Claude Skills by aicodedecode

Build a morning briefing ritual with Muse: overnight priorities, today's calendar, weather-aware planning, and top 3 focus items as a concise chat summary.

Idiomatic Dart: null safety, async, Flutter-ready patterns, packages, and tooling. Use when writing, reviewing, or structuring Dart code (Flutter or server/CLI).

Design clear, actionable dashboards with KPI hierarchy, data visualization best practices, and layout patterns.

Analyze text data with NLP — preprocessing, embeddings, topic modeling, sentiment, classification, and evaluation. Use when turning unstructured text into structured insight.

Design annotation pipelines that produce reliable training labels — guidelines, agreement measurement, and quality control.

Run the data science workflow end to end — framing, exploration, feature engineering, modeling, validation, and communicating results. Use when turning raw data into decisions or predictions.

Relational schema design — normalization, keys, constraints, and evolution — use when modeling data or reviewing a schema.

Datadog guidance — APM, logs, metrics, monitors, SLOs, dashboards, and cost control on the Datadog platform.

Manage ML datasets with the datasets ecosystem — loading, streaming, preprocessing, versioning, and sharing. Use when data handling (not modeling) is the bottleneck.

Analytics engineering with dbt — models, tests, and modular SQL pipelines — use when building or maintaining dbt projects.

Domain-Driven Design: bounded contexts, ubiquitous language, aggregates, and tactical patterns. Use when modeling complex domains or structuring domain logic.

Systematic debugging: reproduce, isolate, hypothesize, verify — with tooling for hard bugs. Use when stuck on a bug, flaky failure, or production incident.

Plan and protect deep work: scheduling focus blocks, task selection, shutdown rituals, and measuring depth. Use when important work never gets sustained attention or days fill with shallow tasks.

Affordable serverless GPU inference on DeepInfra — broad open-model catalog with straightforward pricing.

Build with DeepSeek Coder — open code models with strong reasoning and long-context code understanding.

Build with DeepSeek's models — efficient open-weight reasoning models and low-cost API inference.

Deno runtime guidance — TypeScript-first development, permissions, standard library, and deploying Deno apps.

Review Dependabot PRs efficiently: triage, risk assessment, batching, and auto-merge policies. Use when dependency update PRs pile up or you want a sane update workflow.

Manage software composition analysis — SBOMs, vulnerability triage, and remediation of third-party dependencies.

Reusable deployment templates — one-click deploys, blueprints, and environment-as-code — vendor-neutral patterns.

Run structured design critiques with frameworks for feedback that is honest, specific, and actionable.

Prepare flawless design-to-development handoffs with specs, assets, behaviors, and QA processes.

Apply classic design patterns judiciously: when each pattern fits, modern alternatives, and anti-patterns. Use when designing object interactions or reviewing pattern usage.

Build and govern scalable design systems with tokens, components, documentation, and adoption strategy.

Apply the devil's advocate technique: structured critical thinking that stress-tests ideas, plans, and decisions. Use when you need honest critique before committing to something important.

Embed security into DevOps — pipeline security gates, guardrails, and culture that ships fast and safe.

Density functional theory calculations end to end — structure relaxation, convergence, band structures, and defect energetics.

Evaluating diagnostic tests — sensitivity, specificity, ROC analysis, likelihood ratios, and study design.

Compare files, text, and data effectively with diff strategies, semantic comparison, and review workflows.

Structured differential diagnosis — generating, prioritizing, and ruling out diagnostic hypotheses.

Generate and edit images with diffusion models: prompting, seeds, CFG, img2img, inpainting, conditioning, and API integration. Use when adding AI image generation to apps or workflows.

Create digest emails — curated summaries, personalization, frequency strategy, and engagement optimization.

Build discernment habits: nudges and checklists for evaluating claims, spotting manipulation, and thinking clearly under pressure. Use when you want better judgment about what to believe and share.

Run professional Discord servers — community structure, moderation, events, bots, and engagement for teams and audiences.

Distill large models into smaller ones — teacher-student training, data generation, loss design, and quality validation. Use when you need big-model behavior at small-model cost.

Django guidance — project structure, ORM mastery, admin, auth, async views, and production deployment.

Design data loss prevention — data discovery, classification, policy enforcement across endpoint, network, and cloud.

DNA methylation analysis — array and bisulfite-seq processing, DMP/DMR calling, and epigenetic clocks.

Docker guidance — Dockerfile best practices, multi-stage builds, Compose, networking, volumes, and image security.

Search documentation effectively for agents: index docs, query precisely, and cite sources. Use when agents need accurate answers from documentation rather than guesses.

Building robust document ingestion — chunking, metadata, and multi-format pipelines for search and RAG.

Translating documents while preserving layout, tables, and formatting — use for multilingual document workflows.

Write documentation developers actually use: READMEs, API docs, ADRs, runbooks, and docs-as-code workflows. Use when writing or improving technical documentation.

Word document automation — generating, templating, and parsing .docx files — use when working with Word documents programmatically.

Dose-response modeling — EC50 estimation, curve fitting, synergy analysis, and benchmark-dose methods.

.NET guidance — ASP.NET Core APIs, Entity Framework Core, DI, configuration, testing, and container deployment.

Align language models with human preferences using Direct Preference Optimization — no reward model, no RL loop.

Drizzle ORM guidance — schema-as-code, relational queries, migrations, and SQL-first TypeScript data access.

Screening for drug-drug interactions — mechanistic prediction, database checks, and clinical risk assessment.

Systematic drug repurposing — computational screening, evidence triangulation, and validation strategy.