Explore our collection of Agent Skills to enhance your AI workflow.
Creates and manages Claude Code skills following Anthropic's official best practices and activation patterns.
Defines concepts, quality criteria, and decision boundaries by identifying what they are not through anti-goals and near-miss examples.
Writes idiomatic and comprehensive Minitest tests for Ruby on Rails applications.
Analyzes external environments and detects emerging trends to inform strategic planning and scenario development.
Transforms vague instructions into structured, constraint-aware prompts for consistent and high-quality AI outputs.
Generates clean, idiomatic Ruby 3.x code adhering to Sandi Metz’s maintainability standards and modern syntax best practices.
Builds custom, interactive data-driven visualizations using D3.js for complex layouts, maps, and bespoke charting requirements.
Implements systematic Bayesian probability updates to improve forecasting and decision-making under uncertainty.
Clones Git repositories to temporary local directories using shallow depth for rapid code analysis.
Enables Claude to explore alternative scenarios, test assumptions, and perform pre-mortem analysis to improve decision-making and risk assessment.
Detects and mitigates cognitive biases to improve decision-making, forecasting accuracy, and intellectual honesty.
Generates structured visual representations of complex systems, dependencies, and information architectures using ASCII and Markdown.
Stress-tests predictions by assuming failure and working backward to identify hidden risks and blind spots.
Maps identified symmetries to mathematical groups to formalize requirements for equivariant and invariant neural network architectures.
Optimizes long-term knowledge retention using evidence-based cognitive science techniques like spaced repetition and active recall.
Facilitates transparent, data-driven decision-making by comparing multiple alternatives against weighted criteria to identify the optimal choice through structured trade-off analysis.
Refines academic and scientific correspondence, including journal cover letters and reviewer responses, to ensure professional tone and clear communication.
Provides structured frameworks and systematic workflows for Test-Driven Development (TDD), data exploration, and statistical modeling.
Streamlines decision-making and prevents procedural errors through mental shortcuts and structured validation frameworks.
Conducts structured adversarial reviews to challenge assumptions and identify hidden vulnerabilities in plans or architectures.
Analyzes complex systems to identify high-leverage intervention points and feedback loop dynamics for more effective problem-solving.
Automates the creation of comprehensive project plans by integrating detailed specifications, proactive risk assessments, and measurable success criteria.
Verifies that machine learning models correctly respect intended symmetries through systematic numerical tests and debugging guidance.
Validates product ideas and technical assumptions using low-cost pretotyping techniques and iterative prototyping workflows.
Prioritize product backlogs and feature roadmaps using a systematic 2x2 effort-versus-impact matrix to identify quick wins and strategic bets.
Validates symmetry hypotheses in datasets and models through empirical invariance and equivariance testing protocols.
Analyzes scientific documents to ensure logical rigor, argument soundness, and precise alignment between claims and empirical evidence.
Facilitates structured team retrospectives and project post-mortems to drive continuous improvement and actionable insights.
Resolves polarized debates and false dichotomies by identifying strongest arguments for opposing views to synthesize principled, higher-order solutions.
Manages complex strategic initiatives across multiple time horizons using a disciplined betting framework for resource allocation and risk management.
Scroll for more results...