Workflow pattern standards for creating multi-agent orchestrations including YAML frontmatter (name, goal, termination, inputs, outputs), execution phases (sequential/parallel/conditional), agent coordination patterns, and Gherkin success criteria. Essential for defining reusable, validated workflow processes.

Universal classification system for checker and fixer agents using orthogonal criticality (CRITICAL/HIGH/MEDIUM/LOW importance) and confidence (HIGH/MEDIUM/FALSE_POSITIVE certainty) dimensions. Covers priority matrix (P0-P4), execution order, dual-label pattern for verification status, standardized report format, and domain-specific examples. Essential for implementing checker/fixer agents and processing audit reports

Three-stage content quality workflow pattern (Maker creates, Checker validates, Fixer remediates) with detailed execution workflows. Use when working with content quality workflows, validation processes, audit reports, or implementing maker/checker/fixer agent roles.

README quality standards for engaging, accessible, scannable content including problem-solution hooks, plain language (no unexplained jargon), acronym context, paragraph limits (≤5 lines), benefits-focused language, visual hierarchy, and progressive disclosure. Essential for creating effective README files that welcome and guide users.

Guide for writing Gherkin acceptance criteria using Given-When-Then syntax for testable requirements. Covers scenario structure, background blocks, scenario outlines with examples tables, common patterns for authentication/CRUD/validation/error handling, and best practices for clear testable specifications. Essential for writing user stories and plan acceptance criteria

Comprehensive project planning standards for plans/ directory including folder structure (ideas.md, backlog/, in-progress/, done/), stage-aware naming convention (backlog/done use YYYY-MM-DD__identifier/, in-progress uses identifier/ with no date prefix), five-document file organization (README.md, brd.md, prd.md, tech-docs.md, delivery.md for multi-file default; single README.md for trivially-small single-file exception), BRD/PRD content-placement rules, Gherkin acceptance criteria, and the mandatory structured multiple-choice grilling gates (pre-write and post-write) for resolving design decisions with the user. Essential for creating structured, executable project plans.

Interview the user relentlessly about a plan or design, presenting choices one at a time until shared understanding is reached. Resolves every branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Universal methodology for verifying factual correctness in documentation using WebSearch and WebFetch tools. Covers command syntax verification, version checking, code example validation, API correctness, confidence classification system ([Verified], [Error], [Outdated], [Unverified]), source prioritization, and update frequency rules. Essential for maintaining factual accuracy in technical documentation and educational content

Comprehensive guide for creating in-the-field production implementation guides - production-ready code with 20-40 guides following standard library first principle, framework integration, and enterprise patterns. Essential for creating production tutorials for programming languages on educational platforms

Comprehensive guide for creating by-example tutorials - code-first learning path with 75-85 heavily annotated examples achieving 95% language coverage. Covers five-part example structure, annotation density standards (1.0-2.25 comments per code line PER EXAMPLE), self-containment rules, and multiple code blocks for comparisons. Essential for creating by-example tutorials for programming languages on educational platforms

WCAG-compliant Mermaid diagrams using verified accessible color palette. Use when creating diagrams, flowcharts, or any color-dependent visualizations requiring accessibility compliance for color blindness.

Diátaxis documentation framework for organizing content into four categories - tutorials (learning-oriented), how-to guides (problem-solving), reference (technical specifications), and explanation (conceptual understanding). Essential for creating and organizing documentation in docs/ directory.

Universal markdown content quality standards for active voice, heading hierarchy, accessibility compliance (alt text, WCAG AA contrast, screen reader support), and professional formatting. Essential for all markdown content creation across docs/, web sites, plans/, and repository files. Auto-loads when creating or editing markdown content.

CI/CD standards knowledge for validating project compliance with CI conventions

Guide for creating content on ose-web Next.js 16 content platform. Covers English-only landing page structure, update posts with date-prefixed filenames, markdown frontmatter (title, date, tags, summary, showtoc), simple flat organization, and ose-web specific conventions. Essential for ose-web content creation tasks

Comprehensive guide for developing organiclever-web, the OrganicLever life journal at www.organiclever.com. Covers DDD bounded-context architecture, PGlite local-first storage, Effect TS, XState, Next.js 16 App Router, and Vercel deployment. Essential for development tasks on organiclever-web.

Comprehensive guide for creating content on ayokoding-web, a Next.js 16 fullstack content platform (ayokoding-web). Covers bilingual content strategy (default English), tRPC API, content workflow, and ayokoding-web specific patterns. Essential for content creation tasks on ayokoding-web

AI agent development standards including frontmatter structure, naming conventions, tool access patterns, model selection, and reference documentation structure

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress FILEPATH or "compress memory file"

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress FILEPATH or "compress memory file"