Skill UI

Framework for AI media writing inspired by Synced. Focuses on paper-first reporting, quantitative data, academic plus industry parallelism, layered analysis, and productized content. Applies to deep tech reviews, model benchmarks, industry trend reports, and editorial commentary.

A rigorous, standalone tool designed for explicit, blind, and adversarial code review. It executes the code target through two parallel, independent judges (Judge A and Judge B) with strict rules and limited fix rounds. This process ensures maximum scrutiny, providing a definitive, highly corroborated verdict (APPROVED or ESCALATED) that replaces standard review methods.

This document defines the critical architectural contract for standardizing advisory transport across diverse AI code review runtimes (e.g., Claude Code, OpenCode, Codex). It mandates that all integrations adhere to a shared Go contract, governing how review results, evidence, and validation are processed. This is essential for ensuring system integrity, managing architectural transitions, and preventing the creation of isolated, proprietary review systems.

This skill outlines a highly rigorous, receipt-driven workflow for managing defects and implementing code corrections. It guides public collaboration by enforcing strict controls over change authority, ensuring comprehensive lineage tracking, and mandating evidence-based validation. Key steps include CodeGraph impact mapping, black-box testing, and adherence to strict change budgets, ensuring every deployed change is fully traceable and robust.

The sdd-apply agent is a specialized sub-agent responsible for the core implementation phase of Software Design Documents (SDD). It takes structured tasks, design specifications, and development contracts as input, writing and persisting actual code that strictly adheres to the defined specs and architecture. It manages state transitions and handles complex workload decisions, such as PR branching and risk assessment, ensuring the development workflow is followed precisely.

This sub-agent is responsible for completing the System Design Document (SDD) lifecycle. It merges final delta specifications into the main source of truth and moves the completed change folder to the archive. It enforces rigorous reporting rules, ensuring the archive report reflects the definitive final state of the change, prioritizing authoritative sources over intermediate progress reports.

This specialized sub-agent is responsible for transforming high-level feature proposals and technical specifications into a formal, comprehensive 'design.md' document. It systematically captures all necessary technical details, including architectural decisions, data flow diagrams, detailed file changes, API contracts, and thorough testing strategies. Use this skill during the planning phase of any complex software change to ensure technical completeness and feasibility.

This agent is dedicated to systematically exploring technical ideas, such as new features, refactoring, or bug fixes, *before* committing to code changes. It investigates the existing codebase, analyzes current architecture, compares multiple potential approaches (including pros, cons, and effort), and generates a structured 'exploration' report with a clear recommendation and identified risks. It ensures thorough planning and risk mitigation during the design phase.

This advanced skill initializes the Software Development Documentation (SDD) context within a project. It detects the entire technical stack, conventions, testing tools, and persistence mode across all discovered projects. It then structures and persists this comprehensive context, including building a skill registry and determining the strict TDD status, ensuring a robust starting point for development.

This skill provides an interactive, step-by-step walkthrough of the complete Software Development Development (SDD) life cycle. It guides users through a professional development process, from initial codebase exploration and proposing solutions, to writing detailed specifications, architectural design, task breakdown, implementation, verification, and final archiving. The goal is to teach the entire development lifecycle by applying it to the user's actual codebase, ensuring hands-on mastery of industrial best practices.

This sub-agent generates a comprehensive, structured change proposal (proposal.md) based on exploration analysis or direct user input. It enforces a standard architecture contract, detailing the intent, scope, technical approach, risks, and success criteria for new features or refactoring efforts. It is essential for initiating formal, documented development and architecture review cycles.

This skill acts as a dedicated sub-agent for SDD research, collecting external evidence and source-backed information. It produces auditable evidence envelopes for selected research lanes, verifying grants and mapping claims to source IDs without accessing local artifacts.