All Skills

L3 Worker. Analyzes single pattern implementation, calculates 4 scores (compliance, completeness, quality, implementation), identifies gaps and issues. Usually invoked by ln-640, can also analyze a specific pattern on user request.

L3 Worker. Audits layer boundaries + cross-layer consistency: I/O violations, transaction boundaries (commit ownership), session ownership (DI vs local).

L3 Worker. Builds dependency graph, detects cycles (DFS), validates boundary rules, calculates coupling metrics (Ca/Ce/I, CCD/NCCD). Adaptive architecture detection.

Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.

Coordinates dependency upgrades across all detected package managers

Universal project bootstrapper: CREATE new or TRANSFORM existing project to production-ready structure

Generates project-specific .claude/commands for Claude Code

Configures structured logging (Serilog/.NET, structlog/Python)

Resource lifecycle audit worker (L3). Checks session scope mismatch, streaming resource holding, missing cleanup, pool config, error path leaks, factory vs injection anti-patterns.

Creates test infrastructure with Vitest, xUnit, and pytest

Upgrades npm/yarn/pnpm dependencies with breaking change handling

Configures Husky, lint-staged, commitlint, and Python pre-commit

Transaction correctness audit worker (L3). Checks missing intermediate commits, transaction scope (too wide/narrow), missing rollback handling, long-held transactions, trigger/notify interaction. Returns findings with severity, location, effort, recommendations.

Runtime performance audit worker (L3). Checks blocking IO in async, unnecessary allocations, sync sleep in async, string concat in loops, missing to_thread for CPU-bound, redundant data copies. Returns findings with severity, location, effort, recommendations.

Query efficiency audit worker (L3). Checks redundant entity fetches, N-UPDATE/DELETE loops, unnecessary resolves, over-fetching, missing bulk operations, wrong caching scope. Returns findings with severity, location, effort, recommendations.

Create comprehensive HTML architecture diagrams showing data flows, business objectives, features, technical architecture, and deployment. Use when users request system architecture, project documentation, high-level overviews, or technical specifications.

Perform bulk code refactoring operations like renaming variables/functions across files, replacing patterns, and updating API calls. Use when users request renaming identifiers, replacing deprecated code patterns, updating method calls, or making consistent changes across multiple locations.

Use when applying validated ED decision rules to reduce unnecessary imaging or testing. Includes Ottawa ankle/knee rules, Canadian C-Spine rule, and the PERC rule.

UI/UX screen design (Apple HIG) + design-to-code translation

Speak the last response aloud using text-to-speech

Personalize COG Second Brain workflow through role pack selection and vault initialization

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants to understand usage patterns, optimize workflow, identify automation opportunities, or check if they're following best practices.

Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.