Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Run a team of agents in Herdr panes, one pane per job (scouter, planner, designer, implementer, tasker, reviewer, security-reviewer, researcher, inspector). The calling agent stays the orchestrator: it spawns one CLI agent per role in sibling panes, dispatches self-contained briefs, collects file-based reports, and owns integration, gates, and git. Use when running inside Herdr (HERDR_ENV=1) for any non-trivial work: the user asks for a herd, team, roles, a designer or reviewer agent, parallel workers, or the task needs a survey (several files, another repo, tool conventions), touches more than a couple of files, or the project's AGENTS.md routes work through this skill. Do not use outside Herdr; a one-or-two-file change with no product decision is done directly.
Same pixels, fewer tokens — for user-facing deliverables where visual polish is the spec. Use when building or editing a landing page, marketing site, hero, pricing/feature section, dashboard, or any HTML/CSS UI component. Keeps the full rendered design (layout depth, hierarchy, motion, responsive richness, a11y) and cuts tokens by expressing that design densely — CSS custom properties, shared classes, shorthand, fluid units — instead of by cutting the design. The honey core trims code and prose; this trims how the design is *written*, never how it looks. Reach for it whenever output is user-facing markup, even if the user never says "minimal".
Review a diff for what Honey would cut — over-engineering (speculative generality, hand-rolled stdlib, single-caller abstractions) and over-verbosity (dead code, narration, redundant comments). Outputs a terse delete-list, one line per finding, with the line count each cut saves. Use when asked to review, trim, or de-bloat a change, or before opening a PR. Quality lever only — it finds waste, not correctness bugs.
This skill should be used when the user asks to "build a HubSpot app", "create a HubSpot app", "add a card to HubSpot", "create an app card", "build a UI extension", "set up HubSpot webhooks", "configure HubSpot app", "add a settings page to HubSpot app", "build a HubSpot home page", "fetch data in HubSpot extension", "list an app on the HubSpot marketplace", "submit a HubSpot app listing", "marketplace listing requirements", "add serverless functions to HubSpot app", or mentions building on the HubSpot developer platform 2026.03. Provides comprehensive guidance for building full HubSpot apps with best practices, CLI commands, file structure, serverless functions, and App Marketplace listing requirements.
Hugo template development for InfluxData docs-v2, enforcing build and runtime testing to catch template errors that build-only validation misses. Use when creating or editing Hugo layouts, partials, or shortcodes, debugging template errors, or accessing site data in templates.
Rewrites a README.md to remove AI slop — buzzwords, generic openers, fake enthusiasm, and formulaic structure — replacing it with direct, honest, human-sounding writing. This skill should be used when the user wants to humanize a README, remove AI-generated writing patterns, make documentation sound less like ChatGPT wrote it, or asks to "humanize readme", "make it sound human", "remove AI slop from the docs". NOT for factual drift (whether the README's claims are still true — that is a docs-accuracy audit) and not for source code slop (anti-slop).
Image processing and optimization. Sharp (Node.js), Pillow (Python), Cloudinary, responsive images, WebP/AVIF conversion, thumbnails, and CDN-based image transformation. USE WHEN: user mentions "image resize", "thumbnail", "image optimization", "Sharp", "Pillow", "Cloudinary", "WebP", "AVIF", "image upload processing" DO NOT USE FOR: file upload handling - use `file-upload`; cloud storage - use `cloud-storage`; PDF generation - use `pdf-generation`
How to implement solutions using the MSH (Micro-Service Helper) TypeScript packages from @beecode/msh-* (app-boot, env, error, logger, node-session, util, config). Use this skill whenever the user works with any @beecode/msh-* package, or asks to set up app initialization and graceful shutdown, environment variable validation, HTTP-aware errors and Express error handling, logging, request-scoped sessions/CLS/async-local-storage, or shared utilities (singletons, memoize, timeout, joi validation, time helpers). Also trigger when the user mentions MSH, beecode, AppFlow, LifeCycle, AppStarter, mshEnv, mshEnvResolver, errorFactory, errorHOF, ErrorBaseModel, HttpResponseCodeMapper, PresetConsoleSimpleString, PresetConsoleJson, PresetPino, LogLevel, LoggerStrategy, NodeSessionUtil, SessionStrategy, FastAlsStrategy, ClsHookedStrategy, AsyncLocalStorageStrategy, singletonPattern, SingletonAsync, ObjectUtil, TimeUtil, JoiUtil, memoizeFactory, or msh-config eslint/prettier config. Always consult this skill before writing code that imports from @beecode/msh-* so the correct current API and the right package version are used
Schedule local (on-device) notifications via @capacitor/local-notifications — reminders, daily prompts, post-action follow-ups. Trigger when adding scheduled reminders, drink-water-style daily nudges, or any notification fired by the app itself rather than a server. Distinct from push notifications.
Java language (17+). Covers modern features, patterns, and best practices. Use when writing Java applications, Spring Boot backends, or enterprise systems. USE WHEN: user mentions "java", "records", "sealed classes", "streams", asks about "pattern matching", "switch expressions", "Optional", "collections", "generics" DO NOT USE FOR: reviewing existing Java code - use `review/java`, which covers the defects javac and an unconfigured build do not report DO NOT USE FOR: Spring Boot specifics - use `backend-spring-boot` skill instead DO NOT USE FOR: Lombok annotations - use `lombok` skill instead DO NOT USE FOR: MapStruct - use `mapstruct` skill instead
JSC GC reference for Bun. Use for use-after-free, JS object leaks, "collected too early", or when touching WriteBarrier, visitChildren, visitAdditionalChildren, JSRef, JSC::Strong/Weak, hasPendingActivity, ensureStillAlive, addOpaqueRoot, reportExtraMemoryAllocated, IsoSubspace, HeapAnalyzer, finalize.
Analyze JIRA tickets to determine priority and dependency order, grouped by dependency layer and relationship. Outputs a structured JSON plan with layered groups, branch names, repo assignments, complexity, and verification hints. Use before implement/forge, whenever the user gives you a list of JIRA tickets to work through, or when asked to "prioritize tickets", "order these JIRAs", "what should I tackle first", "plan my sprint", "sort my backlog", "which ticket should I do first", or "figure out the order for these tickets". Also trigger when the user provides a set of JIRA keys alongside a task to implement them.
Session-discipline skill for finishing work, built on top of the beans CLI. One active epic per session, draft-first triage, ~10-minute subtasks delegated to subagents, tests + Proof of Work before any bean closes. Use when you are taking on a goal that spans multiple beans, when an epic risks drifting across sessions, when subagents need a delegatable tree to work against, or when you want completion to be provable rather than confident. Keywords: finish, completion discipline, epic task subtask, draft triage, proof of work, beans loop, session goal, agenda, ledger
Finds and removes legacy, deprecated, compatibility-shim, and fallback code paths so only the current canonical implementation remains. Works on a named target or the full first-party codebase. Use when the user says "kill-legacy", "kill legacy", "remove legacy", "remove fallbacks", "drop compatibility shims", "delete deprecated paths", "remove old code paths", or asks to clean up migration leftovers and dual-write/dual-read bridges that are no longer needed.
Provides strategies for efficiently transforming large text files (thousands to millions of lines) using text editors like Vim, sed, or awk. This skill should be used when tasks involve bulk text transformations, CSV manipulation at scale, pattern-based edits across massive files, or when keystroke/operation efficiency is constrained. Applicable to tasks requiring macros, regex substitutions, or batch processing of structured text data.
This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-to-use shell script templates for system administration
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.
Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Kimi K2, GLM-4.6, Intellect 3. One API for all models with automatic fallback and cost optimization. Use for: AI assistants, code generation, reasoning, agents, chat, content generation. Triggers: claude api, openrouter, llm api, claude sonnet, claude opus, gemini api, kimi, language model, gpt alternative, anthropic api, ai model api, llm access, chat api, claude alternative, openai alternative
This skill generates llms.txt documentation optimized for AI/LLM consumption. It should be used when the user says "crear llms.txt", "generate llms.txt", "documentar para AI", "document for AI", "crear documentacion para LLMs", "generate docs for LLMs", "make repo readable for Claude", or wants to create structured machine-readable documentation following the llms.txt standard.
Build, review, debug, migrate, or plan React code with @mantine/hooks only (standalone React hooks package). Use for useDisclosure, useToggle, useListState, useLocalStorage, useSessionStorage, useHotkeys, getHotkeyHandler, useClickOutside, useDebouncedValue, useDebouncedState, useDebouncedCallback, useThrottledValue, useMediaQuery, useColorScheme, useReducedMotion, useMergedRef, useMove, useDrag, useMask, useCollapse, useHorizontalCollapse, useRovingIndex, useSplitter, useFloatingWindow, useUncontrolled, useFocusTrap, useIntersection, useResizeObserver, useFetch, clamp, randomId, and Mantine 8→9 hooks migrations. Do not use for @mantine/core components, @mantine/form, themes, or other Mantine packages.
Add Lens to a live notebook, explain a notebook with a guided Trail, or address a user's selection on a rendered output or configured DOM target. Use when asked to enable Lens, give a walkthrough, explain results in place, or act on selected points, regions, and notes. The address mode handles every open selection. Requires the live marimo notebook kernel, reached through marimo pair or the editor's code-mode sidebar.
Integrate the alpha markstream-angular package into an Angular 20+ app. Use when Codex needs standalone component imports, signal-based examples, CSS wiring, custom HTML tags or customComponents setup, or optional peer integration in an Angular repository.
Add OpenTelemetry tracing to MATLAB code. Use when the user asks to "add tracing", "instrument with spans", "add OpenTelemetry", "trace my code", "add observability" (when about tracing), or mentions "spans", "distributed tracing", or "OTel tracing" in the context of MATLAB functions. Covers span creation, parent-child context propagation, error handling, attributes, events, and semantic conventions
Cordova MatrixScan AR (Barcode AR, BarcodeAr) via the scandit-cordova-datacapture-* plugins — scanning multiple barcodes at once with AR highlights and annotations (info annotations, popovers, status icons) on tracked barcodes. Use for integration, symbology configuration, highlight and annotation providers, BarcodeArView customization, migration from BarcodeBatch/BarcodeTracking, or troubleshooting.
Capacitor MatrixScan Batch (scandit-capacitor-datacapture-barcode) — MatrixScan, BarcodeBatch, legacy BarcodeTracking — tracking and scanning multiple barcodes at once with basic/advanced AR overlays in Capacitor iOS/Android apps (not the plain-web sibling). Use for integration, settings and symbologies, per-barcode brushes, TrackedBarcodeView annotations, lifecycle, SDK version migration, replacing a third-party scanner (@capacitor-mlkit/barcode-scanning), or troubleshooting.
Capacitor MatrixScan Count (BarcodeCount) — plugin scandit-capacitor-datacapture-barcode. Multi-barcode counting and receiving workflows (scan-and-count, inventory count, capture list, status mode) with BarcodeCountView on a DOM element in Capacitor apps, iOS/Android native only. For React Native use matrixscan-count-rn. Use for integration, symbology configuration, result handling, view customization, or troubleshooting counting workflows.
Guide for implementing deep linking in .NET MAUI apps. Covers Android App Links with intent filters, Digital Asset Links, and AutoVerify; iOS Universal Links with Associated Domains entitlements and Apple App Site Association files; custom URI schemes; and domain verification for both platforms. USE FOR: "deep linking", "app links", "universal links", "custom URI scheme", "intent filter", "Associated Domains", "Digital Asset Links", "open app from URL", "handle incoming URL", "domain verification". DO NOT USE FOR: in-app Shell navigation (use maui-shell-navigation), push notification handling (use maui-push-notifications), or web content embedding (use maui-hybridwebview).
Use this skill when the user asks to “add MCP server”, “integrate MCP”, “configure MCP in plugin”, “use .mcp.json”, “set up Model Context Protocol”, “connect external service”, mentions “${CLAUDE_PLUGIN_ROOT} with MCP”, or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
Model Context Protocol server development, tool design, resource handling, and transport configuration. Use for: mcp, model context protocol, mcp server, mcp tool, mcp resource, fastmcp, mcp transport, stdio, sse, streamable http, mcp inspector, tool handler, mcp prompt.
Use when running the zetic.ai `melange` CLI: uploading/importing on-device AI models, monitoring conversion status, reporting Melange benchmarks, generating deployment guides, browsing repos and the public library. Covers auth, choosing between importing a Hugging Face repo id and uploading exported artifacts, JSON output contract, exit-code branching, upload/resume, non-blocking conversion monitoring, model report templates, and the raw API escape hatch. Also points at the `melange mcp` MCP server alternative and when to prefer its tools over shelling out. Do NOT trigger for general ML work — training, local inference, or other model registries — unless the `melange` CLI is involved.
Merge open Dependabot pull requests in a GitHub repository using the `gh` CLI, filtered by semver bump type and CI status. Use this skill whenever the user asks to merge, clear, batch, or clean up Dependabot PRs — "merge all dependabot PRs", "clear the dependabot backlog", "merge the dependency bumps", "land the safe dependabot updates" — or invokes it as a slash command, including when they ask to include majors, merge despite failing checks, or squash instead of rebase. Not for reviewing or merging human-authored PRs, and not for writing dependabot.yml — that is dependabot-config.
Use when working with low-level Cardano utilities via MeshJS core-cst package. Covers CBOR serialization and deserialization, Plutus data conversion, address resolution and parsing, CIP-8 message signing and verification, script parameterization with applyParamsToScript, native script hashing, and direct access to cardano-sdk types.
Integrating TanStack DB with meta-frameworks (TanStack Start, Next.js, Remix, Nuxt, SvelteKit). Client-side only: SSR is NOT supported — routes must disable SSR. Preloading eager collections in route loaders with collection.preload(). On-demand Query Collections require preloading the live query because source collection preload is a no-op. Multiple collection preloading with Promise.all. Framework-specific loader APIs.
Migrate a React Native project from NativeWind to Uniwind. Use when the user wants to replace NativeWind with Uniwind, upgrade from NativeWind, switch to Uniwind, or mentions NativeWind-to-Uniwind migration. Handles package removal, config migration, Tailwind 4 upgrade, cssInterop removal, theme conversion, and all breaking changes.
Migrate an existing repository from the legacy planned-features.md plus per-feature design.md/tasks.md workflow to dstack's Copier- and Beads-based workflow. Use when asked to adopt dstack, convert legacy workflow state, or resume an interrupted workflow migration.
Cross-platform and native mobile development. Frameworks: React Native, Flutter, Swift/SwiftUI, Kotlin/Jetpack Compose. Capabilities: mobile UI, offline-first architecture, push notifications, deep linking, biometrics, app store deployment. Actions: build, create, implement, optimize, test, deploy mobile apps. Keywords: iOS, Android, React Native, Flutter, Swift, Kotlin, mobile app, offline sync, push notification, deep link, biometric auth, App Store, Play Store, iOS HIG, Material Design, battery optimization, memory management, mobile performance. Use when: building mobile apps, implementing mobile-first UX, choosing native vs cross-platform, optimizing battery/memory/network, deploying to app stores, handling mobile-specific features.
(NS) Interview users through focused technical questions to recommend LangGraph vs CrewAI, propose multi-agent architecture, and design agent personas with tools and models. Use whenever the user wants to build a multi-agent system, choose between LangGraph and CrewAI, design agent crews or graphs, plan human-in-the-loop workflows, or asks how to orchestrate AI agents — even if they only say "I want a bot for my company" or "agents working together". Do NOT use for general app requirements (use pm-clarify-requirements) or implementation coding without architecture intent.
Design and implement multi-agent LLM architectures using the orchestrator-subagent pattern. Use when: (1) Deciding whether to use multi-agent vs single-agent systems, (2) Implementing context isolation for high-volume operations, (3) Parallelizing independent research tasks, (4) Creating specialized agents with focused tool sets, (5) Building verification subagents for quality assurance, or (6) Analyzing context-centric decomposition boundaries.
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.