nalyk-skills

Premium powerline-style statusline for Claude Code with git status, context window, and model info

Proactively detects tasks suitable for Ralph Loop iteration. Auto-scores tasks, generates prompts, and executes with configurable iterations.

Multi-agent orchestration with task decomposition, parallel execution, and smart agent routing. Commands: /orchestrate, /parallel, /plan-only

Elite Senior Principal Engineer persona (Top 0.01%). Dr. House of IT: cynical code diagnostics with 4 protocols — critic (code autopsy), architect (system design), visual (UI dictatorship), core (algorithmic surgery).

Multi-framework audit agent: Jobs (design simplification), Carlin (BS detection), Vibe (engineering quality). Auto-detects contexts. Commands: /jobs-audit, /carlin-audit, /vibe-audit, /multi-audit

ULTRA deep OpenClaw expertise from all 279 documentation pages. Covers architecture, channels, providers, tools, CLI, multi-agent routing, security, automation, platforms, installation, and troubleshooting.

Expert-level Flutter and Dart development — architecture, state management, code templates, quality gates, CI/CD, and deployment

Philosophical reasoning engine: 62 principles from 20 philosophers as a live decision engine and code review framework. Auto-detects situations, selects principles, runs structured protocol, produces actionable output. Commands: /organon, /organon:decide, /organon:review

Deterministic SEO analysis engine. 98 atomic checks, async multi-page crawler, real CWV via PageSpeed Insights, optional GSC integration, internal link graph with PageRank, auto-fix generation, audit history with regression detection. Commands: /seo audit, /seo fix, /seo technical, /seo content, /seo schema, /seo geo

Multi-model adversarial debate. Claude defends positions against external CLI models (Gemini, Codex, Qwen). Requires at least 1 external CLI. Produces tradeoff documents exposing hidden assumptions. Commands: /debate, /debate:doctor, /debate:adr