productivity▌

You're building an automated QA pipeline that tests a Python application end-to-end — running it the same way a real user would, with real inputs — then scoring the outputs using evaluators and producing pass/fail results via pixie test.

Puppeteer-based browser automation with JSON output, screenshot compression, and performance analysis. \n \n Includes 10+ scripts for navigation, screenshots, clicking, form filling, JavaScript execution, element discovery, console monitoring, network tracking, and Core Web Vitals measurement \n Automatic screenshot compression using ImageMagick keeps files under 5MB for API compatibility; supports custom size thresholds and format options \n Supports command chaining by keeping browser sessions

Structured template for creating hypothesis-driven user personas from available research and stakeholder knowledge. \n \n Synthesizes existing user research, market data, and team insights into a working customer profile without requiring months of validation \n Includes step-by-step guidance for defining persona identity, voice, context, and decision-making influences with quality checks at each stage \n Designed to align teams early, guide initial design decisions, and explicitly surface assum

Three-layer parallel analysis of Rust questions across language mechanics, design patterns, and domain constraints. \n \n Executes in parallel agent mode (when layer analyzer files exist) or sequential inline mode, synthesizing results into domain-correct architectural solutions \n Analyzes ownership, borrowing, lifetimes, and error codes at the language layer; evaluates smart pointers, interior mutability, and design trade-offs at the design layer; and applies domain-specific requirements (FinT

Skill by ara.so — Daily 2026 Skills collection.

Expert guidance on prompt optimization, LLM evaluation, and agentic system design for production AI applications. \n \n Covers advanced prompt engineering patterns, few-shot learning, chain-of-thought techniques, and structured output design for Claude, GPT-4, and other LLMs \n Includes RAG optimization frameworks, LLM evaluation methodologies, and performance tuning strategies with reference documentation \n Provides agentic system design principles, multi-agent orchestration patterns, and depl

Code review framework following Sentry engineering practices for pull requests and code quality assessment. \n \n Covers six key problem areas: runtime errors, performance bottlenecks, side effects, backwards compatibility, ORM query issues, and security vulnerabilities \n Includes design assessment guidance for component interactions, architectural alignment, and requirement conflicts \n Requires appropriate test coverage across functional, integration, and end-to-end tests with verification of

Evaluate financial impact of pricing changes using ARPU, conversion, churn, and payback analysis. \n \n Quantifies revenue lift, conversion risk, churn impact, and CAC payback for price increases, new tiers, add-ons, usage-based pricing, discounts, and packaging changes \n Models three scenarios (conservative, base, optimistic) and identifies go/no-go decisions with supporting math \n Recommends implementation, A/B testing, modified approaches, or holding pricing based on net revenue impact and

Source-first CLI for grounding questions in git repos, local directories, and npm packages. \n \n Add and manage resources (git repositories, local directories, npm packages) via btca add , then query them with btca ask using resource names or anonymous one-off URLs \n Ask questions across multiple resources simultaneously to cross-reference answers and connect concepts \n Configuration stored in btca.config.jsonc at project and global levels; project config overrides global settings and control

This skill provides frameworks for navigating difficult workplace conversations and delivering effective feedback. Whether you're addressing performance issues, resolving conflicts, or giving constructive feedback, these structured approaches lead to better outcomes.