Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update the model configuration. Covers models.json configuration, CI test matrix, and handle validation.
Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide, or a documentation page; wants to know which snippets in a Markdown file are broken or out of date; or asks for a snippet verification report. Don't use for running the project's test suite (run pytest directly), for checking code style or formatting (use `adk-style`), or for authoring a new runnable sample agent (use `adk-sample-creator`).
Give an AG2 `Agent` the ability to run shell commands. Covers `SandboxShellTool` (client-side `subprocess` via `LocalEnvironment`, works with any provider) and the provider-native `ShellTool` (OpenAI Responses execution). Use when the user wants the Agent to execute commands, build/test code, manage files, or operate on a workspace. Always pair with sandboxing — `allowed`, `blocked`, `ignore`, or `readonly`.
Plan and deliver repository-aware AI-assisted software work through Agile Iteration Method using intent discovery, PO-owned Epics, TDO-owned User Stories, cross-Epic delivery planning, explicit gates, review, validation, and user-owned acceptance. Use for discussing product direction with repository context, creating and refining Epics and User Stories, planning delivery selections, implementing work, reviewing delivery, configuring project specialists, calibrating repositories and sharing local learning, consolidating knowledge across local AIM projects, controlling AIM modes and cost profiles, opening and controlling local AIM UI, and continuing AIM runs
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Omniscient APEX Ecosystem development skill. Triggers: apex code, omnihub development, tradeline build, aspiral feature, apex bug, fix apex, apex architecture, omnidash component, triforce guardian, man mode, apex security, apex test, armageddon test, apex deploy, apex optimize, semantic translation, web2 web3 bridge. Produces: zero-drift, first-pass success code for APEX OmniHub, TradeLine 24/7, aSpiral, and all connected applications. Compatible with all LLMs.
AI skill for building ApexCharts.js charts and data visualizations (targets v8). Use when the user asks to create, configure, or troubleshoot any chart using ApexCharts (line, area, bar, pie, donut, radialBar, scatter, bubble, heatmap, candlestick, boxPlot, violin, histogram, radar, polarArea, rangeBar, rangeArea, treemap, funnel, pyramid, gauge, sunburst, icicle, unit, waffle, waterfall, dumbbell, streamgraph, raincloud). Covers correct data formats, lifecycle, formatters, tree-shaking, SSR, and the feature platform (plugins, canvas renderer, custom series, small multiples, undo/redo, shareable views, themes, crossfilter, annotation authoring, storyboard, streaming, drilldown, highlight filter). Knows which chart types and features ship in the default v8 bundle and which need an explicit import or the full bundle. In React / Vue / Angular projects, prefer the framework wrapper packages (`react-apexcharts`, `vue3-apexcharts`, `ng-apexcharts`) over the core API
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.
Expert knowledge for Azure Horizondb development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when tuning pgvector, azure_ai SQL functions, LangChain vector stores, Apache AGE graphs, or hybrid search, and other Azure Horizondb related development tasks. Not for Azure Cosmos DB (use azure-cosmos-db), Azure SQL Database (use azure-sql-database), Azure Table Storage (use azure-table-storage).
Strip comments that do not earn their place. Spawns the Comment Reaper on the caller's files or the current diff, applies the accepted deletions, and fixes or reports the code the comments were covering for. Use when asked to banish comments, remove comments, clean up comments, decomment, or run /banish.
Scandit Barcode Capture (`BarcodeCapture`) in React Native projects—the low-level, full-control single-barcode scanning mode (BarcodeCapture + DataCaptureView + BarcodeCaptureOverlay), without the pre-built SparkScan UI. Use for integration, symbology configuration, result handling, viewfinder and feedback customization, SDK version migration, replacing a third-party scanner (react-native-vision-camera, expo-camera), or troubleshooting.
Takes existing content markdown files and builds production-final resource center pages on client websites using their existing tech stack and design system. Output is live-ready — no review pass, no placeholder content, no prototype styling. Implements hub pages, section listings, article pages, and cross-linking for Blog, Guides, Learn, and Comparisons sections.
Generates C4 model architecture diagrams using Structurizr DSL (primary) or Mermaid C4 (fallback). Use when: user asks to "draw a diagram", "create a C4 diagram", "show architecture as a diagram", "generate architecture diagram", "document the system". DO NOT USE for code explanation or walkthroughs (use `explain-code`), class/sequence/ER diagrams (C4 is system-architecture only), or when a diagram is incidental to a code change — only when a C4 diagram is the primary deliverable.
Implement one ready ticket or spec on the current branch, then open a pull request with visual evidence. Use when asked to cast a ticket, implement this ticket, build this issue, take the next ready ticket, or /cast. Pass next to claim the oldest unclaimed ready-for-agent issue, and no-pr to stop after the commit.
When writing Clojure code with unfamiliar Java interop or macros, use this skill to explore and gather context. For Java interop, search for Clojure wrapper libraries first (via WebSearch), then explore Java classes if needed. For macros, expand them to understand what code they generate. This prevents bugs from incorrect API usage. Use this skill when encountering Java classes or unclear macros.
Cloud object storage integration with AWS S3, Azure Blob Storage, and Google Cloud Storage. Covers presigned URLs, multipart uploads, bucket policies, lifecycle rules, and CDN integration. USE WHEN: user mentions "S3", "blob storage", "cloud storage", "object storage", "presigned URL", "file upload to cloud", "GCS", "Azure Blob", "bucket" DO NOT USE FOR: local file uploads - use `file-upload`; database BLOB columns; local filesystem operations
Provides comprehensive guidance for Cocos2d-x v4 game engine including scene graph, nodes, sprites, actions, animations, physics, rendering, shaders, and platform deployment. Use when the user asks about Cocos2d-x, needs to create games, implement game features, set up development environments, or deploy games to multiple platforms.
Integrate App Builder Database Storage (@adobe/aio-lib-db) into an Adobe Commerce app and scaffold a runtime action that reads and writes documents. Use when the user wants persistent, queryable storage backing a Commerce app — either from a web action (HTTP-invokable) or from an event/webhook handler. Requires a base app initialized with commerce-app-init.
Integrate Cartridge Controller into backend services using Node.js, Rust, or headless mode. Use when building server-side applications, game backends, automated bots, or any non-browser environment that needs to execute Starknet transactions. Covers SessionProvider for Node.js, Rust SDK setup, and headless Controller with custom signing keys.
Integrate Cartridge Controller into native mobile applications (iOS, Android, React Native) and web wrappers (Capacitor). Use when building mobile games or apps that need Controller wallet functionality with local keypair signing. Covers SessionConnector for native auth flows, Controller.c FFI bindings, passkey configuration with Apple App Site Association, and platform-specific setup.
Guide for convex-helpers library patterns including Triggers, Row-Level Security (RLS), Relationship helpers, Custom Functions, Rate Limiting, and Workpool. Use when implementing automatic side effects, access control, relationship traversal, auth wrappers, or concurrency management. Activates for triggers setup, RLS implementation, custom function wrappers, or convex-helpers integration tasks.
Create Architecture Decision Records (ADRs) to document significant technical decisions, their context, alternatives considered, and consequences. Use when making architectural choices, selecting libraries/frameworks, or designing system components.
Use CryptPad encrypted collaboration for integration, automation, and diagnosis with its browser integration API, instance discovery, document import/export, and session-key lifecycle. Use for CryptPad API feasibility, embedded editors, sharing, persistence, or self-hosted instance troubleshooting. Do not use for EncryptPad/OpenPGP, generic office-file conversion, or designing an unrelated collaboration service.
The 都爆鸭 platform's **invocation gateway** (infrastructure Skill, **does not handle business intent**): how to carry authentication, how to choose between the two non-fallback routes, how to decode the unified envelope and error codes, and one rule — **pull the input spec right before invoking**. Not responsible for writing articles / finding topics / making covers / checking prohibited words — those go through `dby`. Trigger words: doubaoya invocation protocol / invocation gateway / DOUBAOYA_API_KEY / operationKey / execution.target / inputContract / input spec / unified envelope / SKILL_NOT_FOUND / ENDPOINT_NOT_FOUND / DEDICATED_ROUTE / NO_RESULT / CAPABILITY_UNAVAILABLE / which route to hit; and when calling 都爆鸭 APIs: "401 / 404 / 429 error", "can't connect", "how to authenticate", "requestId".
Load PROACTIVELY when task involves investigating errors, diagnosing failures, or tracing unexpected behavior. Use when user says "debug this", "fix this error", "why is this failing", "trace this issue", or "it's not working". Covers error message and stack trace analysis, runtime debugging, network request inspection, state debugging, performance profiling, type error diagnosis, build failure resolution, and root cause analysis with memory-informed pattern matching against past failures.
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST via `client.speak.v1.audio.generate` and streaming WebSocket via `client.speak.v1.createConnection()` / `connect()`. Use `deepgram-js-voice-agent` when you need full-duplex STT + LLM + TTS instead of one-way synthesis. Triggers include "TTS", "text to speech", "speak", "aura", "streaming TTS", and "speak.v1".
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.
Review Effect v4 code, including beta, RC, and release versions, for correct error propagation, resource ownership, cancellation, concurrency, primitive selection, services/layers, schemas, atoms, observability, and tests. Use for requests such as "effect v4 review", "review my Effect 4 changes", "check Effect patterns", or "audit the Effect codebase" when the project uses v4. Supports files, working changes, PR/branch diffs, and repository audits. Reviews with one agent by default; delegation has an explicit total limit. Verify APIs against the installed version. For Effect v3 use effect-review.
Use when building Elementor addons, creating custom widgets, or managing Elementor components. Covers Widget_Base class (get_name, get_title, get_icon, register_controls, render, content_template), widget registration via elementor/widgets/register hook, addon structure and plugin header, wp_enqueue_script for widget assets, get_script_depends, get_style_depends, inline editing toolbars, custom widget categories, manager registration (register/unregister), selector tokens ({{WRAPPER}}), deprecation handling, and Elementor CLI commands.
Extract reusable components, product patterns, and design tokens into a clearer design system with shared APIs, documented defaults, and better reuse. Use when the user wants to refactor repeated UI, consolidate buttons/cards/forms/sections, build a component library, or turn one-off values into reusable tokens.
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.