informatico-madrid

Canonical rules for the external-reviewer bootstrap, liveness heartbeat freshness gate, and convergence detection. This skill is the single source of truth for reviewer-warmup behavior.

Use only when the user explicitly invokes `$ralphharness`, requests RalphHarness in Codex, asks RalphHarness to handle a named phase, or explicitly requests autonomous or quick mode or continuation without pauses.

Load this skill suite for any spec that involves end-to-end testing, browser automation, Playwright, MCP browser tools, VE tasks, user flow verification, UI testing, or integration tests that drive a real browser. Covers session lifecycle, environment setup, navigation anti-patterns, stable-state detection, auth flows, selector stability, and cleanup guarantees.

This skill should be used only when the user explicitly asks to use `$ralphharness-design`, or explicitly asks RalphHarness in Codex to run the design phase.

This skill should be used only when the user explicitly asks to use `$ralphharness-design`, or explicitly asks RalphHarness in Codex to run the design phase.

This skill should be used only when the user explicitly asks to use `$ralphharness-implement`, or explicitly asks RalphHarness in Codex to run implementation for approved tasks, quick mode, or an explicit continue request.

This skill should be used only when the user explicitly asks to use `$ralphharness-refactor`, or explicitly asks RalphHarness in Codex to revise spec artifacts after implementation learnings.

This skill should be used only when the user explicitly asks to use `$ralphharness-requirements`, or explicitly asks RalphHarness in Codex to run the requirements phase.

Execute deterministic code quality validations as a quality gate for smart-ralph task execution. Runs Layer 3A smoke test (Tier A AST, <1 min), Layer 1 (test execution), Layer 2 (test quality analysis), Layer 3B (Tier B BMAD Party Mode, ~15 min), and Layer 4 (Security & Defense, ~2-5 min). Uses Two-Tier approach: Tier A (AST deterministic) + Tier B (BMAD Party Mode consensus). Layer 4 covers 8 security tools: bandit, safety/pip-audit, gitleaks, semgrep, checkov, deptry, vulture, trivy. Generates a checkpoint JSON consumed by smart-ralph VERIFY steps. Use when you need to validate that code meets quality and security standards before COMMIT.

Create and manage Home Assistant YAML configuration files including automations, scripts, templates, blueprints, Lovelace dashboards, and file organization. Use when working with Home Assistant configuration files (.yaml, .yml) or discussing HA automations, scripts, sensors, or dashboards.

Design, update, and refactor Home Assistant Lovelace dashboards (YAML views/partials) with a constrained, machine-safe design system: button-card-first structure, minimal card-mod styling, optional flex-horseshoe + mini-graph telemetry, strict grid/vertical-stack layout rules, centralized templates, deterministic ordering, and config validation. Use for Home Assistant dashboard work (especially config/dashboards/**), when refactoring views, adding infra/home/energy/environment panels, or translating Stitch design inspiration into safe Lovelace YAML.

Create agent feedback for harness self-improvement. Use after completing complex tasks (>30 min) to document what worked, what failed, and patterns detected. This feeds the continuous improvement loop.

Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.

Iterative consensus-building skill that runs BMAD Party Mode in loops until agents reach consensus. Each iteration enriches context with previous round findings, project domain knowledge, and relevant evidence. Use when you need multi-agent validation, architectural decisions, technical debates, or any situation where consensus is the goal and isolated opinions are insufficient.

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.

Use when users ask how to write, explain, customize, migrate, secure, or troubleshoot GitHub Actions workflows, workflow syntax, triggers, matrices, runners, reusable workflows, artifacts, caching, secrets, OIDC, deployments, custom actions, or Actions Runner Controller, especially when they need official GitHub documentation, exact links, or docs-grounded YAML guidance.

Autonomous AI coding with spec-driven development. Implements Geoffrey Huntley's iterative bash loop with SpecKit integration: JSON state machine, three-layer verification, [VERIFY] checkpoints, recovery mode, and structured task format (Do/Files/Done-when/Verify/Commit).

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training