Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Write, review, audit, refactor, and diagnose POSIX `sh` code and configuration. Use whenever code is intended to run under a POSIX shell or a migration targets POSIX `sh`. Covers `.sh` files, `#!/bin/sh` entrypoints, extensionless commands, sourced libraries, hooks, startup fragments, generated shell fragments, and other shell code with no identifiable shell dialect. Don’t use when the requested output is only code for a non-POSIX shell.
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks required tests and docs, then writes Description / Proofs / Fixes.
Product changelog and release notes that users actually read. Covers categorization, user-facing language, visuals, and distribution. Use for: release notes, changelogs, product updates, feature announcements, versioning. Triggers: changelog, release notes, product update, version notes, what's new, feature announcement, product changelog, update log, release announcement, version release, product release, ship notes
Use when a project's house style already exists somewhere and needs to become something the tooling can check - the developer hands over a standards document, points at an older or company base schema whose naming should be adopted, says "our team does it this way", or asks why an apply preview warned about a name. Derives the patterns from the real schema, verifies them against it, and writes .pythia/conventions.json and conventions.md.
Python SDK for inference.sh - run AI apps, build agents, and integrate with all models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and human approval. Use for: Python integration, AI apps, agent development, RAG pipelines, automation. Triggers: python sdk, inferencesh, pip install, python api, python client, async inference, python agent, tool builder python, programmatic ai, python integration, sdk python
Guidance for managing R package lifecycle according to tidyverse principles using the lifecycle package. Use when: (1) Setting up lifecycle infrastructure in a package, (2) Deprecating functions or arguments, (3) Renaming functions or arguments, (4) Superseding functions, (5) Marking functions as experimental, (6) Understanding lifecycle stages (stable, experimental, deprecated, superseded), or (7) Writing deprecation helpers for complex scenarios.
Analyzes an AI/ML publication — paper, preprint, article, technical blog post — and extracts what an enterprise AI engineer should do about it. Use when someone supplies a URL or document on RAG, embeddings, fine-tuning, prompt engineering, agents, or LLM deployment and asks "review this paper", "what do you make of this", "is this worth adopting", or "summarise the method and its limits". The subject matter must itself be machine learning.
Use when reviewing/judging a finished feature specification to decide if engineering can plan and build from it — an acceptance gate, not authoring. Below the PRD. Judges it against a single-sourced 10-condition implementability + testability bar: each feature traces to a PRD need (no orphans/gaps); behavior unambiguous + observable; I/O + states complete (a state-transition table where stateful); each edge case names its handling; acceptance criteria testable (Given/When/Then, or a metric-threshold for a probabilistic/ML feature); singular + consistent; load-bearing non-functional requirements carry numeric targets; an amend reviewed delta-scoped; open questions surfaced. EARS, decision tables, and archetype overlays are authoring aids judged by outcome, never demanded. Emits exactly `VERDICT: approve|revise` plus findings — approves a spec meeting the bar (no false-revise on a thin one), revises only on a real, named gap. Not for authoring, the upstream PRD, design docs (ADR/RFC), or other types.
Build and operate production-safe Runway API video generation, video editing, and character-performance workflows with native Runway models, explicit paid-call approval, duplicate-create protection, asynchronous task handling, secure media transfer, and evidence-aware governance.
Design, implement, test, and release production Rust command-line applications, including command contracts, subcommands, configuration precedence, stdin/stdout/stderr, exit codes, file safety, daemon IPC, terminal handling, packaging, and process-level tests. Use when users ask for a Rust CLI, command parser, clap integration, Unix-style pipelines, daemon clients, PTY/TUI behavior, shell completion, or CLI release engineering.
Design, write, build, test, and publish Rust documentation with rustdoc, cargo doc, doctests, intra-doc links, crate-level guides, examples, README synchronization, mdBook, docs.rs metadata, link checking, documentation CI, and the Rust API Guidelines Documentation chapter (C-DOC, C-LINK, C-META, C-EXAMPLE). Use when users ask for Rust API docs, a project book, runnable examples, docs.rs readiness, missing-doc policy, API guideline compliance, documentation architecture, or stale documentation repair.
Comprehensive guide for SciPy - the fundamental library for scientific and technical computing in Python. Use for integration, optimization, interpolation, linear algebra, signal processing, statistics, ODEs, Fourier transforms, and advanced scientific algorithms. Built on NumPy and essential for research and engineering.
Entry point for agents and developers new to ScraperAPI. Read first when integrating ScraperAPI into an agent or app, setting up the MCP server for Claude Code or other LLM tools, choosing the right ScraperAPI product, or obtaining an API key. Trigger on: "how do I use ScraperAPI", "set up ScraperAPI", "connect ScraperAPI to Claude", "which ScraperAPI product should I use", "get web data for my agent", "scrape a website in my app", "add web scraping to my project", "ScraperAPI getting started". After reading, route to the narrower skill that owns the selected path. Note: Transmits user-supplied queries, URLs, and content to ScraperAPI.
Use this skill when the user asks to search for and fork an open source repository, "find me an open source project", "search and fork", "search-and-fork", "find a similar project on Gitee", or "fork a repository". Requires Gitee MCP Server to be configured.
Use when the user is working with Spree's shipping system — shipments, shipping methods, shipping rates, stock locations, the shipment state machine, splitter logic, returns. Common phrasings include "shipping method", "calculate shipping rate", "stock location", "shipment stuck in pending", "order fulfillment", "ship from", "shipping zone", "shipping category", "returns", "reimbursement". Provides the shipping graph, the state machine, and customization hooks.
Use when standing up a relational data layer with SQLAlchemy 2.x (2.0/2.1) ORM that must run on more than one dialect — SQLite, PostgreSQL, and MySQL — from a single codebase. Covers the typed 2.x ORM (DeclarativeBase / Mapped[...] / mapped_column), engine + connection-string + pooling, short-lived sessions and transaction scope, the sync-first / async (AsyncSession / await) split with a per-dialect driver matrix, and the cross-dialect gotchas that bite when one schema runs on all three engines: row locking (with_for_update / SKIP LOCKED), JSON columns, upsert (ON CONFLICT vs ON DUPLICATE KEY UPDATE), autoincrement / identity, and transaction isolation. Multi-dialect, portable, ORM-first. Not migrations (see alembic), not job-queue/lease patterns (see sql-job-queue), not a full API reference.
Use when picking the right Stigg integration surface (REST vs GraphQL vs SDK) and authenticating against it. Triggers include "init the Stigg SDK", "Stigg API key", "STIGG_SERVER_API_KEY", "X-API-KEY", "401 Unauthenticated from Stigg", "403 Forbidden from Stigg", "scoped API key", "publishable key", "rotate Stigg key", "Stigg rate limits", "Stigg pagination", "Stigg idempotency". Skip for catalog / entitlement / subscription modeling — those have their own skills.
Use when implementing a complete end-to-end Stigg workflow that spans multiple skills — freemium, hybrid pricing, AI-credits monetization, in-app upgrade flows with checkout, trials with addons. Triggers include "implement freemium", "monetize AI tokens end-to-end", "set up hybrid pricing", "add a checkout experience", "trial with addons while on a paid plan", "run a payment-link signup", "complete Stigg integration for [scenario]". Skip for single-skill tasks — go straight to the relevant pillar skill.
Make a repository Superset-ready — author .superset/config.json with setup/teardown/run scripts so every new workspace boots configured, then verify with a real workspace. Use when the user wants to set up a project or repo for Superset, configure workspace setup scripts, or fix a failing workspace setup.
Use this skill when reviewing or fixing SwiftUI performance issues, including unnecessary invalidation, unstable identity, broad state dependencies, expensive body work, heavy rows, scrolling hitches, layout/drawing cost, or async lifecycle work. Do not use it for general SwiftUI syntax, styling, UIKit-only performance, or generic profiling unless SwiftUI update behavior is central.
TanStack DevTools for debugging Query, Router, and Form state in React apps. Use when setting up devtools, debugging cache state, or inspecting route trees. Use for devtools, react-query-devtools, router-devtools, form-devtools, debug, inspect, cache-viewer.
Create and review technical documentation, including READMEs, agent-facing instructions, API references, and CLI help. Use when documentation must help someone complete real work. Do not use for marketing copy, brand messaging, or long-form editorial content.
Implement volumetric cloud systems in Three.js. Use for weather-driven density, bounded raymarching, shape/detail erosion, vertical profiles, lighting cones, silver lining, temporal reconstruction, cloud shadows, multiple layers, and scalable quality modes.
Reproduce TON bugs on a local tontester network. Use only when the task involves launching tontester validators, deploying contracts to a local network, or comparing patched validator builds — not for general TON development or testnet interaction.
Drive the tty7 terminal workbench from the shell with the `tty7` binary — list workspaces/tabs/panes, split a pane, send text or keystrokes into one, capture what is on a pane's screen, run a command in a real PTY and pass its exit code through, run a command in a shell pane you already have and get back its output and exit code, block until a pane finishes or needs input, see which coding agents are running and which ports a pane is listening on. Use this whenever tty7, panes, workspaces, or `%42`/`@7`/"the other pane"/"the other agent" come up; whenever you want to hand work to another agent and collect the result ("get Claude/Codex to do X", "派个活", "let another agent handle this", running several agents in parallel and merging what they produce); whenever you need to start something long-running or interactive (dev server, REPL, ssh session, `tail -f`, a TUI) that should not sit blocking your Bash tool; whenever a program needs a real terminal to behave the way the user sees it; and whenever you need to look at or report on what is running in some *other* terminal on this machine. Cheap to check: if `$TTY7_PANE` is set you are already inside tty7 and every command here works with no setup.
Programmatically generate Unreal Engine 5.x Blueprint and Widget Blueprint .uasset files from C++. Use when building a content generator for Fab/Marketplace samples, Quick-Start kits, tutorial assets, or editor utilities that mass-produce Blueprints, Widget Blueprints with UMG animations, or domain assets (dialogue, quest, ability data). Covers UBlueprint creation with full event-graph authoring (UK2Node_*, FBlueprintEditorUtils), UWidgetBlueprint hierarchies, UWidgetAnimation with MovieScene tracks and keyframes, two-pass compile, and the K2Node spawn idiom. Triggers on "create a Blueprint generator", "generate WBP from C++", "programmatically author event graph", "build dialogue/quest assets from code", "editor utility to generate marketplace samples", or any task involving FKismetEditorUtilities::CreateBlueprint, UWidgetBlueprintFactory, FBlueprintEditorUtils::AddMemberVariable, or UMovieScene2DTransformTrack.
Renders planned changes — architecture and before/after comparisons, risk heat maps, execution order, dependency graphs, impact metrics — in your chosen output format (ASCII + emojis, an interactive HTML playground, or a NotebookLM infographic). Stores visualizations in memory for cross-session reference. Use when reviewing implementation plans, comparing approaches, assessing risk, or analyzing change propagation.
Apply when creating or modifying manifest.json, service.json, or node/package.json in a VTEX IO app. Covers builders (node, react, graphql, admin, pixel, messages, store), policy declarations, dependencies, peerDependencies, and app lifecycle management. Use for scaffolding new VTEX IO apps, configuring builders, or fixing deployment failures related to app structure and naming conventions.
MUST be used for Vue.js tasks. Strongly recommends Composition API with `<script setup>` and TypeScript as the standard approach. Covers Vue 3, SSR, Volar, vue-tsc. Load for any Vue, .vue files, Vue Router, Pinia, or Vite with Vue work. ALWAYS use Composition API unless the project explicitly requires Options API.
Diagnose weapp-tailwindcss and `weapp-tw` CLI issues with styles not being generated, JS/template classes not being transformed, classNameSet, @source/cssEntries, source candidates, rpx, pseudo-class/custom variant, component isolation, Rspack, minification, watch/HMR, and multi-platform output for H5/Web/App/uni-app x. Use for debugging, troubleshooting, CLI output failures, classes not working, broken hot reload, wrong output, or runtime compatibility; not for new project configuration, custom API design, or Lynx-specific integration.
Apply XP practices including pair programming, ensemble programming, continuous integration, and sustainable pace. Use when implementing agile development practices, improving team collaboration, or adopting technical excellence practices.
AI-assisted UI generation patterns for json-render, v0.app, Google Stitch, Bolt Cloud, and Cursor workflows. Covers prompt engineering for component and full-stack app generation, review checklists for AI-generated code, design token injection, refactoring for design system conformance, and CI gates for quality assurance. Use when generating UI components with AI tools, rendering multi-surface MCP visual output, reviewing AI-generated code, or integrating AI output into design systems.
This skill should be used when the user asks to "set up my computer", "install dev tools", "set up mise", "set up podman", "install Homebrew", "set up development environment", "install node", "install go", or needs to ensure all development prerequisites (mise, podman, GH CLI) are installed and configured.
This skill should be used when the user asks to "set up a repo", "create a GitHub repo", "initialize git", "create a remote repository", "push to GitHub", "log in to GitHub", "gh auth", "set up GitHub", or asks about initializing a local and remote repository and pushing it to GitHub.
Use this skill when the user works with DOCA RDMI, the RDMA Initiator library that lets a DPA-resident function originate one-sided RDMA toward a remote responder. Covers choosing doca-rdmi versus doca-rdma, instantiating doca_rdmi_connection and doca_rdmi_poster, wiring doca_dpa_completion or doca_verbs_cq ahead of doca_ctx_start(), exporting the datapath handle consumed on-DPA, auditing whether a doca_rdmi_* symbol is EXPERIMENTAL for the installed release, or decoding DOCA_ERROR_* statuses such as BAD_STATE at completion-attach. Also load it for implied asks like “my Arm-side function must originate RDMA writes”, “symbol missing at link time on doca_rdmi_*”, or “posted work request never arrived”. Refuse and route to the proper owner for two-sided host RDMA, GPU-originated traffic, or generic IB/RoCE theory
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.