Code principles audit worker (L3). Checks DRY (7 types), KISS/YAGNI, TODOs, error handling, DI patterns. Returns findings with severity, location, effort, recommendations.

Dependencies and reuse audit worker (L3). Checks outdated packages, unused dependencies, reinvented wheels, custom implementations of standard library features. Returns findings with severity, location, effort, recommendations.

Observability audit worker (L3). Checks structured logging, health check endpoints, metrics collection, request tracing, log levels. Returns findings with severity, location, effort, recommendations.

Test suite audit coordinator (L2). Delegates to 5 workers (Business Logic, E2E, Value, Coverage, Isolation). Aggregates results, creates Linear task in Epic 0.

Business Logic Focus audit worker (L3). Detects tests that validate framework/library behavior (Prisma, Express, bcrypt, JWT, axios, React hooks) instead of OUR code. Returns findings with REMOVE decisions.

E2E Critical Coverage audit worker (L3). Validates E2E coverage for critical paths (Money 20+, Security 20+, Data 15+). Pure risk-based - no pyramid percentages.

Coverage Gaps audit worker (L3). Identifies missing tests for critical paths (Money 20+, Security 20+, Data Integrity 15+, Core Flows 15+). Returns list of untested critical business logic with priority justification.

Test Isolation + Anti-Patterns audit worker (L3). Checks isolation (APIs/DB/FS/Time/Random/Network), determinism (flaky, order-dependent), and 6 anti-patterns.

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 architectural layer boundaries, detects violations (code in wrong layers), checks pattern coverage. Invoked by ln-640 once per audit.

Coordinates dependency upgrades across all detected package managers

Coordinates project structure migration to Clean Architecture

Coordinates Docker, CI/CD, and environment configuration setup via auto-detection

Creates test infrastructure with Vitest, xUnit, and pytest

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

Executes all test suites and reports results with coverage

Run and interact with lnd Lightning Network daemon in Docker. Use for Lightning development, testing payment channels on regtest, managing lnd containers, and calling lnd RPC endpoints (getinfo, connect, open/close channels, pay/receive). Supports bitcoind, btcd, and neutrino backends.

load-context

Validate system capacity with realistic load tests.

Performance and load testing for API endpoints, payment pipeline, and concurrent user scenarios

| Atributo | Valor |

Create and manage K6 load tests for REST and GraphQL APIs. Use when creating load tests, writing K6 scripts, testing API performance, debugging load test failures, or setting up performance monitoring. Covers REST endpoints, GraphQL operations, data generation, IRI handling, configuration patterns, and performance troubleshooting.

Auto-activates when user mentions load test, performance test, stress test, k6, Artillery, benchmark, or scalability testing. Expert in designing and executing performance tests.

Run bioinformatics analyses using Lobster AI - single-cell RNA-seq, bulk RNA-seq, literature mining, dataset discovery, quality control, and visualization. Use when analyzing genomics data, searching for papers/datasets, or working with H5AD, CSV, GEO/SRA accessions, or biological data. Requires lobster-ai package installed.

Install, configure, and validate local ClickHouse for gapless-crypto-clickhouse development and backtesting. Use when setting up local development environment, enabling offline mode, improving query performance for backtesting, or running E2E validation. Includes mise/Homebrew/apt installation, mode detection, connection validation, and E2E workflow scripts.

skill that dictates the deployment strategy for local development

PM2-based local development server management for Empathy Ledger. Handles port conflicts and auto-restart.

Comprehensive guide for starting and troubleshooting the Orient local development environment.

Local Kubernetes development with EKS parity using Kind, LocalStack for AWS services, and local Keycloak for authentication testing

Local environment management - run SQL queries, set up fake payments, reset test data. Use when the user needs help with local database operations or test data setup.

Local Frappe development environment for testing APIs before production deployment. Use when developing or testing Python/API changes locally.

local-knowledge

Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like LoRA and QLoRA.

Start and manage a local OCI registry for Bottlerocket kit development

Use when code changes touch database, cache, queue, or other service-dependent components - enforces testing against real local services instead of mocks

This skill walks users through setting up the Magnet MCP server for local development and testing with their MCP client (Claude Code, Cursor, Claude Desktop).

Expert guide for understanding the Local Skills MCP server repository - its structure, architecture, and implementation. Use when exploring this MCP server's codebase, understanding how Local Skills MCP works internally, or contributing to the project.

Enable HTTPS for local development with trusted SSL certificates. Use when developers need to test SSL/TLS features, work with third-party APIs requiring HTTPS, or simulate production environments. Supports mkcert, OpenSSL, and automatic certificate trust configuration for macOS, Linux, and Windows.

Local testing setup - start dev server with mock Claude and run tests (unit tests, CLI E2E)

Managing local .NET tools with dotnet-tools.json for consistent tooling across development environments and CI/CD pipelines.

Run local AI models with LocalAI. Deploy OpenAI-compatible API for LLMs, embeddings, audio, and images. Use for self-hosted AI, offline inference, and privacy-focused AI deployments.

Specialized in multi-language support (i18n) for Gravito. Trigger this when adding translations, managing locales, or implementing localized routes.

Manage localization strings, find missing translations, validate .strings files

Finds WHERE code lives in a codebase - locates files by topic/feature, categorizes by purpose, organizes findings. Super grep/glob/ls tool for navigating unfamiliar codebases.

Use when creating llmring.lock file for new project (REQUIRED for all applications), configuring model aliases with semantic task-based names, managing environment-specific profiles (dev/staging/prod), or setting up fallback models - lockfile creation is mandatory first step, bundled lockfile is only for llmring tools

Use Lockplane for safe database schema management - define schemas in .lp.sql files, validate, and apply with shadow DB testing

Author or update Locque .lq code and tests with the canonical M-expr syntax, CBPV rules, data/match forms, modules/imports/opens, and project conventions.

Record agent run logs into .tmp/logs/. Use this to maintain an audit trail of agent actions and errors.

Execute PowerShell commands on Windows systems with security constraints

Parse and analyze logs to identify errors, patterns, and issues.