Skill UI

A governance skill designed to secure AI agent tool calls using advanced authorization policies. It implements Cedar policies to control which tools agents can access and under what conditions. Key features include running in 'Shadow mode' for safe observation, 'Enforce mode' for strict blocking, and generating cryptographically signed Ed25519 receipts to provide an immutable, tamper-evident audit trail for every policy decision.

This skill covers the advanced language features introduced in Dart 3, including Pattern Matching, Records, sealed classes, and enhanced control flow structures. Learn how to use `if-case` and switch expressions to write safer, more concise, and idiomatic Dart code, and how to manage complex data shapes using records and patterns.

Guides writing documentation and ADRs to capture why architectural or API choices were made, when to comment, and how to structure README/API info so future engineers and agents understand the rationale and trade-offs.

Comprehensive DI guide for Golang covering best practices, architecture decisions, manual constructor injection, and library comparisons (Wire, Dig, Fx, Do) to help teams build testable, loosely coupled services.

Generates a standup-ready summary that combines today’s calendar meetings with open tasks via the GWS workflow command, offering JSON, table, YAML, or CSV output to keep updates concise and ready for reporting.

This skill provides comprehensive management capabilities for Lark Feishu cloud documents (v2). It allows users to create new documents, fetch detailed content (supporting simple, full, and localized reading modes by keyword or section), and update existing documents using various precise commands (e.g., insert, replace, delete). It also supports media insertion, download, and resource searching within the cloud space.

This skill simulates a high-level CTO (P10) perspective, focusing on macro-level corporate planning. It assists in defining overarching strategic directions, designing complex organizational topologies, and managing cross-team architectural decisions. Use this when initiating strategic planning, forming an architecture committee, or resolving enterprise-wide technical conflicts.

Command-line helper that pulls in URLs, local files, transcripts, podcasts, and YouTube links to deliver concise summaries or transcripts, with provider models and fetch fallbacks configurable for any workflow.

Guides multi-axis reviews before merging, checking correctness, readability, architecture, security, and performance while enforcing concise change sizing and descriptive commit messaging to keep PR history clear.

This tool generates ultra-compressed, standardized commit messages adhering strictly to the Conventional Commits specification. It analyzes code changes (diffs) to extract the core intent, structuring the output into a precise subject line and an optional body. It ensures that commit history remains clean, highly readable, and instantly understandable, significantly reducing noise and maintaining professional version control standards.

Streamlines the process of providing code review feedback by enforcing a highly structured, ultra-compressed format. It guides users to cut through noise and deliver actionable, single-line comments (Location: Problem. Fix.) while maintaining critical context like severity and technical rationale. Ideal for team settings prioritizing efficiency and high code quality.

This skill generates highly precise deep links to various resources within the Arize platform, including traces, spans, sessions, datasets, and evaluators. It requires collecting specific resource IDs (e.g., project_id, dataset_id) and managing time ranges (startA/endA) to ensure the user is taken to the exact view, optimizing the user experience for ML practitioners and data scientists.