Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Creates performant CSS-first web animations and chooses the right feedback for an interaction: transitions, View Transitions, scroll-driven motion, Motion for React, reduced motion, and perceived performance. Triggers on “animate this,” “hover effect,” “feel faster,” “skeleton loader,” and “/animations.”
AVFoundation / AVKit / PhotoKit reference. AVPlayer, AVPlayerViewController, VideoPlayer, AVPlayerItem, AVMutableComposition, AVCaptureSession, AVCaptureDevice, AVCapturePhotoOutput, AVCaptureDeviceDirectionCoordinator, CameraCaptureAccessory (iPhone Duo), AVAudioEngine, AVAudioSession, AVAudioPlayer, AVSpeechSynthesizer, PHAsset, PHImageManager, PhotosPicker, PHPhotoLibrary.
Design, review, organize, and evolve scalable, secure, maintainable backend systems across any language, framework, runtime, database, API style, deployment model, or architecture. Detects whether a backend already exists and produces a safe improvement path before changing it; otherwise designs a new backend from scratch. Use when planning backend architecture, reviewing an existing system, reorganizing files, modernizing modules, selecting boundaries, or implementing production-grade backend features.
Archive a completed spec — verify every task completed, QA passed, and indexed references are self-contained, then write <slug>.md under the resolved archive root (<spec-root>/_archived/, or docs/history/specs/ for the built-in docs/specs root) and remove the Spec folder, which stays in Git at the record's source_revision. Runs automatically at the end of a Roundfix Spec Run after a QA pass, or whenever the user asks to archive a spec.
This skill provides a comprehensive approach for building astrology-specific backend systems with AI integration. Use when implementing vedic astrology features including kundli generation, dasha analysis, dosha detection, and astrological predictions. Builds on the ai-integrated-api-backend skill with astrology domain expertise.
Deep codebase analysis for building architectural context before vulnerability or bug finding. Uses line-by-line analysis with First Principles, 5 Whys, and 5 Hows. Use when deep comprehension is needed before security auditing, architecture review, or threat modeling.
Use when loading with `AssetServer::load` or `AssetServer::load_builder().with_settings(..)`, holding a `Handle<T>`, spawning a glTF scene with `WorldAssetRoot` (`Handle<WorldAsset>`), mutating through `Assets::get_mut` / `AssetMut`, polling `LoadState::is_loaded`, resolving an `AssetPath`, or replacing `AssetId::invalid()` with `Option<AssetId<T>>` in Bevy 0.20.
Use this skill to run BMad (Breakthrough Method of Agile AI-Driven Development) as a harness-agnostic control-plane protocol that turns human intent into bounded, inspectable, resumable agent work. Compress intent into a five-field contract (Why, Capabilities, Constraints, Non-goals, Success signal); classify work as direct/bounded/initiative and route to the smallest safe path; carry decisions in durable artifacts; review as triage; route failure to the layer where ambiguity entered; and gate autonomy on observable acceptance with machine-readable status (draft/ready-for-dev/in-progress/in-review/done/blocked). Use when a change request, feature, delegated build, or multi-agent epic needs intent capture, bounded implementation, review, and resumability in any agent harness. Do not use for validating whether a problem is real (product-discovery), shaping bets before planning (product-shaping), formal spec/gate pipelines (spec-driven-development), or the issue-to-PR delivery flow (neckbeard)
Wire a web or React Native frontend to Bounded: the @bounded-sh/client SDK (reads, writes, subscriptions, queries), hosted static frontends, and end-user auth UI (email OTP, OAuth, browser guest/anonymous accounts, and upgrades). Use when building the client of a Bounded app or handling how end users sign in. Part of the Bounded skill family; server-side rules, functions, and the actor model live in the bounded-backend skill, and deploy/hosting config in bounded-deploy.
Turn a plain-language request into a working, tested Agenta agent through the Agenta API. Use when the user wants to build, create, schedule, or test an Agenta agent from their coding agent (Claude Code, Codex, Cursor). Writes one config and runs a few bundled shell scripts. Triggers on "build an Agenta agent", "create an agent on Agenta", "schedule an Agenta agent", or wiring an agent to a tool like GitHub or Slack via Agenta.
Three.js 3D building system with spatial indexing, structural physics, and multiplayer networking. Use when creating survival games, sandbox builders, or any game with player-constructed structures. Covers performance optimization (spatial hash grids, octrees, chunk loading), structural validation (arcade/heuristic/realistic physics modes), and multiplayer sync (delta compression, client prediction, conflict resolution).
Use this skill to attach a USB device or emulator to ADB, list transports with `adb devices` / `adb devices -l`, disambiguate among multiple devices using `-s SERIAL`, `-d` (single USB), `-e` (single TCP/IP), or `-t TRANSPORT_ID`, gate scripts on a transport with the canonical `adb wait-for[-TRANSPORT]-<state>` syntax (TRANSPORT in {usb, local, any}; state in {device, recovery, rescue, sideload, bootloader, disconnect}), interpret device states (`device`, `offline`, `unauthorized`, `no permissions`, `recovery`, `sideload`, `bootloader`, `rescue`), accept the RSA fingerprint dialog on first connect, and install Linux udev rules. Use when the user mentions `error: more than one device/emulator`, `error: device not found`, `unauthorized`, `no permissions`, `daemon not running`, "wait for device to boot", `wait-for-device-online` (which is not a real subcommand), or asks how to script around emulator startup.
For cross-project CRD recipients: independently assess long-term proposals and state a position, provide a focused response, or report implementation results. Proposers use crd. For non-Kubernetes CRDs or code implementation. When code changes are needed, generate a development plan that includes the source CR and an agreement to report back on completion.
Generates a delivery timeline from a completed milestones.yaml. Asks for a production deploy date, QA rounds, and days per QA session. Updates each milestone with estimated_days, produces timeline.yaml with a complete relative-day schedule, and appends a workback block mapping every item to a real calendar date working backwards from the production deploy date.
Analyze a codebase to detect its language, framework, conventions, and CI gates. Run this on first use in a project to generate stack context that all coding principle skills reference. Use when the user says "detect stack," "analyze this project," or "what's this codebase using."
Classify, validate, generate, and audit documentation using the Diátaxis framework. Enforces quadrant purity across tutorials, how-to guides, reference, and explanation. Use when creating documentation, reviewing docs, auditing doc sets, restructuring existing content, or when the user mentions Diátaxis, documentation structure, or doc quality.
This skill should be used when deciding whether a doc should exist, where it belongs, whether something is really an ADR, or whether an architectural decision is missing from the record. PROACTIVELY activate on "should this be an ADR?", "where should I document X?", "is this architecturally significant?", "ADR vs RFC vs design doc vs runbook", "Diátaxis", "audit docs folder", "clean up the decision log", "doc drift", "doc governance", "ADR template selection", "Nygard vs MADR vs Y-statement", "missing ADR", "missing decision record", "undocumented architecture", "implicit decision", "historical documentation clutter", "inherited repo", "large legacy repo", "architecture archaeology", "code archaeology", "scan for decision records", "find decisions not captured in ADRs." Provides: doc placement diagnostic, alternatives catalog, ADR canon, folder audit procedure, and BACKFILL-ADR candidate detection.
Create, restructure, review, audit, or migrate DeepSeek Harness Markdown documentation, package READMEs, and the documentation website using audience-first hierarchy, kind-mapped YAML metadata, bilingual line alignment, summary/contents navigation, progressive user-to-developer detail, executed-operation fact-checking, and repository validation. Use for new or revised DSH docs, docs-tree organization, documentation-quality audits and budgets, website page publishing, and bilingual documentation structure changes.
Optimize and build programmatic prompt systems with Stanford DSPy. Signatures, modules (Predict, ChainOfThought, ReAct), optimizer/teleprompter selection, compilation, caching, evaluation. Use when doing programmatic prompt optimization or building compiled prompt programs. Do not use this skill for unrelated requests; route to the nearest named specialist.
Excel template filling skill based on Alibaba EasyExcel (com.alibaba:easyexcel:4.0.3). Covers simple object filling, list filling ({.}+forceNewRow), horizontal multi-column combination filling (FillWrapper+WriteDirectionEnum.HORIZONTAL), complex filling (with total rows/statistics rows, fill then write), Spring Boot integration, template design conventions, escape characters, differences between 03 and 07 formats, and performance optimization (batched fill, file caching). Use this skill when the user needs to fill Java objects or Map data into a pre-made .xlsx template (variable syntax {var}, {.}, {prefix.}) to generate reports (payslips/contracts/statements/invoices/financial statements/statistics tables/summary tables); not for "programmatically generating Excel" scenarios that don't use a template (use easyexcel-write instead).
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Use when adding, reviewing, or documenting Email SDK integrations in TypeScript/Bun apps. Dynamically refreshes the current Email SDK docs/source before implementation, then covers adapter selection, fallbacks, CLI smoke tests, hooks, and secret-safe observability.
Audit and implement an app's error UX end-to-end: rewrite error messages, place them correctly, add recovery actions, and build error states for validation, network, permission, system, and 404 failures. Use when the user says 'improve my error handling', 'my error messages suck', 'users get stuck when something fails', 'add form validation errors', 'handle offline/network errors', 'design a 404 page', or when a review finds bare 'Something went wrong' strings, silent failures, or errors with no way forward. Produces an error-state matrix (every failure mode × message × recovery action) plus the implemented error components and copy.
This skill should be used when the user asks to "configure esp32-s3-box-3", "set up box-3", "create box-3 voice assistant", "display lambda on box-3", "configure ili9xxx display", "set up gt911 touch", "configure i2s audio", "es7210 microphone", "es8311 speaker", "box-3 audio pipeline", or mentions error messages like "I2S DMA buffer error", "Touch not responding", "Display flicker", "Audio popping", "PSRAM not detected". Provides complete ESP32-S3-BOX-3 hardware templates, display lambda cookbook, touch patterns, and voice assistant configurations.
This skill should be used when writing tests, fixing bugs, adding features, or modifying the gateway layer. Use when you need guidance on testing architecture, working with fakes, implementing ABC gateway interfaces, or understanding the defense-in-depth testing strategy. Essential for maintaining test quality and understanding where different types of tests belong.
FastAPI framework mechanics and advanced patterns. Use when configuring middleware, creating dependency injection chains, implementing WebSocket endpoints, customizing OpenAPI documentation, setting up CORS, building authentication dependencies (JWT validation, role-based access), implementing background tasks, or managing application lifespan (startup/shutdown). Does NOT cover basic endpoint CRUD or repository/service patterns (use python-backend-expert) or testing (use pytest-patterns).
Systematic code review focusing on bugs that break at runtime (contract mismatches, logic/async errors, serialization, styling) and JS/TS static analysis via fallow. Use when reviewing code changes for runtime errors, post-implementation checks, finding contract mismatches, or running static analysis via fallow on changed files.
Use a small FlareSolverr JSON CLI for browser-backed GET and POST requests, readiness checks, and session lifecycle management when a site requires Cloudflare or DDoS-GUARD challenge handling. Do not use this skill for unrelated requests; route to the nearest named specialist.
Configure and verify Flutter flavors, environments, signing, versioning, release artifacts, obfuscation symbols, and store-ready builds. Use for local artifact configuration; route CI provider workflows to flutter-ci-cd, and do not publish or change live credentials without explicit authorization.
Build or repair adaptive Flutter layouts across devices, constraints, breakpoints, overlap, clipping, orientation, and input modes. Use with flutter-accessibility when text scaling causes reflow, clipping, or disappearing controls; not for general widget state architecture.
Design, review, simulate, and verify FPGA logic using explicit RTL contracts, clock and reset models, CDC analysis, timing constraints, and reproducible implementation evidence. Use for synthesizable HDL, fixed-point arithmetic, handshakes, testbenches, resource tradeoffs, timing closure, and FPGA release or bring-up planning. Do not use for ordinary MCU firmware, generic circuit design, a substitute vendor-tool manual, or unsupported claims of hardware or timing signoff.
Enforce safe Frida 17 MCP operations with strict phase gating. Use when attaching/spawning sessions, writing or loading scripts, applying Java/native hooks, troubleshooting instrumentation failures, or interpreting Frida MCP output. Require docs-first usage and run the mandatory workflow: Idea -> Scripting -> Execution -> Notes.
Use this skill when the user asks to commit and push together, save and push changes, run `/git-maker`, select current-session or all changes, or propagate newly created commits to `&&`-separated branches. It supports linked Git worktrees, automatic push, and intent-preserving conflict resolution.
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.