Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Repo-local workflow skill for large coding tasks. Initializes .agent/tasks/TASK_ID artifacts, installs project-scoped Codex and Claude subagents, updates AGENTS.md plus the repo's Claude guide file with the workflow, and runs a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.
Guides authorized reverse engineering—static and dynamic binary analysis, disassembly and decompilation workflows, protocol and file-format reversing, defensive malware analysis (behavior, IOCs, YARA ideas), firmware RE, patch diffing, and vulnerability research documentation. Emphasizes written authorization, export-control awareness, and no assistance bypassing protections on unowned or unlicensed software. Use for reverse engineering, disassemble, decompile, Ghidra/IDA-style workflows, binary analysis, malware analysis for defense, firmware RE, patch analysis—not disk imaging forensics (digital-forensics-analyst), live incident command (incident-responder), SOC alert triage (soc-analyst), authorized pentest exploitation (penetration-tester), LLM red team (ai-redteam), or CI pipeline gates (devsecops).
Reads GitHub and GitLab and constructs unexecuted forge payloads for the other RHDH skills: parse an issue, pull request, or merge request reference, fetch issue detail, resolve a plugin workspace, inspect checks or pipelines, read repository files, or build the exact command for a GitHub pull request, GitLab merge request, comment, label, assignee, approval, or /publish write. Use for a forge URL, a bare #number, a !number merge request, "which workspace is this issue in", a stale statusCheckRollup, "why did that check fail", or safe gh, glab, and jq command construction.
Converts a legacy Backstage frontend plugin used by Red Hat Developer Hub to the New Frontend System (NFS): replace createPlugin and createRoutableExtension with createFrontendPlugin, PageBlueprint, EntityContentBlueprint, AppDrawerContentBlueprint and createFrontendModule; map RHDH app-config.dynamic.yaml mount points onto extensions; add the ./alpha export to package.json without breaking legacy consumers; and verify the migrated dynamic plugin in a real RHDH instance. Use for "migrate my plugin to NFS", Blueprint migration, createFrontendPlugin, compatWrapper, alpha versus colocated exports, translations moved into a createFrontendModule with pluginId app, RHDH operator app.extensions and app.routes.bindings, and ENABLE_STANDARD_MODULE_FEDERATION testing.
Optimize Next.js App Router data fetching by converting slow client-side fetching to fast server-side fetching using React Server Components (RSC). Use when: - User reports slow initial page load with loading spinners - Page uses useEffect + useState for data fetching - StoreContext/useStore pattern causes waterfall fetching - Need to improve SEO (content not in initial HTML) - Converting "use client" pages to Server Components Triggers: "slow loading", "optimize fetching", "SSR data", "RSC optimization", "remove loading spinner", "server-side fetch", "convert to server component", "data fetch lambat", "loading lama"
Expert in the Yudao (芋道源码) ruoyi-vue-pro backend framework. Suitable for backend development tasks in Spring Boot monolith projects: module development, writing Controller/Service/Mapper/DO/VO, MyBatis Plus data access, permission control, multi-tenancy, data permissions, Excel export, scheduled tasks, and more.
Design Rust error types and panic policy — Result over unwrap, thiserror for libraries, anyhow for binaries, context that survives the call stack. Use when code calls unwrap or expect outside tests, when designing or refactoring an error enum, when choosing between thiserror and anyhow, or when the user asks how errors should be handled or propagated.
Rust performance optimization covering memory allocation, ownership efficiency, data structure selection, iterator patterns, async concurrency, algorithm complexity, compile-time optimization, and micro-optimizations. Use when optimizing Rust code performance, profiling hot paths, reducing allocations, or choosing optimal data structures. Complements the rust-refactor skill (idiomatic patterns and architecture). Does NOT cover code style, naming conventions, or project organization (see rust-refactor skill).
Profile before optimizing, cut allocation out of hot paths, and treat LTO, codegen-units, PGO and target-cpu as the last five percent. Use when Rust code is too slow, when a benchmark regresses, when reviewing code that allocates or formats inside a loop, when release-profile or codegen flags come up, or when the user asks how to make Rust faster.
Spectacle, budgeted. Scroll-driven animation with native CSS first and GSAP ScrollTrigger when needed, smooth scrolling with Lenis and when to turn it off, split-text reveals, pinned scenes, canvas and WebGL on a performance budget, shaders as material, pausing off-screen, loading strategy, and the reduced-motion and no-JS fallbacks that keep the page readable. Use for marketing pages, portfolios, launches and hero sections. Never for product UI.
Guided entry point for using Sentry through your agent. Orients you to your current setup and, for a new project, sets up Sentry end to end with sane defaults — provision a project, install the SDK (errors, tracing, and whatever it enables by default), and confirm real telemetry reaches Sentry. Routes other intents (adding more signals, fixing issues) to the right skill.
Orchestrate any code change from requirements to review-ready branch — scope-calibrated from small fixes to full features. Composes /spec, /implement, and /research with depth that scales to the task: lightweight spec and direct implementation for bug fixes and config changes, full rigor for features. Produces tested, locally reviewed, documented code on a feature branch. The developer pushes the branch and creates the PR. Use for ALL implementation work regardless of perceived scope — the workflow adapts depth, never skips phases. Triggers: ship, ship it, feature development, implement end to end, spec to PR, implement this, fix this, let's implement, let's go with that, build this, make the change, full stack implementation, autonomous development.
Verify exact SillyTavern, Tavern Helper / JS-Slash-Runner, STScript, macro, prompt-injection, worldbook, EJS, MVU, and runtime-library capabilities before implementing or reviewing rolecard automation. Use when a task depends on a function signature, event payload, slash-command grammar, variable scope, message-floor operation, generation option, runtime-symbol provider, Git/CDN loader, or version-sensitive extension capability.
Use when writing SpacetimeDB C# or Unity clients, generated C# bindings, connection setup, subscriptions, cache access, reducer invocation, callbacks, or identity handling. Triggers on: C#, CSharp, Unity, C# SDK, generated C# bindings, Unity SDK, C# subscription, C# reducer call.
Write approved implementation plans in one of two modes. Explicit Inline mode creates a conversational plan for bounded work. Spec-backed Plan converts an approved design.md into plan.json. Both modes stop after producing their plan output. Trigger after atelier-orchestrator selects a mode, when the user asks to plan work, or after spec-brainstorm completes. Direct invocation without a selected mode uses Spec-backed Plan. Do NOT use for research or execution.
Check whether a named implementation specification is ready to hand to an implementer without forcing them to invent structural contracts. Use explicitly before implementation handoff to return READY or root-complete NOT READY blockers. Do not use as a runtime correctness or PR merge review.
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
Spring Batch for batch processing in Spring Boot 3.x. Covers Job, Step, ItemReader/Processor/Writer, chunk processing, job parameters, restart, skip/retry, partitioning, and monitoring. USE WHEN: user mentions "spring batch", "batch job", "ETL Spring", "ItemReader", "ItemWriter", "chunk processing", "job scheduling Spring" DO NOT USE FOR: real-time processing - use streaming, simple scheduled tasks - use `spring-scheduling` instead
Write code against the Subconscious API. Use when the user wants to: call the Subconscious API, use the OpenAI SDK with Subconscious, use tim-qwen3.6-27b, use api.subconscious.dev, build a chat app on Subconscious, configure thinking / enable_thinking, structured output via response_format, OpenAI function tools, stream chat completions. Do NOT use for OpenAI/Anthropic-only tasks unrelated to Subconscious.
Agent development workflow and discipline skills. Use when developing features, debugging issues, managing code branches, writing plans, or ensuring code quality through TDD and systematic processes. Triggers on any software development task that benefits from structured workflows.
Use when the user needs to generate or validate Protheus data dictionary configuration scripts -- covering SX2 (table headers), SX3 (fields), SIX (indexes), SXG (field groups), SXA (form folders/tabs), SX1 (report questions), SX5 (generic tables), SXB (F3 lookup queries), and SX7 (triggers). Also triggers on Portuguese phrasing like "criar campo customizado", "cadastrar tabela customizada", "dicionario de dados", "criar indice SIX", "gatilho de campo", "tabela generica SX5", "consulta F3", or field-prefix names like ZA1/ZZ1.
Contributing to the Twenty codebase itself (twentyhq/twenty server internals), not for building apps on top of Twenty. Wire syncable entity services into NestJS modules, create service layer and resolvers for Twenty entities. Use when registering builders, validators, and action handlers in modules, creating business services, or exposing entities via GraphQL API with proper exception handling.
Create interactive 3D Circular Charts with Syncfusion ASP.NET Core. Implement pie/donut series, data labels, legends, tooltips, custom styling, titles, empty point handling, and print/export functionality. Use this skill when the user needs to build or configure pie charts, donut charts, circular data visualizations, or charts showing proportional data in ASP.NET Core applications.
Creating and customizing Syncfusion Circular Gauge - a circular data visualization component for displaying numeric values. ALWAYS use this skill when users need to implement circular gauges, display metrics on a circular scale, configure gauge axes, add pointers or ranges, create data visualization gauges, customize gauge appearance, handle user interactions with gauges, or build dashboards with circular gauge components.
Implement Syncfusion ASP.NET Core ComboBox component for dropdown selection with filtering, data binding, and customization. Use this when creating dropdown controls, enabling user selection from lists, implementing autocomplete/search functionality, or handling cascading dropdowns. Covers installation, basic setup, data binding, filtering, templates, grouping, and advanced features.
Implement Syncfusion DropdownList component in ASP.NET Core immediately. Single selection control with data binding, filtering, grouping, templates, and accessibility features. Essential for building professional dropdown interfaces with server-side data binding.
Implementing Syncfusion HeatMap Chart component for ASP.NET Core Razor Pages. Use this skill ALWAYS when the user needs to create heat maps to visualize two-dimensional data, customize cells with gradients or fixed colors, configure axes with multiple types, add legends with flexible positioning, bind array or JSON data, enable tooltips and cell selection, create bubble heat maps, or customize appearance and styling. Essential for data visualization, pattern detection, and matrix visualization use cases.
Implement and configure Syncfusion ASP.NET Core ListBox component with selection controls. Use this when building selection interfaces with single/multiple modes, data binding, or advanced features. Covers ListBox implementation, selection state management, appearance customization, and user interaction handling.
Implement Syncfusion RangeNavigator (Range Selector) in ASP.NET Core applications for interactive data range selection and navigation. Use this skill when user needs to select data ranges, visualize time-series data with interactive sliders, add period selectors, customize range appearance, export range visualizations, or integrate range selection into dashboards and charts.
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.