Results for “engineering”

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

Creates and manages AI agent teams for complex engineering tasks, with model routing, cost optimization, and performance evaluation.

Write a PRD or feature spec that aligns design and engineering — problem with evidence, explicit non-goals, measurable success metrics, and testable acceptance criteria.

Engineering retrospective — generates a data-driven report of development velocity, commit patterns, hotspots, and team insights from git history. Saves results for week-over-week comparison.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations,...

Executable documentation governance with compound engineering and abductive learning. Enforces the Seven Laws through type compilation, schema validation, and hookify-based enforcement. Implements programmatic compound engineering where K' = K ∪ crystallize(assess(τ)) for monotonic knowledge growth. Integrates abstracted abductive learning (OHPT protocol) for systematic debugging and pattern extraction. Trigger when writing code, debugging, establishing governance, or when mentioned vibecode, compound, abductive, or executable documentation. Self-validating and homoiconic.

Keeps AI coding agents tightly scoped by enforcing minimal changes, simplest solutions, and asking before expanding scope.

Provides ClickHouse schema design, query optimization, and data ingestion patterns for high-performance analytical workloads.

Transforms vague UI ideas into structured, Stitch-optimized prompts with design system context and UI/UX keywords.

Prompt and interaction designer for reliable AI behavior. Use when the user asks to talk to Luna, requests prompt engineering, or needs agent behavior specification.

Package a customer escalation for engineering, product, or leadership as a decision-ready handoff — impact, timeline, facts vs. hypotheses, and a specific ask with an owner.

Routes ambiguous or multi-domain engineering requests to the smallest ordered skill set. Do not use for clear single-skill work or same-task follow-ups.

Mobile-first design and engineering doctrine for iOS and Android apps. Covers touch interaction, performance, platform conventions, offline behavior, and mobile-specific decision-making. Teaches pr...

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

Discover, compare, audit, repair, adapt, craft, run, debrief, and publish repeatable AI-agent loops for engineering workflows.

Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide techniques to avoid over-engineering and apply iterative improvements.

Recommend the right AI model for a task by scoring candidates across six dimensions (Reasoning, Engineering, Speed, Breadth, Reliability, Governance) and displaying a spider-chart profile.

ガイドサイト（claude-code-guide / loop-engineering-guide 等、convert.py経由・手書きHTML問わず全ガイドrepo）に新しいHTMLページを追加する際のルール（CSS変数・ダーク/ライトモード対応・視認性チェック・CIテスト通過）を自動適用するスキル。ユーザーが「新しいHTMLページを作って」「インタラクティブな章を追加したい」「HTML章を追加して」と言った時、または /html-guide を呼んだ時にトリガー。

Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.

Reverse engineering de diseños Figma para generar especificaciones técnicas completas listas para implementar en código. Usar cuando el usuario comparte capturas, exports o descripciones de un diseño en Figma y quiere documentarlo técnicamente, extraer tokens de diseño, entender la estructura de layouts, o preparar una spec para que un desarrollador o Claude Code lo implemente. También usar cuando el usuario dice "reverse engineering del diseño", "documenta este Figma", "quiero implementar este diseño", "dame las propiedades CSS de este diseño", "convierte este diseño a código", o cuando comparte pantallazos de Figma (layers, propiedades, canvas). Activar también cuando el usuario quiere crear documentación técnica de un diseño existente antes de pasarlo a Claude Code.

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates with evals.

Generates high-fidelity images using reasoning-driven prompts and structured creative briefs via muapi.ai.

Estrutura prompts para geradores de imagem e vídeo, otimizando custo e consistência com a marca.

Coordinate a full Galyarder Framework release across engineering verification, npm, GitHub, smoke testing, and announcement follow-up.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

Generates feature ideas from PM, Designer, and Engineer perspectives for initial product discovery of a new product.

Apply GDPR-compliant engineering practices across your codebase, covering API design, data models, authentication, logging, retention, and cloud infrastructure.

Design, deploy, and operate production-ready software with stability patterns, capacity planning, and zero-downtime releases.

Provides a structured template for creating new Agent Skills, including sections for description, activation criteria, core concepts, practical guidance, and integration notes.

Guides users through installing dbt Core or the dbt Cloud CLI and points to official dbt documentation and community resources.

Forces a second, harder escalation pass using the original glazer prompt words verbatim, pushing for a sharper replacement thesis rather than more polish.

Keeps AI coding agents tightly scoped by enforcing minimal changes, simplest solutions, and asking before expanding scope or adding dependencies.