Loading...
Loading...
Found 1,140 Skills
Use when investigating why something happened and need to distinguish correlation from causation, identify root causes vs symptoms, test competing hypotheses, control for confounding variables, or design experiments to validate causal claims. Invoke when debugging systems, analyzing failures, researching health outcomes, evaluating policy impacts, or when user mentions root cause, causal chain, confounding, spurious correlation, or asks "why did this really happen?"
Refactor Scikit-learn and machine learning code to improve maintainability, reproducibility, and adherence to best practices. This skill transforms working ML code into production-ready pipelines that prevent data leakage and ensure reproducible results. It addresses preprocessing outside pipelines, missing random_state parameters, improper cross-validation, and custom transformers not following sklearn API conventions. Implements proper Pipeline and ColumnTransformer patterns, systematic hyperparameter tuning, and appropriate evaluation metrics.
Diagnose risks and inefficiencies in an existing investment portfolio. Use when the user asks to review, audit, or stress-test their current holdings, evaluate portfolio concentration, check factor exposures, assess correlation risks, identify hidden tilts, or get actionable improvement suggestions for a portfolio they already own.
Apply startup execution wisdom to product, strategy, and business decisions. Use for feature prioritization, build-vs-buy decisions, go-to-market planning, pricing, hiring, scope/timeline reality checks, or when evaluating whether an idea has product-market fit potential.
Senior/Lead Developer Bun.js + Docker dengan pengalaman 20 tahun. Skill ini digunakan ketika: (1) Membuat project Bun.js baru dengan Docker, (2) Code review dan refactoring untuk clean code, (3) Debugging complex issues, (4) Optimisasi performa dan scalability, (5) Arsitektur aplikasi production-ready, (6) Memilih library yang tepat dan terpercaya, (7) Setup CI/CD dan deployment. Trigger keywords: "bun", "bunjs", "bun.js", "docker", "typescript backend", "clean code", "scalable", "maintainable", "debugging", "performance".
Use when working with AWS Strands Agents SDK or Amazon Bedrock AgentCore platform for building AI agents. Provides architecture guidance, implementation patterns, deployment strategies, observability, quality evaluations, multi-agent orchestration, and MCP server integration.
LLM-based deep iterative search and reasoning service. Specializes in handling complex problems, automatically decomposing queries, conducting multi-round iterative retrieval, evaluating and verifying information, and finally generating comprehensive and structured deep analysis reports.
Use when you need to generate many creative options before systematically narrowing to the best choices. Invoke when exploring product ideas, solving open-ended problems, generating strategic alternatives, developing research questions, designing experiments, or when you need both breadth (many ideas) and rigor (principled selection). Use when user mentions brainstorming, ideation, divergent thinking, generating options, or evaluating alternatives.
Calculate, understand, and improve the unit economics of a solopreneur business. Use when figuring out if the business is actually profitable per customer, when CAC or LTV numbers are needed, when evaluating whether a pricing or acquisition strategy is sustainable, or when making data-driven decisions about marketing spend and pricing. Covers CAC, LTV, payback period, contribution margin, and the feedback loops between them. Trigger on "unit economics", "CAC", "customer acquisition cost", "LTV", "lifetime value", "payback period", "is my business profitable", "contribution margin", "am I making money per customer", "should I spend more on marketing".
Facilitates solution ideation with clear trade-offs and a final recommendation. Use when exploring architectural decisions, evaluating technology choices, or comparing implementation approaches before writing code.
Warden skill: evaluates first-pass findings and proposes deterministic lint rules that could permanently catch the same patterns. Requires Warden's multi-pass pipeline (phase 2).
Self-referential completion loop for OpenCode. Re-injects continuation prompts until the task is fully complete with a completion promise.