Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Design, implement, debug, and harden integrations between AI agents and Bitrix24 REST API (webhooks, OAuth 2.0, scopes, events, batch, limits, REST 3.0). Use whenever the user wants to connect an AI assistant or agent to a Bitrix24 portal or act on one — for example create or update a lead, deal, contact or company; find duplicate contacts; log a call or activity; move a deal stage; generate a quote or invoice; attach products; send a chat message or user notification; build a chat-bot; manage tasks, projects or templates; upload files; run a business process; sync offline events; pick webhook or OAuth; or resolve Bitrix24 API errors (WRONG_AUTH_TYPE, QUERY_LIMIT_EXCEEDED, expired_token) and performance issues — even if Bitrix24 is not named explicitly. Do NOT use for other CRMs (Salesforce, HubSpot, amoCRM, Pipedrive, Zoho) — those have their own skills.
Use this skill when writing, running, or debugging tests for BoxLang applications using TestBox: BDD-style describe/it specs, xUnit-style test classes, expectations (expect/toBe matchers), assertions ($assert), life-cycle methods (beforeAll/afterAll/beforeEach/afterEach/aroundEach), MockBox mocking (createMock/prepareMock/$()/$results()), mock data generation (mockData()), async testing, exception testing, focused/skipped specs, attaching files to specs (attach()), spec retries (it retries argument, retries annotation, --retries), rerunning only failures (--failed, the Run Failed button of the HTML reports, TestResult.getFailedTargets()), choosing reporters (HTML reporters with Run Failed and Ask AI, the Agent reporter for AI agents), and running tests via the BoxLang CLI runner. For browser tests (the @browser annotation, ColdBox BaseTestCase with @browser) also load bx-playwright-testing.
This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature requests, or when the user's request has multiple valid interpretations that need clarification.
Browser automation with two engines: agent-browser CLI (default for interactive work — navigate, snapshot, click, fill, screenshot, diff) and Playwright scripts (for compound operations — console/network capture, a11y audits, video recording, responsive sweeps, GIF pipeline, shadow DOM piercing). Triggers: browser automation, web test, screenshot, responsive test, test the page, automate browser, headless browser, UI test, console errors, network inspection, accessibility audit, a11y test, performance metrics, video recording, browser state, page structure, authenticated testing, annotated gif, dialog handling, tracing, pdf generation, shadow DOM, web components, DOM stabilization.
End-to-end development lifecycle for AI coding agents — scaffold projects, plan and build features, create Linear tickets, open and review PRs, clean up after merge, audit codebases, and improve UI polish/motion quality. Works with any agent that reads CLAUDE.md or AGENTS.md. Use when starting a project, implementing a feature, shipping code, addressing PR reviews, merging, auditing code quality, designing or reviewing UI polish, or reviewing animations.
Use Catsu for unified, high-performance embedding API calls across 11 providers (OpenAI, VoyageAI, Cohere, Jina, Mistral, Gemini, Together AI, Mixedbread, Nomic, DeepInfra, Cloudflare) through a single consistent interface. Covers model selection and discovery, automatic retry with exponential backoff, cost and token tracking, Matryoshka dimension reduction, input type hints (query vs document), async/await support, and per-request API key overrides. Use when: generating embeddings, comparing embedding providers, building search or RAG systems, or integrating embeddings into Python or Rust applications.
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
Use when a user's request is vague, ambiguous, or underspecified. Explores the codebase first, then runs an iterative Q&A loop grounded in the findings until ambiguity is gone. Outputs a clear, well-scoped context brief so the user can plan sharply. Triggers on "I want to...", "I need...", "let's build...", "can you help me...", "we should...", or any request where the full scope isn't immediately clear.
Build with Claude Messages API using structured outputs (v0.69.0+, Nov 2025) for guaranteed JSON schema validation. Covers prompt caching (90% savings), streaming SSE, tool use, model deprecations (3.5/3.7 retired Oct 2025). Use when: building chatbots/agents with validated JSON responses, or troubleshooting rate_limit_error, structured output validation, prompt caching not activating, streaming SSE parsing.
Design, explain, audit, or redesign a command-line interface through the CLI design delivery framework, for people, scripts, and agents that call it. Use when designing a new CLI or new commands, reviewing an existing CLI's commands, flags, output, errors, or help, restructuring or renaming a command tree, or deciding one question such as a command's name or a flag's shape.
Use when running a CloudCannon site locally with `cloudcannon dev` — starting the local editing loop so the user can edit in the CloudCannon editor and see the site rebuild, choosing the build command per SSG, and reading the `/__api` surface the server exposes
Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Includes critical guidance on choosing between Agents SDK (infrastructure/state) vs AI SDK (simpler flows). Use when: deciding SDK choice, building WebSocket agents with state, RAG with Vectorize, MCP servers, multi-agent orchestration, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors.
Build durable, long-running workflows on Cloudflare Workers with automatic retries, state persistence, and multi-step orchestration. Supports step.do, step.sleep, step.waitForEvent, and runs for hours to days. Use when: creating long-running workflows, implementing retry logic, building event-driven processes, coordinating API calls, scheduling multi-step tasks, or troubleshooting NonRetryableError, I/O context, serialization errors, or workflow execution failures. Keywords: cloudflare workflows, workflows workers, durable execution, workflow step, WorkflowEntrypoint, step.do, step.sleep, workflow retries, NonRetryableError, workflow state, wrangler workflows, workflow events, long-running tasks, step.sleepUntil, step.waitForEvent, workflow bindings
CloudBase Run backend development rules (Function mode/Container mode). Use this skill when deploying backend services that require long connections, multi-language support, custom environments, AI agent development, or migrating existing/GitHub apps that need VPC access to MySQL/PostgreSQL/Redis. Also use when diagnosing CloudRun container deploy failures (deploy_failed, readiness/probe failed, image won't start, docker.io pull loops) or a deploy stuck behind a running deploy task. For stateless HTTP services, prefer HTTP cloud functions.
Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Guide for authoring Convex components - isolated, reusable backend modules with their own schema and functions. Use when building reusable libraries, packaging Convex functionality for NPM, creating isolated sub-systems, or integrating third-party components. Activates for component authoring, convex.config.ts setup, component testing, or NPM publishing tasks.
Build a Crowdin app end to end and leave the user with a published app they can click — scaffold it with @crowdin/serverless-apps-cli, write the UI with @crowdin/serverless-apps-sdk, publish it into their Crowdin or Crowdin Enterprise organization, and open it for them. Use whenever someone wants something of their own inside the Crowdin UI — a panel in the translation editor, a tool or report in a project, a page in the organization menu, a dashboard over their projects — and also when they describe a localization chore they are tired of doing by hand. Covers phrasings like "create a Crowdin app", "add a tool to my Crowdin project", a bare "/create-app", and cases where the word "app" is never said. Also use it when a serverless Crowdin app already exists in the working directory and needs another module, a manifest change, or a republish. Not for the separate Crowdin CLI that syncs sources and translations through crowdin.yml.
Use when building a custom scaffolder template action — a step that scaffolder templates can call from their YAML steps. Covers createTemplateAction with Zod input/output schemas, the action handler context (logger, workspacePath, input, output, etc.), and module wiring via scaffolderActionsExtensionPoint. Triggers on phrases like "scaffolder action", "template action", "custom action".
Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Includes tech debt analyzer, team scaling calculator, engineering metrics frameworks, technology evaluation tools, and ADR templates. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.
Architecture and hard-won debugging lessons for customization enablement (plugins, MCP servers, agents, skills, instructions) in the agent host. Use when changing how customizations are discovered, published, enabled/disabled, or handed to a provider SDK; when a customization shows the wrong enabled state in the UI; or when a disabled MCP server or plugin is still reaching the model.
A flexible library for parallel computing in Python. It scales Python libraries like NumPy, pandas, and scikit-learn to multi-core systems or distributed clusters. Features lazy evaluation and task scheduling for data that exceeds RAM capacity. Use for out-of-core computing, parallel processing, distributed computing, large-scale data analysis, dask.array, dask.dataframe, dask.delayed, dask.bag, task scheduling, lazy evaluation, and scaling beyond memory limits.
Guide for making changes to the database schema, validation, types, and data access layer. Use when adding tables, columns, relations, or modifying the data model. Triggers on: add table, add column, modify schema, database change, data model, new entity, schema migration.
Build virtualized data tables with @virtuoso.dev/data-table. Use this skill when (1) building a data grid with sorting, filtering, or grouped rows, (2) installing the shadcn-styled or headless table, (3) connecting remote/paginated data sources, (4) adding sticky, resizable, reorderable, or hideable columns, (5) persisting table state, (6) controlling a table from outside (scrolling, actions), (7) migrating from TableVirtuoso, or any task involving VirtuosoDataTable, DataTable, DataTableColumn, localModel, remoteModel, or engine refs like scrollToRow$ and dispatchModelAction$.
Create or regenerate a repository's own development container with devcontainer-kit — .devcontainer/devcontainer.json, docker/local/<service>/Dockerfile (official runtime image pinned by digest, DeepWorkPlan Vim, Herdr, coding agents through agentkit), docker/local/docker-compose.yaml and dev.sh — then prove it with a real build. Use only when the user asks for a dev container, a devcontainer, a docker/local/<service>/Dockerfile or a `dev.sh up` container for a repository, or to regenerate or upgrade one made by devcontainer-kit. Do not use for production images, deployment, Kubernetes, CI runners, or merely because a repository contains a Dockerfile.
This skill should be used when cleaning up codebases that have accumulated dead code, redundant implementations, and orphaned artifacts — especially codebases maintained by coding agents. Triggers on "find dead code", "clean up unused code", "remove redundant code", "prune this codebase", "dead code sweep", "code cleanup", or when a codebase has gone through multiple agent-driven refactors and likely contains overlooked remnants. Systematically identifies cruft, categorizes findings, and removes confirmed dead code with user approval.
Use early when debugging a medium or hard bug, especially when tests alone may not reveal the real runtime failure. Trigger this before extended TDD iteration when a bug involves runtime state, ordering, persistence, streaming, concurrency, UI/manual reproduction, external services, or when a red or newly passing test may not model the real issue. Skip only when the root cause is already directly proven by a stack trace or deterministic test that exercises the real runtime path.
Use when writing or reviewing Python code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribe_url` / `transcribe_file` (REST) and `client.listen.v1.connect` (WebSocket). Use this skill for basic ASR; use `deepgram-python-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-python-conversational-stt` for turn-taking v2/Flux, and `deepgram-python-voice-agent` for full-duplex assistants. Triggers include "transcribe", "live transcription", "speech to text", "STT", "listen endpoint", "nova-3", "listen.v1".
Design an agentic AI architecture from a use case and produce a dated design document. Use when the user wants to design or architect an agent or multi-agent system, decide single vs multi-agent, choose where to place memory, human-in-the-loop, or evaluation, or asks how to build an agent for a specific use case.
Edit and review developer documentation for technical accuracy, completeness, structure, clarity, brevity, peer feedback, technical review, technical verification, QA procedure testing, and feedback integration. Use when reviewing, editing, refactoring, or preparing developer docs for release, especially docs with procedures, examples, prerequisites, or high-risk technical claims.
Dibbla CLI for scaffolding projects, deploying apps, managing apps/databases/secrets and multi-service `dibbla.yaml` manifests, authoring and operating workflows (slim YAML; `wf execute` sync/`--async`/`--follow`; `wf logs <runId>`, `wf runs list/output` for run monitoring), building Go workers via `github.com/dibbla-agents/sdk-go`, and running `dibbla-task.yaml` pipelines (`dibbla run`).
You are a documentation expert specializing in creating comprehensive, maintainable documentation from code. Generate API docs, architecture diagrams, user guides, and technical references using AI-powered analysis and industry best practices.
Build and sharpen a project's domain model and ubiquitous language. Use when discussing codebase or domain terminology, writing or editing `CONTEXT.md`, recording or editing an ADR, or when the user wants glossary, bounded-context, or terminology cleanup.
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.