, remember, mutableStateOf, State, LaunchedEffect. Column, Row, Box, LazyColumn, Pager, ConstraintLayout, WindowSizeClass, pane scaffold. BasicText, BasicTextField, TextStyle, IME, clickable, gestures, focus, semantics.
Provides comprehensive guidance for Android development with Kotlin including activities, fragments, views, lifecycle, navigation, and Android app development. Use when the user asks about Android Kotlin, needs to create Android applications, implement Android components, or work with Kotlin in Android.
Drive Archon through its CLI: run AI workflows on a repo, watch and answer runs that need a decision, manage the SDLC pack's queues (intake, build queue, merge queue, discoveries), set up Archon or change its config, and author and validate workflows. Use when the user says "use archon", "run archon", "archon workflow", "fix issue #N with archon", "have archon review this PR", "what's running / check run <id>", "approve/reject/answer/cancel/resume that run", "run the build queue", "drain discoveries", "set up archon", "configure archon", "change my archon config", "create a workflow", "author a workflow", or asks how to write a better Archon prompt. NOT for: doing the coding work yourself. Archon delegates it to isolated runs.
Build and debug encrypted Solana applications with Arcium — data stays private during computation, no single party sees it. Use when writing Arcis circuits (#[encrypted], #[instruction]), wiring Anchor programs with init/queue_computation/callback flows, choosing Shared vs Mxe encrypted state, encrypting inputs with @arcium-hq/client (RescueCipher, x25519), or debugging ArgBuilder ordering, nonce, callback, or computation finalization failures. Covers dark pools, sealed-bid auctions, encrypted voting, hidden game state, confidential DeFi, secure randomness, and threshold signing. Also use for getting started with your first Arcium app.
Route Arduino and embedded-system requests across Arduino IDE, Arduino CLI, PlatformIO, and vendor-specific tools. Use when a request combines firmware, board constraints, electronics, power, networking, calibration, enclosure, upload, debugging, OTA, or maintenance, or when the exact board or toolchain is not yet clear.
Creates beautiful ASCII art visualizations for plans, architectures, workflows, and data. This skill should be used when explaining system architecture, creating implementation plans, showing workflows, visualizing comparisons, or documenting file structures. NOT for code syntax highlighting or markdown tables. User explicitly loves ASCII art - use liberally for visual communication.
Only use when the user explicitly invokes /ask (or $ask in Codex). Never auto-invoke. A read-only skill that provides fact-based analysis and answers to questions without any implementation or editing. For questions about how code works, implementation approach, error causes, or design validity, it answers based on the facts of the implementation and documentation rather than speculation.
Better environment variable management for agents and humans with full type safety, CLI-based remote environment synchronization, and environment validation. Use when setting up typed config schemas, validating env variables, or managing remote env vars across Vercel, Netlify, Railway, Cloudflare, and Fly.io with better-env.
Reason about Commet subscription, plan-change, invoicing, dunning, usage, credits, balance, seats, add-on, pricing, Offer, and billing edge cases. Use the installed SDK documentation for exact API contracts and these verified references only for behavior that the generated contract cannot express.
Scan all blueprint documents and assign IDs to those missing them, update manifest registry. Use when the user asks to "sync document IDs", assigns PRD-NNN / ADR-NNNN / PRP-NNN / WO-NNN IDs to docs missing them, wants to build GitHub issue index for orphans, creates issues for unlinked documents with --link-issues, or previews ID changes with --dry-run.
You MUST use this before any creative work — creating features, building components, adding functionality, modifying behavior, or when users request help with ideation, marketing, and strategic planning. Explores user intent, requirements, and design before implementation using research-validated prompt patterns.
End-to-end development lifecycle for AI coding agents — scaffold projects, plan and build features, create Linear tickets, open and review PRs, clean up after merge, audit codebases, and improve UI polish/motion quality. Works with any agent that reads CLAUDE.md or AGENTS.md. Use when starting a project, implementing a feature, shipping code, addressing PR reviews, merging, auditing code quality, designing or reviewing UI polish, or reviewing animations.
Triggers on /c3 or architecture questions in projects with .c3/ directory. Phrases: "adopt C3", "onboard", "where is X", "audit architecture", "check docs", "add component", "implement feature", "what breaks if I change X", "add ref", "coding standard", "edit the canvas", "add prd/user-story". Ops: onboard, query, audit, change, ref, rule, canvas, sweep. The CANVAS is your architecture's own vocabulary; onboarded facts FREEZE; work advances by change-units. Classifies intent, loads the reference, runs the CLI.
Anti-detect stealth browser automation using Camoufox (Firefox-based, C++-level fingerprint spoofing). Use this skill for ANY browser automation that must avoid bot detection — social media logins, persistent sessions, humanized interaction, or scraping protected sites. Covers 2026-current Camoufox API, known instability warnings, async/sync patterns, persistent context, and humanization config. ALWAYS use this over raw Playwright when stealth is required.
Use when the user asks to generate a changelog, release notes, or delivery notes from ADVPL/TLPP code changes on TOTVS Protheus -- analyzing diffs or a list of changed files, classifying each change (NEW/FIX/CHANGE/REMOVE/REFACTOR), assessing business impact (ALTO/MEDIO/BAIXO), and detecting affected tables. Also triggers on Portuguese phrasing like "gerar changelog", "notas de versao", "documentar entrega", "o que mudou nessa versao", or requests to audit code changes for compliance.
Create or update a `.changeset/*.md` file for the current branch or PR in this repository, choose the correct package scope and release type, and verify the result against repo-specific Changesets config. Use when a publishable package changed, when a PR is missing a changeset, when an existing changeset needs correction, or when Codex needs to confirm whether a branch should have a changeset at all.
Clean code principles. Covers naming, functions, and readability. Use when writing or reviewing code for quality. USE WHEN: user mentions "code quality", "readability", "refactor", "clean up code", "naming", "magic numbers", asks about "how to write better code", "code smells", "DRY", "KISS", "YAGNI", "single responsibility" DO NOT USE FOR: SOLID principles - use `solid-principles` instead, Git workflow - use `git-workflow` instead, Performance optimization - use `performance` instead
Scan and analyze a software repository or project for design quality using principles from A Philosophy of Software Design by John Ousterhout. Use when user asks to review, audit, scan, or evaluate code quality, design quality, architecture, or technical debt. Also trigger for: code review, design review, complexity analysis, code health check, module depth analysis, information hiding review, information leakage, how good is my code, review my project, find design problems, what is wrong with my codebase, rate my code, audit my small project, quick code review, design check, or anything about evaluating software design quality at a structural level. This is not a linter or style checker. It evaluates deep design qualities like module depth, abstraction quality, information hiding, and complexity patterns. Adapts to project size — small projects (<20 files) get a concise review, large projects get sampled.
Build, test, deploy, and certify commercetools Connect applications — service/API-extension, event/subscription, job, and Connect-hosted Merchant Center custom apps and views — in TypeScript/JavaScript (Java supported). Covers the connect.yaml contract, least-privilege scopes, lifecycle scripts, sync-vs-async idempotency and ack, testing, and deployment. For a named vendor or domain integration see commercetools-integrations; not for the hosted Checkout widget (see commercetools-checkout). Use when building, deploying, certifying, or debugging a Connect connector.
Implement and diagnose Commet webhook endpoints in Node, Python, Go, Java, or PHP, including framework handlers, signature verification, event handling, retries, and idempotency. Use event names, payloads, headers, and helpers from the installed SDK documentation and types rather than a copied event catalog.
Build and deploy the Goldsky Compose bitcoin-oracle example under the user's own account — a cron task that fetches BTC/USD from CoinGecko and writes `(timestamp, price)` as `bytes32` values to an on-chain `PriceOracle` contract via a Compose-managed wallet, appending each price to a durable collection. Triggers on: 'build a bitcoin price oracle', 'BTC/USD oracle onchain', 'push a price feed onchain', 'cron price oracle', 'set up / deploy the bitcoin-oracle example', 'compose price oracle'. Recommends the shared fully-unpermissioned oracle on Base Sepolia so there's nothing to deploy. Scaffolds the example from goldsky-io/documentation-examples, walks CLI install, contract choice (reuse shared / deploy own), wiring, optional GitHub publish, and a log-tailing smoke test. For a custom/novel Compose app that isn't this oracle, use /compose. For debugging an already-deployed app, use /compose-doctor. For manifest/CLI/API field lookups, use /compose-reference.
Run all infrastructure standards checks and configure compliance across a project. Use when performing a comprehensive infrastructure audit, setting up a new project against all standards, batch-fixing compliance issues with --fix, or validating CI/CD compliance. Natural triggers: "check all standards", "audit project compliance", "configure everything", "run all configure checks".
When the user wants to solve complex scheduling, allocation, or combinatorial problems using constraint programming (CP). Also use when the user mentions "constraint programming," "CP-SAT," "constraint satisfaction," "all-different constraint," "global constraints," "propagation," "search strategies," or when the problem has complex logical constraints, scheduling with disjunctive resources, or allocation problems. For MIP, see optimization-modeling. For metaheuristics, see metaheuristic-optimization.
Authoring or revising a Git commit message, titling a pull request, or judging whether a header conforms — the Conventional Commits v1.0.0 header contract, plus a validator that catches a malformed header before it reaches your history. Triggers on "write a commit message", "what type should this be", "is this header valid", "does this need a scope", "mark this as a breaking change", or preparing a squash-merge title that becomes a permanent commit subject. Not the pull request body, which a pull-request-description capability owns, and not issue titles. Covers types, scopes, footers, breaking-change markers, and SemVer correlation.
Use when converting or migrating email templates from another provider (SendGrid, Mailgun, Mandrill, Postmark, Brevo, Amazon SES) to Mailtrap-compatible Handlebars syntax. Supports single file, bulk directory, and inline HTML conversion.
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.