AI Engineering

Deep Research is a 13-agent pipeline for rigorous academic research on any topic, from research question formulation and systematic literature search to source verification, synthesis, meta-analysis, and APA 7.0 report compilation.

Claude.md creates or updates CLAUDE.md files according to best practices for AI agent onboarding. Use it to audit existing files, remove anti-patterns, and structure project documentation for universal applicability.

Claude MD creates or updates CLAUDE.md files using best practices for AI agent onboarding. It audits existing files for quality and applies progressive disclosure to keep instructions focused and under 300 lines.

CLAUDE.md Authoring creates, updates, and audits CLAUDE.md files following best practices for optimal AI agent onboarding, using progressive disclosure and removing anti-patterns to keep instructions concise.

CLAUDE.md Guide creates or updates CLAUDE.md files following best practices for optimal AI agent onboarding. Use it to draft a new file, improve an existing one, or audit current content against recommended structure and length.

Self-Assessment runs an interactive quiz covering 10 Claude Code feature areas, scores per-topic proficiency, and identifies skill gaps to generate a personalized learning path.

Block No-Verify Hook configures a PreToolUse hook in Claude Code settings to block git commands that include bypass flags like --no-verify and --no-gpg-sign. Use it when setting up projects that enforce commit quality gates and want to prevent AI agents from skipping pre-commit hooks.

NFT Standards implements ERC-721 and ERC-1155 NFT contracts with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT collections, building marketplaces, or implementing digital asset systems.

Parallel Feature Development coordinates parallel feature work by defining file ownership boundaries, interface contracts, and integration patterns so multiple agents can implement different parts of a system without merge conflicts.

Task Coordination Strategies decomposes complex tasks into parallelizable units, designs dependency graphs, and monitors workload across agent teams. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.

Team Communication Protocols defines messaging rules for agent teams: when to use direct messages, broadcasts, plan approvals, and shutdown requests, plus anti-patterns to avoid.

Team Composition Patterns provides heuristics and preset configurations for designing multi-agent teams in Claude Code, covering team sizing, agent type selection, and display modes. Use it when deciding how many agents to spawn, choosing between review, feature, or debug teams, or configuring teammate display modes.