Навыки: Тестирование

Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.

Desarrollo guiado por pruebas para Laravel con PHPUnit y Pest, factories, pruebas de base de datos, fakes y objetivos de...

Comprehensive testing patterns with Pest. Use when working with tests, testing patterns, or when user mentions testing,...

Run before PRs, after major changes, and pre-deploy.

Measures the inference latency of binarized, 8-bit, and 32-bit convolutional layers on edge devices to evaluate the effi...

Use when working on latency-sensitive Laravel paths — realtime dashboards, streaming, queues, caches, or execution gatew...

Expert at evaluating software projects for production readiness. Assesses codebases holistically to determine what's shi...

Experiment with configs by creating and managing variations. Helps you test different models, prompts, and parameters to...

Use when an engineering task requires diagnosis, runtime verification, correction of recurring agent failures, or coordi...

Performs a hallucination check on machine_readable sections by verifying every element traces back to the original legal...

Multi-layer validation strategy for CFN Loop to prevent "consensus on vapor" and ensure robust, high-quality deliverable...

Use lazy evaluation for expensive operations that may not be needed Use when optimizing code performance. Performance ca...

Implement lazy loading and code splitting to reduce initial bundle size and improve load times. Activate whenever the us...

Code splitting and lazy loading with React.lazy, Suspense, route-based splitting, intersection observer, and preload str...

Build a structured LBO returns analysis with bear/base/bull scenarios, MOIC and IRR sensitivity to entry multiple and le...

Scores an account list that already exists against ICP criteria and returns a priority tier of High, Medium or Low with...

Use when analyzing merged PRs for AI blind spots, extracting patterns from human reviewer feedback, or applying accumula...

Consume an immutable Validate verdict and

Close the loop: after a unit of work ships, read what actually happened — the measure lens (baseline/target/realized), t...

Use when the user says /learn or asks to save this lesson.

Tailored learning coach for deeply learning a subject, skill, tool, or discipline. Use only when the user explicitly inv...

Extract reusable patterns from the session, self-evaluate quality before saving, and determine the right save location (...

Extract actionable patterns, architecture decisions, code conventions, and skill-relevant insights from GitHub/GitLab re...

Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcom...

Review completed non-trivial work, extract evidence-backed lessons likely to recur, and propose the right durable artifa...

Manage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth pre...

Run Robium's learning cycle when asked or when its session-start reminder is approved: consolidate captured signals, abs...

Decision transparency, feedback collection, and debate invitations for AID methodology. Active in ALL phases for ALL rol...

Generate measurable learning outcomes aligned with Bloom's taxonomy and CEFR proficiency levels for educational content....

Facial modeling, expression, blendshape/morph, facial rig and performance capability for speech, emotion, eye/jaw motion...

Engine-ready 3D asset production skill covering topology, LODs, collision, pivots, scale, normals/tangents, material bud...

Organize document evidence into auditable competing hypotheses, source-linked observations, an assessment matrix and doc...

Expert legal advisor specializing in technology law, compliance, and risk mitigation. Masters contract drafting, intelle...

Use when legacy prompts or older framework flows reference `legal-counsel` and you need the modern runtime to resolve th...

Decision-map decomposition for legal matters too big or too foggy for one session. Charts a map (destination, decisions...

Use when an issue has passed review and its parked implementer is revived for the mandatory pre-merge Legion retrospecti...

GATE OBLIGATORIO pre-commit/pre-PR — tests unitarios, CI, cobertura. NADA se sube sin tests en verde. Trigger: Siempre a...

Write a portfolio-level lending risk brief: concentration analysis by sector, geography and single name, vintage perform...

Use when about to edit a file or run a state-changing command, or after any failure, correction, or surprising result.

Use when analyzing patterns across multiple incidents, bugs, failures, or successes to extract organizational learning....

lev POC-to-core builder with prior art, placement, patches, and E2E validation. Use when formalizing POCs, migrating wor...

World-class level design expertise - spatial storytelling, player flow, blockout methodology, and the invisible hand tha...

Architecture audit worker (L3). Checks DRY (7 types), KISS/YAGNI, layer breaks, error handling, DI patterns. Returns fin...

Dead code & legacy audit worker (L3). Checks unreachable code, unused imports/variables/functions, commented-out code, b...

Audit identifiers and namespaces for lexical-semantic and ontological correctness. Detect semantic role misalignment (ag...

Contribute a verified bug fix for lfg or its GrokBuild adapter payload. Use when the user asks to debug and fix an lfg s...

Use when forensically auditing a Claude Code skill/agent/command/workflow library against RULESET.md by a fixed mechanic...

Use when creating or reviewing tests for a TypeScript library, including runtime tests, type tests, regression coverage,...