Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
This skill provides guidance for implementing headless terminal interfaces that programmatically control shell sessions. Use this skill when implementing terminal emulation, pseudo-terminal wrappers, or interfaces like BaseTerminal that require sending keystrokes and reading output from shell processes.
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
Model development orchestration Skill covering asset query, model training, inference deployment, and real-robot evaluation in any combination. Supports full end-to-end pipeline or partial stages (e.g., train+deploy only, deploy+eval only). When user requirements involve two or more stages, prefer this Skill over individual module Skills. Triggers include: "用XX机器人训练XX任务", "so101 插笔", "训练部署", "部署评测", "训练评测部署", "模型开发流程", "端到端训练", "训练推理评测", "只训练不评测", "训练完部署", "model workflow", "end-to-end training", "train and deploy", "deploy and eval".
Help a human understand and inspect completed AI-authored repository work through actual results, before-and-after explanations, and supporting evidence. Use when the user asks to understand the work before accepting it, examine assumptions beyond an AI summary, or resume a human review after switching tasks. Also use for explicit requests to judge unresolved product behavior. Ordinary change summaries, automated defect hunting, and non-repository content do not need this skill.
Covers all non-grid Ignite UI for Angular UI components: application scaffolding and setup, form controls (inputs, combos, selects, date/time pickers, calendar, checkbox, radio, switch, slider), layout containers (tabs, stepper, accordion, splitter, navigation drawer), data-display components (list, tree, card, chips, carousel, paginator, progress indicators, chat), feedback overlays (dialog, snackbar, toast, banner), directives (button, icon button, button group, ripple, tooltip, drag-and-drop), Dock Manager, Layout Manager, Tile Manager, and Charts. WHEN TO USE: users ask about any Ignite UI Angular component that is NOT a data grid, such as forms, dropdowns, pickers, dialogs, navigation, lists, trees, cards, charts, or initial project setup. WHEN NOT TO USE: data grids, tables, or tabular data (use igniteui-angular-grids); theming or styling (use igniteui-angular-theming).
Reference skill for building high-end interactive 3D websites (WebGL hero scenes, scroll-driven camera moves, product-style renders) using Three.js, React Three Fiber, drei, and GSAP ScrollTrigger — including retrofitting 3D into an existing site (restyle/redesign) without breaking its current routes, content, or accessibility. Use when the user wants to build, restyle, review, or debug a 3D/WebGL web experience — hero canvases, scroll-jacked sections, particle fields, instanced objects, hub/navigation scenes, or performance issues in a Three.js/R3F scene, on a new or existing project. Complements the frontend-design skill: frontend-design covers general UI/UX craft (layout, color, accessibility), this skill covers the 3D/WebGL implementation layer.
Execute one task file from docs/specs/<slug>/ end-to-end — ground in the PRD/TechSpec, implement only the slice, and hand back evidence under the execution mode's settlement contract. Starts immediately when assigned, with no confirmation prompt. Use when the user says "run task_03", "execute the next task", "pick up a task", or when an implementation loop or daemon assigns a task file from a spec folder.
Ink.js (React for CLI) design and implementation guide. Use when: (1) Creating or modifying Ink.js components (2) Implementing Ink-specific hooks (useInput, useApp, useFocus) (3) Handling emoji/icon width issues (string-width workarounds) (4) Building terminal-responsive layouts (5) Managing multi-screen navigation (6) Implementing animations (spinners, progress bars) (7) Optimizing performance (React.memo, useMemo) (8) Handling keyboard input and shortcuts (9) Testing CLI UI (ink-testing-library)
This skill should be used when the user asks about TUI input handling, raw mode, cbreak mode, terminal keyboard parsing, Esc vs Alt ambiguity, Ctrl-C, shortcuts, focus management, mouse events, scroll wheel, bracketed paste, paste safety, command palettes, forms, text editing, resize events, or keybinding design. PROACTIVELY activate for: raw mode, keyboard input, keybindings, mouse support, paste handling, focus model, terminal forms, text input, vim/emacs-style shortcuts, input conflicts, and cross-platform Windows/macOS/Linux input behavior. Provides: input architecture, shortcut rules, focus patterns, paste/mouse safety, and failure-mode triage.
Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API configuration", or "extend council".
Design and implement microinteractions, motion design, transitions, and user feedback patterns. Use when adding polish to UI interactions, implementing loading states, creating gesture-based interactions, designing hover/focus states, building notification/toast systems, adding scroll-triggered animations, implementing drag-and-drop, or creating delightful user experiences.
Before starting a Ralph RLM loop, interview the user to sharpen the goal, stress-test the design, and write an authored PLAN.md (goal, definition of done, milestones, open questions, invariants) that the loop can follow. Use when a user wants to plan, scope, or stress-test work before delegating it to the supervisor / start_loop, or whenever PLAN.md is still the placeholder bootstrap.
Inworld TTS API. Covers voice cloning, audio markups, timestamps. Use when integrating Inworld text-to-speech, cloning voices, adding audio markups (SSML-like), or aligning viseme timestamps. Keywords: Inworld, text-to-speech, TTS, voice cloning, visemes.
Java code quality with Checkstyle, SpotBugs, PMD, and SonarJava. Covers static analysis, code style, and best practices. USE WHEN: user works with "Java", "Spring Boot", "Maven", "Gradle", asks about "Checkstyle", "SpotBugs", "PMD", "Java code smells", "Java best practices" DO NOT USE FOR: SonarQube generic - use `sonarqube` skill, testing - use Spring Boot test skills, security - use `java-security` skill
Use when asked to update CHANGELOG.md, add an entry, write release notes, or cut a version section; or when user-facing changes land that it should record. Not when the file is auto-generated in another format, and not for performing the release itself.
Explain what a specific piece of code actually does for a given input by producing a step-by-step execution trace (interprocedural, with name resolution and type transitions). Trigger when the user is confused about behavior or asks why code produces X instead of Y — "walk me through this", "trace through X with input Y", "why does this return X", "what does yield-from do here", "explain the execution path". SCOPE HARD RULE: a specific function + a specific input scenario. If the user wants to find bugs without a scenario in mind, use logic-review; two-version comparison uses logic-diff; concrete failures use logic-locate; codebase-wide audit uses logic-health. Do NOT trigger for: finding bugs without a behavioral question, style or design discussion, or concept explanations not tied to specific code.
Locate the root cause of a CONFIRMED failure via backward-then-forward semi-formal tracing. Trigger when the user provides a stack trace, failing assertion, error message, or specific wrong-value observation — "find the bug", "this test is failing", "track down this crash", "why is this test failing", "KeyError at line 89", "expected 70, got 100", "NoneType has no attribute X", "cart empties when second tab opens". SCOPE HARD RULE: requires a concrete failure (exception, failing test, or specific wrong output). Vague suspicion without evidence uses logic-review; behavior explanation uses logic-explain; refactor comparison uses logic-diff; codebase audit uses logic-health. Do NOT trigger for: vague "what's wrong" without a concrete symptom, style questions, or performance issues.
Integrate the Ludeo SDK into a Unity (C#) game using the Ludeo Unity plugin. Sets up the package install + scripting defines, wires the SDK lifecycle through MonoBehaviour/scene flow, maps and implements game actions, maps and tracks GameObjects as attributes, restores state for playable Ludeos, verifies the integration, then widens capture/restore coverage and finalizes. Use when the user asks to integrate, install, add, set up, or wire up Ludeo into their Unity game.
Create, deploy, and operate Streamlit apps in PostHog via the streamlit-apps MCP tools — create an app, set its source, read and patch its code, start and stop its sandbox, poll status, list versions, delete, and share the app with humans via its PostHog URL. Use when asked to "create a streamlit app", "deploy a data app", "ship a dashboard app", "restart/stop my app", "why is my app not running", or "give me a link to the app".
Integrate the beta markstream-react package into a React 18+ or Next app. Use when Codex needs to add the React renderer, choose the root, `next`, or `server` entrypoint, import CSS correctly, choose between `content` and `nodes`, keep client boundaries safe, add renderer-local `streamingComponents` or `htmlComponents`, use parser transforms, or prepare a repo for `react-markdown` migration.
Use when writing, solving, or debugging MATLAB optimization code — formulating problems (optimproblem, optimvar, fcn2optimexpr), selecting and configuring solvers (fmincon, linprog, quadprog, intlinprog, lsqnonlin, ga, surrogateopt, optimoptions), or validating results (exitflag, convergence, constraint violations). Covers problem-based and solver-based approaches, solver tuning, and solution verification.
Guidance for consuming REST APIs in .NET MAUI apps. Covers HttpClient setup with System.Text.Json, DI registration, service interface/implementation pattern, full CRUD operations (GET, POST, PUT, DELETE), error handling, platform-specific clear-text traffic configuration, and async/await best practices. USE FOR: "REST API", "HttpClient", "call API", "GET request", "POST request", "API service", "JSON deserialization", "CRUD operations", "clear-text traffic", "consume API MAUI". DO NOT USE FOR: Aspire service discovery (use maui-aspire), authentication token handling (use maui-authentication), or local database storage (use maui-sqlite-database).
Generates Mermaid diagrams from codebases, topics, files, conversations, or specs. Supports flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, C4 architecture, mindmaps, Gantt charts, timelines, user journeys, gitGraphs, pie charts, quadrant charts, requirement diagrams, and beta types (xychart, sankey, block, architecture). Use when asked to create a Mermaid diagram, visualize a process or system, draw a flowchart, sequence diagram, class diagram, state machine, ERD, architecture diagram, mind map, timeline, Gantt chart, user journey, git branching graph, or any "diagram this" request.
Make a web app feel native on a phone—the small CSS and meta-tag fixes that separate “a website in a browser” from something that feels installed. Covers sticky hover states, tap highlight flashes, the 100vh bug, inputs that zoom the page, laggy taps, pull-to-refresh hijacking scroll, content under the notch, long-press selecting button text, carousels that scroll the wrong way, mismatched status bars, and the rule that you test on real hardware. Use when a web app is being built for or reviewed on mobile, when something “works in Chrome but feels wrong on my phone,” when building a PWA, a bottom sheet, a carousel, a full-screen layout, or any touch interaction. For motion itself use animate; for React Native use animate-expo.
Migrate a model from the latest vLLM upstream repository into the vllm-plugin-FL project (pinned at vLLM v0.13.0). Use this skill whenever someone wants to add support for a new model to vllm-plugin-FL, port model code from upstream vLLM, or backport a newly released model. Trigger when the user says things like "migrate X model", "add X model support", "port X from upstream vLLM", "make X work with the FL plugin", or simply "/model-migrate-flagos model_name". The model_name argument uses snake_case (e.g. qwen3_5, kimi_k25, deepseek_v4). Do NOT use for models already supported by vLLM 0.13.0 core, or for multimodal-only components that don't need backporting.
Optional, modular cleanups and style improvements to apply on new mo:core projects (or after mo:core migration). Covers import ordering, unused import cleanup, and single‑expression return removal, with detection checks and automation recipes.
Add or change a capability of a Boring app - an agent, a job, a chat, a tool, a view or a page - and decide whether to expose it in boring.json. Use when a task asks for a new agent or output field, a change to an agent's prompt, rules, model or output, work that runs several agents, a chat, a tool an agent or the hub calls, or a view the hub frames. Lists the files to create, the contracts to keep, the tests to run and the feature-map entry to update.
Next.js 15 API route patterns, NextRequest, NextResponse, error handling, maxDuration configuration, authentication, request validation, server-side operations, route handlers, and API endpoint best practices. Use when creating API routes, handling requests, configuring timeouts, or building server-side endpoints.
Apply Odoo 18-20 best practices for module architecture, ORM patterns, XML views, OWL components, security, testing, and performance, plus dev environment setup and an official documentation index. Use when developing, reviewing, or debugging Odoo custom modules or setting up an Odoo development environment.
Build AI applications with OpenAI Agents SDK - text agents, voice agents (realtime), multi-agent workflows with handoffs, tools with Zod schemas, input/output guardrails, structured outputs, and streaming. Deploy to Cloudflare Workers, Next.js, or React with human-in-the-loop patterns. Use when: building text-based agents with tools and Zod schemas, creating realtime voice agents with WebRTC/WebSocket, implementing multi-agent workflows with handoffs between specialists, setting up input/output guardrails for safety, requiring human approval for critical actions, streaming agent responses, deploying agents to Cloudflare Workers or Next.js, or troubleshooting Zod schema type errors, MCP tracing failures, infinite loops (MaxTurnsExceededError), tool call failures, schema mismatches, or voice agent handoff constraints.
Search OpenSearch documentation, blogs, and community forums. Use when the user asks about OpenSearch features, configuration, APIs, troubleshooting, k-NN, neural search, cluster settings, index mappings, query DSL, or any OpenSearch-related questions.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, goals/subtasks, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", "orca goal", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Run multiple AI coding agent sessions in parallel using git worktrees — each agent isolated in its own worktree, working on a separate branch. Use this skill whenever the user wants to: run two or more AI agents simultaneously on different features or bugs, set up isolated agent workspaces in the same repo, push parallel branches to GitHub and open/update PRs, coordinate between concurrent agent sessions, or clean up after merging. Triggers on: "parallel agents", "multiple agent sessions", "git worktree", "run agents in parallel", "work on two things at once", "isolated agent workspace", "spin up another agent", or any request involving simultaneous AI-assisted development streams.
Performance profiling — measures code execution time, DB call time, and identifies bottlenecks at both the application and database layer. Use when asked to "profile performance", "measure execution time", "find bottlenecks", "check response times", or "why is this slow".
Pick the right library for a given frontend task from a curated, opinionated list — numbers, OTP inputs, charts, command menus, virtualization, drag and drop, toasts, state, styling, and more. Only runs when explicitly invoked; it does not trigger on its own.
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.