DevOps e Infra

Amazon Working Backwards PR/FAQ generator that forces customer-outcome thinking before any code is written. Produces a press release, an internal FAQ, and an external FAQ as a single decision artifact.

Generate production-grade operational runbooks from codebase analysis. Covers deployment procedures, incident response, database maintenance, scaling operations, and monitoring setup. Every step includes copy-paste commands, verification checks, rollback procedures, escalation paths, and time estimates. Use when bootstrapping ops docs, preparing for on-call, or post-incident improvements.

Notion expert for product management workflows. Covers database design for PRDs, OKRs, Roadmaps, and Decisions; property types (relation, rollup, formula); view design (Board, Timeline, Calendar, Gallery, Table); page architecture; Notion-flavored Markdown blocks; Notion REST API patterns; and sync patterns with Jira, Linear, and GitHub.

Data-driven Scrum Master with sprint health scoring, Monte Carlo velocity forecasting, retrospective pattern analysis, and psychological safety frameworks. Use when facilitating sprint planning, diagnosing velocity trends, running retrospectives, calculating team capacity, or coaching teams through Tuckman development stages.

Structured PM interview preparation across product sense, execution, strategy, behavioral, and technical rounds, using CIRCLES, AARM, STAR, and the estimation framework. Calibrated to APM, PM, Senior PM, and Group PM rubrics.

EU AI Act readiness assessment + sprint playbook. Use when preparing for the Aug 2026 high-risk AI system requirements deadline, when notified-body conformity assessment is scheduled, when GPAI (general-purpose AI) obligations apply, or when annual readiness assessment is due. Pairs with our deep eu-ai-act-specialist skill — that one builds the program; this one preps for the specific assessment.

This skill should be used when the user asks to "estimate LLM costs", "count tokens in prompts", "optimize prompt token usage", "compare model pricing", or "reduce LLM API costs".

Design and generate CI/CD pipelines from detected project stack signals. Covers GitHub Actions, GitLab CI, CircleCI, and Buildkite with caching, matrix builds, deployment strategies (blue-green, canary, rolling), environment gates, and security scanning. Use when bootstrapping CI, migrating pipelines, or optimizing build times.

Complete environment and secrets management lifecycle. Covers .env file scaffolding, validation scripts, secret leak detection in git history, credential rotation playbooks, and integration with HashiCorp Vault, AWS SSM, 1Password CLI, and Doppler. Use when setting up projects, scanning for leaked secrets, or rotating credentials after an incident.

FDA Quality System Regulation (21 CFR 820 / QMSR) audit-prep playbook for medical device companies. Use when an FDA inspection is announced, when preparing for the new QMSR (Quality Management System Regulation, 2026), when 483 / Warning Letter response is needed, or when annual readiness assessment surfaces gaps. Pairs with our fda-consultant-specialist for program-building; this skill is the aud

Design, build, and operate Kubernetes operators using the operator pattern. Use when extending Kubernetes with a custom controller for a domain object (database, message queue, ML pipeline, internal platform primitive), deciding between operator-SDK / Kubebuilder / controller-runtime / metacontroller, designing CRDs with proper schema and conversion, implementing reconciliation loops that are idem

Data leadership advisor for Chief Data Officers on data strategy, governance, quality, monetization, platform decisions, and team design. Use when defining a data strategy, scoring data maturity, auditing a data governance program, evaluating a data platform stack, designing the data org, or preparing the data section of a board update.