core

Toolkit for creating and validating skills and subagents. Use when: creating a new skill (fast or full mode), validating an existing skill, deciding Skills vs Subagents, migrating docs to skills, estimating token cost, or running a security scan. Triggers: "create skill", "build skill", "validate skill", "new subagent", "skills vs subagents", "estimate tokens", "security scan".

Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.

Pre-build orientation for skill creators. Answers "what are skills?", "should I make one?", and "is my skill good enough?" before you start building. Use for: understand skills, decide skills vs subagents, validate an existing skill. When ready to actually build, invoke /skillkit directly instead.

Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.

Apply systematic problem-solving techniques for marketing challenges including campaign complexity (simplification cascades), creative blocks (collision-zone thinking), recurring campaign patterns (meta-pattern recognition), assumption constraints (inversion exercise), audience scale uncertainty (scale game), and dispatch when stuck. Techniques derived from proven problem-solving frameworks adapted for marketing execution.

Search engine optimization strategies and tactics for organic growth. Use when optimizing content for search, conducting keyword research, performing SEO audits, or building link strategies.

Core marketing concepts, psychology, and frameworks for effective marketing. Use for foundational knowledge on funnels, customer journey, positioning, value propositions, and marketing psychology.

Email campaign strategy, automation, and optimization. Use when creating email sequences, improving deliverability, designing automation workflows, or optimizing email performance.

Performance measurement, attribution modeling, and marketing ROI analysis. Use when setting up tracking, analyzing campaign performance, building attribution models, or creating marketing reports.

When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' or 'ideas to grow.' This skill provides 140 proven marketing approaches organized by category.

When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application.

Brand strategy, identity, positioning, and voice development. Use when developing brand guidelines, creating positioning statements, defining brand voice, or building brand architecture.

Social media strategy, content creation, and platform optimization. Use when creating social content, developing engagement strategies, optimizing for platform algorithms, or building community.

Content planning, creation, and distribution strategy. Use when planning content calendars, developing content pillars, creating editorial strategies, or optimizing content for different funnel stages.

Paid media strategy and optimization across platforms. Use when planning paid campaigns, optimizing ad performance, managing budgets, or setting up tracking for paid channels.

Output-verbosity compression. Cuts response tokens ~40-70% without losing technical accuracy. Four intensity levels (off/brief/terse/ultra) aligned with Rulebook's agent-tier system. Use when user says 'terse mode', 'be terse', 'less tokens please', or invokes /rulebook-terse. Auto-activates via SessionStart hook with tier-aware default.

Maintain a clean dependency graph (DAG) to prevent circular dependencies and ensure maintainable architecture.

Terse Conventional Commits generator. Subject ≤50 chars (hard cap 72), body only when 'why' isn't obvious, no filler. Use when user says 'write a commit', 'generate commit', 'commit message', or invokes /rulebook-terse-commit. Independent of the base rulebook-terse mode.

Ultra-compressed code review comments. One line per finding: location, problem, fix. Use when user says 'review this PR', 'code review', 'review the diff', or invokes /rulebook-terse-review. Independent of the base rulebook-terse mode.

Mandatory workflow that AI agents MUST execute after EVERY implementation.

Spec-driven task management for features and breaking changes with OpenSpec-compatible format

These rules are NON-NEGOTIABLE and MUST be followed without exception.

All documentation in English. Root README concise, detailed docs in `/docs`.