Claude Skills by kina2711

Build governed staging, intermediate, mart, dimensional and semantic models with tests, documentation, lineage, incremental logic and release controls. Use for Analytics Engineering, dbt or analytics-ready dataset work. Route source ingestion to data-engineering and catalog, lineage harvesting or metadata quality to metadata-engineering-and-catalog.

Turn books, PDFs, EPUBs, documents or source collections into reusable agent skills, Second Brain packs, career/interview/project systems, curricula, workflows or technical content. Use when structure, frameworks, decisions, citations, copyright controls and progressive loading matter more than a summary.

Use when the user asks to build agent skill, requests the stated deliverable, or supplies an artifact that requires this atomic workflow. Do not select by job title alone.

Use when the user asks to publish derived skill, requests the stated deliverable, or supplies an artifact that requires this atomic workflow. Do not select by job title alone.

Use when the user asks to validate derived skill, requests the stated deliverable, or supplies an artifact that requires this atomic workflow. Do not select by job title alone.

Design, build, test and govern BI semantic models, KPIs, dashboards, reports, interactions, row-level security, refresh, accessibility and adoption. Use for BI Engineer, reporting or dashboard work. This skill owns the semantic layer upward; pipelines belong to data-engineering.

Maintain and index company-specific data context including glossary terms, metrics, datasets, systems, owners, policies and platforms. Use when Claude must initialize, route, retrieve or verify organizational context without storing secrets.

Design and deliver role-based Data Academy curricula with theory, labs, capstones, assessments, remediation, certification and effectiveness measurement. Use for structured learning programs across Data roles and levels. Route hiring loops, scorecards and candidate evaluation to data-talent-acquisition-and-interview; this skill teaches, never selects.

Perform programmatic EDA, reproducible analysis, SQL-to-business explanation, methodology communication, peer review and retrospective. Use for Data Analyst requests involving datasets, SQL, statistics, insights or analytical quality.

Design data target states, domains, models, integration patterns, contracts, technology decisions, migrations and architecture reviews. Use for enterprise, solution or data architecture deliverables and ADRs.

Elicit and validate data requirements, business rules, processes, use cases, acceptance criteria and traceability. Use for Data Business Analyst work or when an ambiguous business request must become an implementation-ready specification.

Build evidence-based Data career systems, persistent cross-skill learner memory, mastery/decay tracking, compact transition context, competency maps, portfolios, interview readiness, remediation and review cycles. Use when prior learning should be reused without reteaching; never infer mastery from exposure or fabricate experience.

Route ambiguous, organizational or multi-role Data Department requests and compose governed workflows with owners, dependencies, gates and handoffs. Use when the named deliverable cannot be built until another role sources, models or certifies its inputs — a dashboard from systems not yet ingested, an incident spanning monitoring, diagnosis and revalidation, a rebuild combining discovery, implementation and proof. Also owns the run itself: continuing an in-flight workflow from its last approv...

Improve data developer setup, repositories, end-to-end data-path understanding, templates, local environments, CI feedback, standards and inner-loop productivity. Use for Data DevEx, repo reverse engineering, evidence-based walkthroughs or golden paths.

Create validated data documentation, ADRs, runbooks, postmortems, ERDs, BPMN, sequence, state, lineage and architecture diagrams. Use when the primary deliverable is a data document or technical diagram.

Enable data teams through technical onboarding, learning plans, explanations, walkthroughs, pairing, knowledge checks, articles and knowledge-base curation. Use for internal data enablement or knowledge-transfer work.

Design, build, test, diagnose execution plans and operate batch, API, file, CDC and streaming pipelines with idempotency, schema evolution, reconciliation, recovery and runbooks. Use for Data Engineer ingestion, performance or pipeline work. Route feature pipelines and model serving to machine-learning-engineering, dbt-style modelling to analytics-engineering, and catalog or lineage harvesting to metadata-engineering-and-catalog.

Define and operate data ownership, policies, glossary, classification, access governance, retention, certification, stewardship and control evidence. Use for Data Governance, Data Office or Data Steward work.

Plan and operate Data Department preboarding, access readiness, orientation, shadowing, first work, checkpoints, crossboarding, reboarding and offboarding. Use for new-hire or role-transition integration.

Create differentiated personal Data projects for portfolios, learning or capstones from a problem, dataset, repository, role gap, technology, paper, course, open-source issue, incident, constraint or mixed evidence. Use when Claude must select a project mode, assess a reference repo, transform borrowed inspiration into an attributed user-owned thesis, plan execution, or evaluate portfolio proof.

Design and operate data platforms, environments, orchestration, CI/CD, observability, capacity, reliability, cost and disaster recovery. Use for Data Platform, DataOps or platform operations work. The model lifecycle itself belongs to mlops.

Define data quality rules and SLOs, implement observability, reconcile data, triage incidents, run game days and prevent recurrence. Use for Data Quality, Data Reliability or data incident work.

Frame and execute statistical, causal, forecasting, optimization and machine-learning studies with leakage controls, validation, explainability and model-risk evidence. Use for Data Scientist or decision-science work.

Protect data through classification, threat modeling, least privilege, encryption, masking, audit, privacy workflows and incident response. Use for Data Security, Privacy, DSR or sensitive-data risk work.

Design and run structured Data hiring with role profiles, scorecards, interview loops, work samples, rubrics, calibration, debriefs, fairness and validity controls. Use for recruiting or interviewing Data roles. Route curriculum, labs and certification of existing staff to data-academy-and-curriculum; this skill decides who to hire, never how to train.

Build evidence-backed technical series for Facebook in Vietnamese, LinkedIn and Substack in English, and GitHub from research and a canonical article through code, diagrams, channel-native adaptations, QA, publishing and measurement. Use for Airflow, dbt, Spark, Kafka or other technical-content programs.

Build and evaluate governed RAG, retrieval, prompt, tool-using agent and GenAI systems with guardrails, injection testing, monitoring and system cards. Use for production GenAI data products or agents.

Lead data strategy, operating model, portfolio, roadmap, service intake, prioritization, value, adoption and executive governance. Use for Head of Data, CDO or Data Product Management deliverables.

Engineer training pipelines, features, model artifacts, batch or online serving, performance, testing, deployment interfaces and resilience. Use for ML Engineer implementation and productionization work. Route general batch, CDC or streaming ingestion to data-engineering, and registry, drift or model rollout operations to mlops.

Design and operate master entities, identity matching, survivorship, golden records, reference data, hierarchies, stewardship and synchronization. Use for MDM, entity resolution or reference-data work.

Build and operate metadata ingestion, catalog, search, lineage, ownership, usage and metadata quality. Use for data catalog, discovery, technical metadata or lineage engineering requests. This skill describes assets rather than building them, so pipeline construction belongs to data-engineering and transformation modelling to analytics-engineering.

Operate the ML lifecycle through experiment tracking, registry, CI/CD, deployment, monitoring, drift, retraining, rollback, lineage and governance. Use for MLOps, model release or ML platform operations. The underlying platform belongs to data-platform-and-dataops.

Build or operate a local-first AI Second Brain with 1_Nguon, 2_Wiki, 3_Toi and 4_Ket-Qua layers. Use for Obsidian or local-file knowledge systems, migration from Notion/Sheets/Lark, source ingestion, linked notes, personal context, grounded retrieval, reusable outputs, privacy, backup and freshness.

Define product events and metrics, analyze funnels, activation, retention and growth, and design or evaluate experiments. Use for Product Analyst, growth analytics, instrumentation or A/B testing work.

Apply shared data controls for bounded task-context packaging, discovery, schema inspection, profiling, validation, evidence, approvals and handoffs. Use when a data task needs reusable cross-role safeguards, a prompt-ready context bundle or artifact checks.

Translate foreign-language books, documentation, web content and technical material into Vietnamese that reads as a domain expert wrote it, with a fixed glossary, style guide, fidelity review and translation memory. Use for translation or localisation into Vietnamese; route the authoring of new Vietnamese technical content to data-technical-content-and-social.