Latest Agent Skills

Use to get access to Rulebase and connect an AI client to it — signing up, finding your data region, installing the Rulebase MCP server in Claude Code, Claude Desktop or Cursor, and creating an API key for the REST API. Trigger for "connect Claude to Rulebase", "install the Rulebase MCP", "set up the Rulebase connector", "create a Rulebase API key", "how do I sign up for Rulebase", "Rulebase returns 401", "no token provided", or when Rulebase tools are missing from a session.

Use to find cancellation, downgrade and switching intent in support conversations, and to be honest about how much of your churn support can actually see. Trigger for "which customers are at risk of leaving", "find cancellation intent", "customers asking how to export their data", "top reasons customers asked to close their account", competitor mentions, or building a churn early-warning signal from support data.

Use when answering difficult or disputed TypeScript questions about assignability, inference, narrowing, variance, generics, conditional or mapped types, declarations, or compiler-option semantics.

Align TypeScript module resolution, package exports, and declaration emit so that consumers can import the published artifact under every supported runtime and bundler.

Use when configuring or maintaining a TypeScript repository, package manager, tsconfig files, linting, formatting, testing, builds, workspaces, CI, or publishing automation.

Use when tightening annotations in existing TypeScript, removing avoidable any or assertions, improving changed-file types, or reducing compiler errors without broad refactoring.

Use when facing multiple implementation tasks that could benefit from parallelization or when deciding between solo, parallel agent, sequential subagent, or agent team approaches

Use when work requires inter-agent communication, cross-layer coordination, or configurable autonomy with Claude Code Agent Teams

Use when implementing or reviewing substantial TypeScript, designing public APIs, modeling domain state, validating runtime data, or refactoring project-scale TypeScript code.

Design, implement, and debug Python asyncio and concurrent code with structured concurrency, bounded parallelism, cancellation safety, timeouts, cleanup, and clear error propagation. Use for async workflows, task orchestration, or choosing among concurrency models.

Answer detailed or normative questions about Python's type system using the complete vendored typing specification. Use for subtle assignability, generics, variance, protocols, overloads, narrowing, qualifiers, TypedDict, or checker-semantics questions that exceed everyday annotation guidance.

Use when designing or implementing tests for TypeScript behavior, public types, compiler failures, filesystem or process boundaries, or package-consumer compatibility.

Configure and maintain Python projects, dependencies, packaging, environments, linting, formatting, type checking, testing, builds, and publishing. Use for pyproject.toml, an existing repository toolchain, or repository-level Python tooling work, not for a standalone script.

Use when writing zero-setup macOS utilities for Apple's /usr/bin/python3, Command Line Tools Python 3.9, standard-library-only execution, or integration with stable macOS command-line programs.

Tighten annotations in existing Python code with a focused, low-churn workflow based on Honnibal's tighten-types skill. Use to improve changed files, remove avoidable Any, make container and return types precise, or reduce type-checker errors without broad refactoring.

Use before any Bash command that invokes Python, including Bash(python3 ...), Bash(python ...), python3 -c, python -c, Python heredocs, and temporary .py helper files. Also use whenever an agent creates a one-off Python script to inspect, transform, validate, or summarize data during a coding session, even when the user did not ask for Python or for a script.

Use when formatting, linting, or type-checking standalone Python files that are not governed by a repository toolchain. Do not use for pyproject.toml or repository-level tooling work.

Apply opinionated, production-grade Python design and review standards. Use for substantial Python implementation, refactoring, API design, module design, exception boundaries, interfaces, or a deep code-quality review; not for a quick standalone script.

Design and implement robust Python tests with pytest, including unit and integration boundaries, fixtures, parametrization, failure cases, and optional property-based tests. Use when adding tests, repairing a test suite, or deciding how Python behavior should be verified.

Use when writing or editing typed Python scripts, parsing untyped input, choosing lightweight data shapes, or resolving common checker errors without project-scale type-system research.

Use when writing Textual TUI CSS styles or checking valid CSS properties

Use when working with Textual TUI widgets — looking up available components, reactive attributes, constructor parameters, or messages emitted

Use when the user says "task:", "fix:", "todo:", "log task:", "log fix:", "run task:", "run fix:", or asks to log, run, list, or manage project tasks. Also use when asked to generate or update a changelog from completed tasks.

Guides Claude in writing idiomatic, efficient, well-structured Rust code using proper data modeling, traits, impl organization, macros, and build-speed best practices. TRIGGER when working on .rs files or Rust projects (Cargo.toml present).

Use when creating test scenarios for a skill, setting up a tests/ directory for a plugin or package, running skill tests against a subagent, or verifying whether a SKILL.md changes agent behavior

BlockRun works with Claude Code and Google Antigravity.

Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts.

Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.

Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.

Answer repository questions grounded entirely in source code evidence. Use when user asks a question about the codebase, user wants to understand a specific file, function, or component, or user asks "how does X work" or "where is Y defined".

Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add overlays/subtitles, generate media, and create real-time alerts.

Secure-by-default environment variable management for Claude Code sessions.

Design user flows and navigation structure following proven UX patterns

Generate UX microcopy (button labels, error messages, empty states, toasts) following a casual-but-polite voice and tone

Use Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally.

Scaffold a new mobile page/screen using the StyleSeed layout patterns

Quick automated lint — detects common design system violations in seconds

Audit a component or page for accessibility issues and fix them

Master modern SQL with cloud-native databases, OLTP/OLAP optimization, and advanced query techniques. Expert in performance tuning, data modeling, and hybrid analytical systems.

Optimize content for AI Overviews, ChatGPT, Perplexity, and other AI search systems. Use when improving GEO, AI citations, llms.txt readiness, crawler accessibility, and passage-level citability.

Seaborn is a Python visualization library for creating publication-quality statistical graphics. Use this skill for dataset-oriented plotting, multivariate analysis, automatic statistical estimation, and complex multi-panel figures with minimal code.

Riff a winning TikTok into your own short video — study a proven video's emotion formula and regenerate it with your product, character, and language (EN/ES). Also makes UGC ad creative.

When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' 'monetization,' 'how much...

Write idiomatic PHP code with generators, iterators, SPL data structures, and modern OOP features. Use PROACTIVELY for high-performance PHP applications.

CRITICAL: Use for MolyKit AI chat toolkit. Triggers on: BotClient, OpenAI, SSE streaming, AI chat, molykit, PlatformSend, spawn(), ThreadToken, cross-platform async, Chat widget, Messages, PromptInput, Avatar, LLM

Analyze AI disruption pressure across a business, map competitive exposure, and produce a 90-day defensive action plan.

Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use when the user wants to create media content, chat with MiniMax models, perform web search, or manage MiniMax API resources from the terminal.

Human-in-the-loop web studio to tune AI-generated output by eye. Stand up a local interactive studio (sliders, pickers, drag handles) or an inline edit/highlight/comment annotation studio for prose & media, instead of guessing values or shipping a static comparison grid.

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

Algorithm-first discipline: state Big-O, data structure, and algorithm family BEFORE writing loops, queries, or recursion. Catches O(n^2), N+1, and brute-force defaults.

Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers.

Five-phase pipeline (triage → clarify → research → PRD → plan) that turns a raw idea into four linked files: clarifying questions, deep research, a PRD with non-goals and metrics, and a phased execution plan with mermaid user journey and kill criteria.

Use HasData APIs for web scraping and structured web data extraction.

Compact the current conversation into a handoff document for another agent to pick up.

GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper controls, clients can craft queries that bring down your server.

GDB debugging assistant for AI agents - analyze core dumps, debug live processes, investigate crashes and deadlocks with source code correlation

Generate favicons from a source image

Build native UI with the @expo/ui package: real SwiftUI on iOS and Jetpack Compose on Android rendered from React in an Expo or React Native app. Covers universal cross-platform components (Host, Column, Row, Button, Text, List, and more imported from @expo/ui), drop-in replacements...

Use DeepAPI for supported scraping, research, and email workflows with explicit credentials and approval.

Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization.