company-os

Interactive setup wizard for Company OS. Configures company.config.yaml, generates .claude/settings.json with tech-stack-specific permissions, and scaffolds directories. Supports three modes — interactive wizard, express config block, or auto-extract from a URL/unstructured text.

Produces RFC/ADR defining system boundaries, modules, data model, and integration points. Use when translating a PRD into technical design, making architectural decisions, or designing new system components.

Produces architecture diagrams, data flow diagrams, ERDs, and system overviews in Mermaid (inline) and Excalidraw JSON (standalone). Use when an RFC, threat model, or documentation needs visual diagrams.

Performs data flow threat analysis with structured mitigations. Use when assessing security threats for new features, architecture changes, or compliance reviews.

Creates platform-specific marketing playbooks for acquisition channels. Use when launching or optimizing a specific growth channel (e.g., LinkedIn, Twitter, email, Product Hunt).

Prepares pre-call briefings, captures post-call debriefs, and routes insights to ICP refinement and PRD evidence. Stores conversation logs as CONV- artifacts in artifacts/decision-memos/.

Turns messy, unstructured customer and user feedback into actionable themes with supporting evidence. Use when consolidating feedback from multiple sources into product insights.

Time-boxed go-to-market sprint that sequences customer validation, positioning, launch, and distribution over 7-21 days. Use when validating market demand, launching an MVP, or running a structured GTM push.

Maps objectives to required artifacts, stages, and responsible agents. Use when routing any objective, deciding what happens next, or determining which agents need to be involved in a task.

Designs "aha moment" flows and activation experiments to improve new user onboarding. Use when optimizing the path from sign-up to first value realization.

Designs AI/ML feature architectures including LLM integration, RAG pipelines, prompt engineering, and AI cost optimization. Use when building features that involve AI/ML components.

Designs REST/GraphQL API contracts with consistent error handling, pagination, auth, and i18n. Use when designing new API endpoints, modifying existing APIs, or creating service interfaces.

Generates API testing playbooks covering contract tests, authentication testing, pagination validation, and error handling. Use when building or reviewing API test suites.

Imports existing documents (PRDs, RFCs, API specs, test plans) into Company OS with proper frontmatter, type classification, and artifact linking. Use when bringing external documents into the artifact system.

Design patterns for background job processing including retries, idempotency, and queue management. Use when designing or reviewing async task infrastructure.

Structured multi-section code review with interactive feedback — architecture, quality, tests, performance. Use for PR reviews, pre-merge quality checks, or self-review before handoff.

Performs SOC2-lite checklist assessment and compliance gap analysis. Use when preparing for audits, assessing compliance posture, or building toward SOC2 certification.

Produces multi-format content strategies with editorial calendars, content briefs, and multiplication workflows. Use when building a content marketing engine, planning blog/newsletter cadence, or creating content briefs.

Produces structured decision records with rationale, alternatives considered, and consequences. Use when recording non-trivial decisions that future team members need to understand.

Designs deployment pipelines, rollout strategies, and environment configurations. Use when establishing deployment procedures, planning a feature rollout, or setting up CI/CD pipelines.

Reads configured design archetype and UX baseline to produce project-specific design tokens, component guidance, and UX patterns. Use when building UI components, reviewing design consistency, or configuring design preferences for the first time.

Generates Docker Compose files and dev scripts from tech stack config. Creates environment-specific infrastructure for local development, QA, and production.

Smart pre-build discovery that validates novel feature ideas before committing to a full PRD. Classifies objectives as common patterns (skip) or novel concepts (full validation with lean canvas, competitive scan, and risk assessment).

Autonomous dogfooding — tests the product by using it as real users would, capturing issues with severity ratings. Supports web apps (via agent-browser) and API-only products.

Designs email sequences, templates, and send triggers for SaaS lifecycle marketing and transactional emails. Use when planning onboarding drips, transactional notifications, activation campaigns, or retention email flows.

Designs statistically rigorous A/B experiments with sample size calculation, guardrail metrics, and results analysis. Use when planning experiments, validating feature impact, or analyzing test results.

Designs feature flag strategy, progressive discovery patterns, and per-feature flag specifications for safe rollouts and organic product learning.

Defines ideal customer profile and product positioning. Use when establishing or refining who the product serves and how it is differentiated in the market.

Generates incident runbooks, post-mortem templates, and incident response records. Use when establishing incident response procedures, handling a live incident, or conducting post-incident reviews.

Scans standards/ and artifacts/ for new or changed content and suggests updates to skills, agents, and configuration. Use after adding new standards documents, API specs, or artifacts to synchronize the system.

Defines analytics instrumentation standards including event taxonomy, tracker ID conventions, and per-feature instrumentation plans for measurable product development.

Generates conversion-focused landing page copy organized by sections. Use when creating or optimizing landing pages for product launches, features, or campaigns.

Produces competitive landscape scans, technology radar assessments, and trend timing analysis. Use when monitoring competitors, evaluating new technologies, or identifying market opportunities.

Defines responsive web design patterns and React Native/Expo mobile architecture ensuring all products work on every screen size. Use when building mobile-first web UIs, planning native mobile apps, or adding PWA support.

Design patterns for multi-tenant architecture including org scoping, row-level security, and tenant data isolation. Use when designing or auditing tenant isolation boundaries.

Establishes logging, metrics, and tracing conventions for the codebase. Use when setting up or auditing the observability stack and standards.

Crafts a crisp product narrative and competitive differentiators for go-to-market materials. Use when defining or refreshing the product story for marketing and sales.

Generates consistent PRDs with problem statements, acceptance criteria, success metrics, and scope boundaries. Use when creating or updating product requirements for any feature.

Performs CAC/LTV analysis and pricing model validation. Use when setting initial pricing, evaluating pricing changes, or assessing unit economics health.

Defines data retention policies, access controls, and deletion procedures. Use when establishing or auditing how personal and sensitive data is stored, accessed, and removed.