Explore skills

Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions, high fan-out, refactor candidates, code quality audit, graph query syntax, Cypher

Xcode Cloud CI/CD configuration, workflows, custom scripts, testing, deployment, and optimization. Use when setting up or troubleshooting Xcode Cloud pipelines.

Audits third-party code repositories, typically GitHub URLs, for security issues, malicious code, supply-chain risks, and dangerous patterns before adoption or execution. This skill is used when users inquire about repository safety or trustworthiness, or request an an audit.

Your session's guard dog — naps when safe, barks when you drift, bites the leash before you crash.

Generate or edit images using Nano Banana Pro (Gemini 3 Pro Image) with predefined templates or free-form editing. This ensures consistent team image structure via Cloudflare Gateway + OpenRouter API.

Generate production-quality SVG+PNG technical diagrams from natural language. Use this tool to create architecture, data flow, flowchart, sequence, UML, mind map, or concept map diagrams and export them as SVG+PNG.

Evaluates SEO, AEO, and GEO meta information, including title tags, meta descriptions, and schema markup. It scores these across 9 dimensions (0-10), providing a weighted overall score out of 100, covering technical search quality and executive audience quality.

Archived source pointer. The canonical GitHub repo design skill now lives in claude-code-skills/development/github-repo-design.

Auto-invoked after every significant task completion. Captures mistakes, inefficiencies, and improvements so Claude gets smarter over time. Never ask the user — just reflect and write.

Expert Pulse Check for product decisions. It triggers automatically when Claude offers multiple options for major product decisions, entering expert review mode, or manually when requested by the user.

Performs deep iterative research, taking a topic and an optional existing document. Each iteration uses a subagent to improve the document by filling gaps and avoiding duplicate research, adhering to a defined schema.

A daily pre-market analysis framework for Nifty intraday directional assessment. It performs a two-phase analysis (previous evening and morning pre-market) to output a directional bias, conviction level, and comprehensive market state assessment.