Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Debug Clerk-delivered SMS (phone verification codes, OTPs) using the sms.* Application Logs. Understand the delivery lifecycle — sms.accepted, sms.delivered, sms.failed, sms.undeliverable, sms.unconfirmed — read the normalized failure reason, and follow one message across events by its trace. Use when a user reports "I never got the code", a phone number won't verify, or SMS delivery to a country/carrier looks broken.
Tambo CLI reference for project setup and component installation. Agent-friendly with non-interactive mode and exit codes. Use when running tambo init, tambo add, npx tambo commands, or browsing the component library. For guided project creation with tech recommendations, use start-from-scratch skill. For adding Tambo to existing projects, use add-to-existing-project skill.
Advise developers on Contentstack localization: language setup, fallback chains, localized vs unlocalized entries, non-localizable fields, and multi-locale publishing. Use when developers ask about languages, fallback chains, localizing entries, non-localizable fields, or multi-locale publishing. Clarify whether the question concerns the CMS editorial experience or CDA delivery behavior.
Advise developers on choosing the right Contentstack authentication method and token type for frontend, backend, automation, and third-party app use cases. Include security guidance, rate-limit awareness, and SSO considerations. Use when developers ask about authentication, token types, API keys, rate limits, SSO integration, or credential security.
Run code quality checks (ruff, mypy, pytest) and optionally simplify code. This skill should be used when the user wants to check code quality, run linters, run tests, or simplify recently modified code. Triggered by /lint, /check, or /code-quality commands.
Use when investigating the current state of a Datex Studio codebase with read-only inspection — answers questions about existing components, flow code, type definitions, datasource shapes, and configuration without modifying anything. Carries Datex Studio- specific patterns: extract flow code from `nodes[0].stepConfig.executeCodeConfig.code` (not from the JSON surface), delegate OData schema queries to `schema-explorer`, fetch enum values from `*-customType` configs on the branch via `dxs source explore`, return in `Answer / Sources / Caveats` format. Triggers: "research the codebase", "investigate how X works", "find where Y is defined", "answer questions about current code state". Consumed by impact-analysis, requirements-gathering, report-creator, and any skill needing grounded read-only inspection.
Validate commit messages against the Conventional Commits specification. Auto-detects and installs commitlint CLI if missing. Checks project config or falls back to sensible defaults. Use when validating commit messages, preparing PRs, or enforcing commit conventions.
Use when scaffolding a new Datex Studio component from a documented skeleton — maps a requested type to folder, suffix, configurationTypeId, minimal-valid skeleton, and matching creator skill. Owns scaffold-routing so creator skills stay focused on authoring their own type. After creating the minimal-valid skeleton on the branch via dxs, hands off to the matching creator (action-creator, function-creator, grid-creator, hub-creator, form-creator, editor-creator, embed-creator, selector-creator, storage-creator, type-definition-creator, backend-test-creator, datasource-creator) for body authoring. Triggers: "scaffold a new component", "create a new grid/hub/form/editor/embed/selector/storage/interface/enum/backendTest/action/function/datasource", "starter <type> file", "new <type> from scratch".
Language-level TypeScript conventions for every project, framework or not — compiler strictness, banning unsafe types, inference and `satisfies`, discriminated unions and branded ids, narrowing, generics, utility types, nullability, async, errors as `unknown`, module and language hygiene. The base skill that `react`, `angular`, `vue`, and `architecture-and-design` build on. Use it when writing, reviewing, or refactoring TypeScript, setting up `tsconfig.json`, or when the user says "TypeScript", "tsconfig", "strict mode", "type error", "any", "generics", "type safety", "utility types", "discriminated union", or "narrowing".
Datex Studio platform conventions for component file authoring: file format invariants (configurationTypeId table, file locations and suffixes, TS-expression encoding rule for declarative string slots, the `return;` outparam pitfall), naming conventions (per-component-type suffix indicators, tailored_/custom_ provenance prefixes, sentence-case display-text rule, user-facing `title` vs `referenceName` distinction), and defaults (package=Utilities, accessModifier=public, descriptions ≤100 chars and mandatory), plus the universal cross-cutting component checklist that validators and creators link. Not invoked directly — other skills link into the files below. Install this alongside any Datex Studio component-creator skill (action-creator, function-creator, grid-creator, hub-creator, form-creator, editor-creator, selector-creator, storage-creator, type-definition-creator, datasource-creator, backend-test-creator, tailoring-overlay) so cross-skill references resolve.
Datex Studio platform runtime semantics: platform-injected globals (`$flow`, `$datasources`, `$db`, `$shell`, `$frontendFlows`, `$operations`, `$apis`, `$flows`, `$types`, `$utils`, `$services.jobs`, `$editor`, `$datasource`), the three-tier execution model (functions / actions / UI components) and the caller→callee allow/deny matrix per tier, the generic CRUD action set in the Utilities package, and the `controlConfig.type` values used on field controls (codeBox, textBox, numberBox, dateBox, checkBox, selectBox, button, label, text, image, draw, progressBar, matrix) with sibling-config-block rules. Not invoked directly — other skills link into the files below. Install this alongside any Datex Studio component-creator skill (action-creator, function-creator, grid-creator, hub-creator, form-creator, editor-creator, selector-creator, storage-creator, db-query, tailoring-overlay) so cross-skill references resolve.
Diagnose Fireworks training and deployment issues, including stuck or failed jobs, error messages, poor quality, checkpoint and resume problems, LoRA adapter load mismatches, and deployments that are ready but not serving. Use for systematic read-only triage before retrying. Use configure for a new or approved retry run; use research when the starting method, data, or cookbook example is unclear.
Work with the app's code in Dessn's cloud when there is no local checkout. Find a screen from the person's words, find the code behind it, explain how it's built, change it on a copy, look at the result, put it on a board beside the original, and undo, all through the Dessn MCP. Use when the user has no code locally (a PM or designer with Claude Desktop, claude.ai or Claude Code in an empty folder) and wants to understand, change or explore a screen of their Dessn project, such as "where does this text come from", "change the copy on the pricing page", "how is the empty state built", "make this friendlier and show me".
Bring the user's local UI changes onto the Dessn canvas. Push the files changed in their working tree to a copy of a Dessn frame, see the result in a real picture, and put the routes they changed on a page. Use when the user codes locally (Claude Code, Codex, Cursor on their own checkout) and wants their change on Dessn, "show my local change in Dessn", "push this branch's UI to the canvas", or "make frames of what I changed".
Build and review HTMX interactions in Django server-rendered projects, especially generated django-saas-starter apps. Use when adding hx attributes, partial template responses, request.htmx branching, django-htmx response headers, forms, swaps, triggers, redirects, polling, boosted links or forms, or coordinating HTMX with Alpine.js local state.
Guide for implementing sortable and droppable components using dnd-kit library. Use this skill when building React applications that require drag-and-drop functionality with both container reordering (useSortable) and item dropping (useDroppable) capabilities, such as Kanban boards, file management systems, or playlist editors.
Improve source-code understanding with useful comments, API docs, or focused docs without changing behavior. Use when the user asks to document code, add comments or docstrings, or run a documentation pass over code or a diff; not for explanation-only requests.
Run after making Docyrus API changes to catch bugs, performance issues, and code quality problems. Use when implementing or modifying code that uses Docyrus collection hooks (.list, .get, .create, .update, .delete), direct RestApiClient calls, query payloads with filters/calculations/formulas/childQueries/pivots, or TanStack Query integration with Docyrus data sources. Triggers on tasks involving Docyrus API logic, data fetching, mutations, or query payload construction.
Build DSPy 3.2.x programs through spec, program, metric and baseline; extend to optimization and export when requested and justified by task budget. Orchestrates the other four DSPy skills (dspy-fundamentals, dspy-evaluation-harness, dspy-gepa-optimizer, dspy-rlm-module) in the correct order. Use for greenfield DSPy builds; prototypes may stop at a validated baseline.
Expert in optimizing the end-to-end developer journey. Specializes in Internal Developer Portals (IDP), DORA metrics, and on-call health. Use when improving developer experience, building internal platforms, measuring engineering productivity, or reducing developer friction.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Use when authoring or modifying a Datex Studio editor (configurationTypeId=4, *-editor.json suffix) on a branch — single-entity view/edit screen with embedded single-result datasource, onInit/onDataLoaded lifecycle, view/edit mode toggle, and save-button gating via onFormValidateFlowConfig. Triggers: "create an editor", "build a detail screen for X entity", "view/edit a single record", "add a field to xxx_editor", "add save/cancel buttons", "$editor.entity is undefined in onInit", "save button never enables".
Specialized agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. Use proactively when unfamiliar libraries or frameworks are involved, working with external dependencies, or needing examples from open-source projects to understand best practices and real-world implementations.
Set up the Fiddler Everywhere MCP server connection for AI agent tools (Claude Code, GitHub Copilot CLI, GitHub Copilot in VS Code, Cursor, OpenAI Codex CLI). ALWAYS use this skill when Fiddler MCP tools are not available, you cannot see Fiddler tools, get an authentication error connecting to Fiddler, need to configure Fiddler MCP for the first time, or hear "tool not found" errors when trying to use other Fiddler skills. Calls Fiddler's local autoconfigure API to detect existing config and write the correct settings automatically. The only prerequisite is that Fiddler Everywhere is running.
Use when authoring or modifying a Datex Studio form (configurationTypeId=5, *-form.json suffix) on a branch — transient-input collector, dialog opener, and validate-then-confirm workflow host. Owns the TypeScript-expression encoding for declarative string slots, declarative vs imperative init separation, dialog opener pattern, and confirm-button gating. Triggers: "create a form", "add a field to xxx form", "open a dialog that collects X", "a confirmation dialog with inputs", "validate-then-confirm workflow", "declarative binding is not populating the field", "confirm button always disabled", "dialog outParams are undefined on cancel".
Write minimal, accessible web UI without over-engineering, adapting to whatever stack the project uses — React, Vue, Svelte, Angular, web components, or plain HTML. Use this skill on every project and every task that writes or reviews markup or components, builds forms, adds interactive elements like buttons, dialogs, accordions, or tabs, or audits code for accessibility — even when the user never mentions accessibility, and even inside a framework, CMS, or design system. It's non-negotiable regardless of project type, stack, or deadline. About to reach for ARIA attributes, a dialog library, a focus-trap package, or a headless UI component? Use this skill first.
Guide for implementing Dify frontend query and mutation patterns with TanStack Query and oRPC. Trigger when creating or updating contracts in web/contract, wiring router composition, consuming consoleQuery or marketplaceQuery in components or services, deciding whether to call queryOptions()/mutationOptions() directly or extract a helper or use-* hook, configuring oRPC experimental_defaults/default options, handling conditional queries, cache updates/invalidation, mutation error handling, or migrating legacy service calls to contract-first query and mutation helpers.
Use when implementing OCI GenAI inference APIs, troubleshooting rate limits or token errors, optimizing GenAI costs, or handling sensitive data (PHI/PII) in prompts. Covers model selection, cost calculations, token management, response validation, and healthcare/compliance considerations.
Spec-first REST development in Go with OpenAPI: generating server interfaces and clients with oapi-codegen, request validation middleware, RFC 9457 error bodies, contract testing, and detecting breaking API changes. Use when the API has or should have an OpenAPI document, when wiring code generation into the build, or when a hand-written handler has drifted from its published contract. Trigger examples: "OpenAPI", "swagger spec", "oapi-codegen", "generate a client from the spec", "validate requests against the schema", "breaking API change". Not for: handler structure and shutdown (go-api-design), gRPC and protobuf (go-grpc), GraphQL schemas and resolvers (go-graphql).
Playbook for using lines-of-code (SLOC) as a north-star metric to genuinely simplify and improve an engineering solution — without gaming the number. Use when asked to "cut SLOC", "reduce/simplify the codebase", remove bloat/complexity/tech-debt, delete dead code or duplication, or hit a line-count target. Covers preflight (baseline + feedback loops + tooling), an honest reduction order, a self-audit against gaming, stop conditions, and a Flutter reference.
Expert Godot 4 game developer specializing in GDScript, the node/scene system, signals, resources, and engine-native patterns. Provides deep knowledge of Godot's unique architecture, performance optimization, and best practices for building games from simple prototypes to production-ready releases. Use when "godot, gdscript, godot 4, godot engine, build a game with godot, godot scene, godot node, godot signal, godot resource, godot tilemap, godot physics, godot animation, godot ui, godot multiplayer, godot, gdscript, game-engine, game-development, 2d-games, 3d-games, open-source" mentioned.
Use when authoring or modifying a Datex Studio grid (configurationTypeId=3, *-grid.json suffix) on a branch — the densest UI component. Owns the pre-author rows-source decision (owned vs standalone datasource, OData vs flow), the five-location dynamic-filter wiring rule, secondary enrichment datasources, imperative cell API, and the mandatory grid-validator gate after every edit. Triggers: "create a grid", "add a column to xxx grid", "make the grid filterable/sortable by X", "add a toolbar button", "add a filter", "enrich rows with extra data", "empty column", "dynamic filter contract mismatch", "grid renders blank", "tailored/custom grid variants", enrichment-datasource work.
Set up and improve Harness engineering for AI agent-friendly codebases (including AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering). Trigger scenarios: setting up a new/empty project for an AI agent, creating AGENTS.md or CLAUDE.md, questions about Harness engineering, making an agent work more efficiently on a codebase. Also triggers when the user is frustrated or complains about agent quality (e.g. 'the agent always ignores the spec', 'it never follows instructions', 'why does it always get X wrong', 'the agent is broken') — because poor agent output almost always means missing Harness, not a model problem. Covers: context engineering, architectural constraints, multi-agent collaboration, evaluation, long-running task Harness, the agent loop (autonomous operation, verifiers, stop conditions), agent memory (cross-session memory, memory stewardship), and diagnosing agent quality issues.
Harness Engineering phase 1: scan an existing project and generate AGENTS.md (a directory file) and a complete docs/ knowledge base structure. Use this skill immediately when the user wants to add agent support to a project, help AI understand my project better, start harness engineering, create AGENTS.md, set up an agent documentation structure, or make Claude Code work better. Also applies when the user says help me organize the project docs for agent use, I want to start developing with AI agents, sort out what business problems this project solves, or asks to create business-solution.md.
Home Assistant YAML configuration and automation. The most common skill for general HA questions. Covers automations, blueprints, scripts, scenes, template sensors, Lovelace dashboards, Mushroom cards, packages, helpers, presence detection, voice Assist, calendar automation, Jinja2 templates, notification patterns, energy monitoring, Matter devices, automation debugging and traces, dashboard sections view, and trigger-based template entities.
[Hyper] Use when working on Hono projects or adding Hono into a codebase. Enforces Hono architecture rules for app composition, scalable route modules, middleware, validation, database/ORM boundaries, Drizzle integration, migrations, error handling, OpenAPI/Swagger documentation, testing, and typed RPC boundaries before any code change.
Install Kunpeng DevKit in WebUI mode on Huawei Cloud. Create a Kunpeng (aarch64) ECS via Python SDK with random password, encrypt password via Python KMS SDK, use hcloud CLI for EIP/VPC operations, use Python paramiko SSH (password in process memory only) to install DevKit-All-x.x.x-Linux-Kunpeng.tar.gz, including framework and all plugins (porting/affinity/devtools/debugger/sys_perf/java_perf/sys_diagnosis). Use this skill when the user wants to install DevKit on a new Kunpeng ECS. Trigger: user mentions "DevKit", "Kunpeng DevKit", "install DevKit", "DevKit WebUI", "Kunpeng DevKit", "DevKit-All", "鲲鹏DevKit", "安装DevKit", "鲲鹏开发套件"
Build, customize, and debug advanced Hugo CMS themes — template architecture, asset pipeline (CSS/JS/image processing), shortcodes and render hooks, page bundles, cover images, Hugo Modules, performance, SEO, and CI/CD. Use when working on a Hugo theme or site template layer. Do not use this skill for unrelated requests; route to the nearest named specialist.
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.