“data engineering”

Create, transform, and select features with leakage-aware discipline.

Builds a graph-of-plans for end-to-end one-shots: research then questions (must ask; do not guess), then a master graph covering docs-in, architecture…

The full lifecycle in one call — spec, plan, build, verify, review, ship — with approval gates and resume.

When the user wants to build GTM automation with code, design workflow architectures, use AI agents for GTM tasks, or implement the 'architecture over tools'…

Ingénierie du contexte : garder la mémoire compacte et utile

Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates.

Principal Go Engineer skill providing cloud-native, high-performance, resilient, observable, and idiomatic Go backend services and distributed systems.

Audits a given scope (skill, system prompt, tool set, CLAUDE.md, or project) against context engineering best practices and applies improvements.

Use when a project needs persistent storage and no database technology has been chosen yet, or an existing choice is being reconsidered.

Design attribute-based access control.

Beginner-friendly reverse-engineering workflow for Js Hook Engineering.

Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents

Capture data lakes, data marts, data catalogs, domains, products, streams, storage locations, and data quality rules into the DEKC second brain.

use for cross-cutting engineering rules that are language/framework-agnostic, including communication, verification, validation, dependency choices…

Design and analyze engineering experiments or simulations using baseline cases, hypothesis-driven DOE, traceable data processing, defensible plots…

Feed agents the right information at the right time.

Load when writing or optimising a query that will run on BigQuery — partition and cluster filters, MERGE, deduplication, UNNEST, native JSON, numeric typing…

Phishing, pretexting, vishing, credential harvesting.

Use for database schema, queries, migrations, indexing, transactions, ORM behavior, data integrity, and performance across SQL and NoSQL systems.

Turn a manual, repeated AI task into an automated loop.

Authoritative, source-cited reference for prompt engineering and context engineering with current frontier LLMs (Claude Opus 4.7 / Sonnet 4.6, GPT-5.4 / 5.5…

Default engineering control for agent work.

Use when you need to interact with the MCP engineering bridge tools (cm_plan, cm_review, cm_qa, cm_deploy, cm_search).

Full SLMCode engine — context→explore→plan→split→execute→review→test→memory.