productivity▌

Convert Jupyter notebooks to marimo Python scripts with CLI-driven transformation and cleanup guidance. \n \n Use uvx marimo convert <notebook.ipynb> -o <notebook.py> to generate marimo-compatible .py files without local installation \n Run marimo check before and after manual edits to catch syntax and compatibility issues \n Common cleanup tasks include removing Jupyter artifacts ( %magic commands, display() calls), verifying package metadata, and ensuring final cell expressions rende

Audit Google Drive files shared outside your organization and manage external access permissions. \n \n Requires the gws-drive skill to execute; queries Google Drive for files with external sharing enabled \n Three core operations: list externally shared files, review permissions on specific files, and revoke access when needed \n Includes a safety caution recommending confirmation with file owners before revoking permissions to prevent unintended access loss \n

Issue fields are org-level typed metadata (single select, text, number, date) that replace label-based workarounds with structured, searchable, cross-repo fields. Every organization gets Priority, Effort, Start date, and Target date preconfigured, with support for up to 25 custom fields.

Rust mutability design: choosing between &mut , interior mutability, and thread-safe patterns. \n \n Guides decision-making for E0596, E0499, E0502 errors by asking whether mutation is necessary and who controls it, rather than reflexively adding mut \n Covers single-thread patterns (Cell, RefCell) and multi-thread patterns (Mutex, RwLock, Atomic types) with clear selection criteria \n Includes borrow rule reference, anti-patterns (RefCell overuse, Mutex in hot loops), and decision tables f

When running a security review on a codebase, follow these structured steps to identify potential vulnerabilities, leaks, and misconfigurations.

Clean up AI-generated code bloat by removing unnecessary comments, defensive checks, and style inconsistencies from your branch. \n \n Analyzes diffs against main to identify and remove extra comments, defensive try/catch blocks, and type-safety workarounds that deviate from codebase patterns \n Focuses on changes introduced by AI, preserving intentional human code and existing file conventions \n Provides a concise summary of modifications made, keeping feedback to 1–3 sentences \n

Comprehensive customer success management covering onboarding, health scoring, QBRs, expansion playbooks, and retention strategies.

You are a code migration expert specializing in transitioning codebases between frameworks, languages, versions, and platforms. Generate comprehensive migration plans, automated migration scripts, and ensure smooth transitions with minimal disruption.

Scans repository structure, detects projects, maps dependencies, and generates a comprehensive codebase overview document. \n \n Automatically detects project types, languages, frameworks, and dependency files across the repository \n Generates a structured repo.md file documenting project architecture, components, and organization for security analysis or codebase understanding \n Caches results in a configurable directory to avoid redundant scans on subsequent runs \n Works entirely with local

Compile-time state validation through type encoding, eliminating invalid states at the type level. \n \n Covers six core patterns: newtype for type-safe primitives, type state for state machines, PhantomData for variance tracking, marker traits for capability flags, builders for gradual construction, and sealed traits for closed impl sets \n Emphasizes asking \"can the compiler catch this?\" before adding runtime validation, with decision guides mapping common needs to appropriate patterns \n In