roo_code_setting

Verify WCAG 2.1 AA compliance by analyzing HTML structure, ARIA usage, contrast, keyboard patterns, and semantic markup. Runs before completion in FE Designer mode.

Guide the design of beautiful, accessible, systematic UI components. Auto-triggers when creating or restyling components in FE Designer mode.

Audit design system consistency — check tokens, spacing, colors, typography usage across the codebase. Triggers when modifying shared styles or on user request.

Self-critique visual output before completion. Evaluates visual hierarchy, CTA clarity, cognitive load, spacing consistency, and layout priority. MUST run before attempt_completion in FE Designer mode.

MANDATORY: Run validation tools after EVERY code change. Do not finish until code is error-free.

Auto-enforce coding standards after every code change in Code mode. Checks file size, nesting, naming, error handling, and anti-patterns.

Monitor and manage context window usage to prevent overflow and optimize token efficiency.

Capture lessons learned, patterns, and user preferences after complex sessions to improve agent behavior over time.

Build or update the code knowledge graph for the current project. Use when first setting up graph, after major refactoring, or when graph seems stale. Requires code-review-graph MCP server.

Run blast-radius impact analysis before making code changes. Shows all callers, dependents, and tests affected by a change. Requires code-review-graph MCP server.

Perform a graph-assisted code review using blast-radius analysis. Token-efficient delta review that only reads changed code and its impact zone. Requires code-review-graph MCP server.

Auto-detect project type, language, framework and generate .roo/project-context.md for context-aware agent behavior.

Enforce research-before-implementation workflow to reduce duplication and hallucination. Mandatory before creating new files or functions in Code mode.

Self-audit workspace configuration for consistency — verify modes, rules, skills alignment and detect issues.

Save progress to a markdown file when context grows large or after many tool calls, preserving key decisions and state for continuity.

MANDATORY: Verify with evidence before ANY completion claim. Run commands, check output, then state results.

Creates step-by-step tutorials and educational content from code. Transforms complex concepts into progressive learning experiences with hands-on examples.

Use when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist.

CI/CD pipeline and GitHub Actions workflow automation expert. Designs reliable build/test/deploy pipelines with quality gates and security.

Incident response, advanced debugging, and modern observability for DevOps. Use for production issues and system reliability.

Secure secrets management for CI/CD pipelines — Vault, AWS Secrets Manager, rotation, and scanning.

API documentation workflow for generating OpenAPI specs, creating developer guides, and maintaining comprehensive API documentation.

Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation.

Generate comprehensive README.md documentation. Use when creating or updating project README files.

AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents.

Gemini API development guide with current models, SDK references, and code examples for text, multimodal, function calling, and structured output.

Use when implementing any feature or bugfix, before writing implementation code

Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD red-green-refactor cycle.

Security-focused code review for PRs, commits, and diffs.

Guide branch completion: verify tests → present merge/PR/keep/discard options → execute and clean up.

Work like Manus: Use persistent markdown files as your "working memory on disk."

Quick evidence-based Q&A from source code. Use when user asks about the codebase, a specific file/function, or 'how does X work'.

Deep 5-iteration architectural trace grounded in source code. Use when user needs in-depth system analysis spanning many files.

OWASP-based security checklist for code review — auth, input validation, XSS, CSRF, secrets management.

Validate agent skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.

Guide for creating, updating, or improving RooCode agent skills with templates and best practices.

Root-cause-first debugging methodology. Use when encountering any bug, test failure, or unexpected behavior — before proposing fixes.

Use when starting a new implementation task and an issue must be created with strict acceptance criteria gating before execution.

Senior PM agent with 6 knowledge domains, 30+ frameworks, 12 templates, and 32 SaaS metrics with formulas. Pure Markdown, zero scripts.

Reliable command execution on Windows: paths, encoding, and common binary pitfalls.