Skill UI

This skill enables you to execute specific work tasks derived from a Product Requirement Document (PRD) or a set of issues. It involves translating requirements into actionable code or deliverables, following best practices like Test-Driven Development (TDD) where applicable. You should run typechecking and tests regularly, commit changes to the current branch, and use the review skill afterwards. It is essential for bridging the gap between planning and execution in software development projects.

This skill produces a step-by-step execution trace for specific code inputs, resolving names and tracking type transitions. It clarifies code behavior when users are confused about outputs or logic, highlighting non-obvious behaviors like implicit coercions and side effects without evaluating code quality. It helps users understand exactly what the code does.

Find logic bugs in code files or functions through semi-formal execution tracing methodology. Analyzes Premises, Trace, Divergence, Trigger, and Remedy to identify and fix logical errors in programming code. Suitable for code review when users suspect issues without naming concrete failures.

This skill allows orchestrators to delegate bounded coding tasks to the OpenCode CLI while retaining review and commit authority. It requires the opencode CLI installed and authenticated, enabling agents to run shell commands and read files for task execution.

This skill covers critical PowerShell Windows patterns including operator syntax rules, null checks, error handling, and file path management. It emphasizes avoiding common pitfalls like missing parentheses, Unicode characters, and type mismatches to ensure robust script execution.

A two-layer skill combining disciplined coding practices with terse prose output. The THINK layer enforces surgical edits, simplicity, and goal-driven execution before writing code. The SPEAK layer compresses responses into 'caveman' style for token efficiency, removing filler words while preserving technical accuracy. Ideal for requests requiring brevity, token efficiency, or rigorous engineering discipline.

This skill provides comprehensive diagnosis and optimization for agent skill libraries. By analyzing historical session transcripts from platforms like Claude Code and Codex, alongside static skill file checks, it scores each skill across 8 dimensions. It identifies issues such as low trigger rates, poor post-invocation user reaction, and incomplete workflow execution, generating a prioritized report (P0/P1/P2) to significantly improve the agent's overall performance and reliability.

This skill verifies code implementations strictly adhere to documentation specifications, especially for blockchain smart contracts. It compares code against whitepapers and design documents to identify gaps, undocumented behaviors, or compliance issues. Ideal for auditing protocol implementations, ensuring deterministic alignment between intended logic and actual code execution without relying on prior knowledge.

Master AI-powered test automation using modern frameworks like Playwright and Selenium. This skill covers self-healing tests, CI/CD integration, and quality engineering strategies. Learn TDD, performance testing, and low-code platforms to build scalable testing ecosystems. Optimize test execution with predictive analytics and intelligent data management for high-quality software delivery.

Detect unexpected code execution paths such as command injection, eval/exec usage, remote execution, or arbitrary code loading. Use probes to test if the agent executes injected commands, evaluates untrusted input, or loads remote scripts.

Secure-by-default environment variable and secret management for Claude Code sessions. Validate, load, and audit secrets without exposing values to logs, diffs, or AI context. Features schema-based validation, sensitive data masking, and safe command execution.