agent-os-lab

Audit a generated OS repository for completeness, consistency, and architectural integrity against the 15 design principles and 23-item checklist.

Transplant a skill, command, or capability from one agentic-system repo into another via a 5-phase gated protocol (inventory → import → localize → wire → verify). Use when grafting a feature from an upstream repo that has its own dependencies, platform assumptions, or upstream-specific file references that need adapting before the feature will work in the destination repo. Not for copying a self-contained file — use only when the feature has a dependency footprint and the destination repo has its own conventions the import must respect.

Design multi-dimensional evaluation rubrics with calibrated scales, thresholds, and function-adaptive weights.

Identify who evaluates the user's output, what each audience prioritizes, and where their priorities conflict.

Define the user context model — identity axes, context files, persona variants, and privacy rules for the target OS.

Design compounding feedback loops — what data accumulates, what reads it, and how the system gets smarter with use.

Design the complete skill set for the target OS — each skill's purpose, inputs, process, output format, auto-triggers, and quality checks.

Design reviewer personas — adversarial quality gates with different priorities than the creation skills they review.

Interactive interview to understand the domain, the target user, and the problem space. First skill to run — fills initial domain-input files.

Assemble all domain inputs and component designs into a complete, deployable Claude Code agent OS repository.

Extract the daily/weekly workflow, pipeline stages, time allocation, and healthy metrics from the domain expert.

Audit a generated OS repository for completeness, consistency, and architectural integrity against the 8 design principles.

Define the non-negotiable rule, verification checks, anti-patterns, banned vocabulary, and tone for the target OS.

Design multi-dimensional evaluation rubrics with calibrated scales, thresholds, and function-adaptive weights.

Design the generation pipeline for non-text deliverables — templates, rendering, design tokens, storage, and verification.

Design the historical backtesting library for the target OS — what historical artifacts to collect during onboarding, how to organize them, and how skills use them for calibration and live reference.

Design the parallel/headless worker execution model for processing items at scale — worker prompts, state tracking, and merge pipelines.

Define file ownership boundaries — which files the user owns, which the system manages, and which are hybrid with shared access.

Map external data sources with trust levels, freshness thresholds, verification rules, and fallback chains.

Define the user context model — identity axes, context files, persona variants, and privacy rules for the target OS.

Design multi-language and multi-culture support for the target OS — localized modes, culture-specific vocabulary, and language detection.

Design the complete skill set for the target OS — each skill's purpose, inputs, process, output format, auto-triggers, and quality checks.

Interactive interview to understand the domain, the target user, and the problem space. First skill to run — fills initial domain-input files.

Assemble all domain inputs and component designs into a complete, deployable Claude Code agent OS repository.

Extract the daily/weekly workflow, pipeline stages, time allocation, and healthy metrics from the domain expert.

Define the non-negotiable rule, verification checks, anti-patterns, banned vocabulary, and tone for the target OS.