Cognitive framework that transforms AI agents into senior architects — evidence-first system understanding, honest uncertainty mapping, architecture debt and convention assessment, knowledge-graph-assisted dependency mapping, impact and blast radius analysis, and architecture reasoning before action. Use when an agent…
Question-first architecture proposal discipline for AI agents. Use when a user provides a raw idea, product concept, feature request, business goal, or system goal without an existing implementation and needs a reviewable architecture proposal with assumptions, open questions, risks, decision options, workflows…
Aetox Agents collaboration protocol — Entry Ritual, Scope Boundary, Handoff, Exit Report. Load before starting any project work. Every Aetox agent must read AGENTS.md in project root, report in, check scope, and log exit. This skill is the central rulebook for all Aetox Agents.
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
Contract-first protocol for frontend and backend agents. Use when creating/updating API endpoints, integrating FE with BE, defining shared types, handling errors, or when frontend or backend behavior crosses the API boundary. Load this before any FE-BE integration work — never guess, always contract-first.
GitHub patterns using gh CLI for pull requests, stacked PRs, code review, branching strategies, and repository automation. Use when working with GitHub PRs, merging strategies, or repository management tasks.
Cognitive framework that transforms AI agents into senior architects — evidence-first system understanding, honest uncertainty mapping, and architecture reasoning before action. Use when an agent must understand a codebase, map architecture, produce handoff notes, propose changes, or turn an idea into a reviewable…
Token Saver (RTK Protocol) — Load this skill before running bash commands this session. CLI proxy that filters/strips command output before it reaches LLM context. Saves 60-90% tokens on git, test, install, lint, build, cloud, containers. Default-on: try rtk for any long-output command, not just the listed ones.…
Documentation architecture discipline for AI agents. Use when creating, updating, auditing, or organizing software project documentation so docs stay clear, non-duplicated, source-of-truth driven, and token-efficient.