Explorar skills

Analyze relationships in a bounded set of Obsidian notes: candidate links, repeated patterns, contradictions, and follow-up opportunities. Load when user asks to find connections, suggest wikilinks, or surface contradictions. Do NOT use for inbox triage, weekly synthesis, or note promotion.

Audit ML experiment tracking infrastructure for reproducibility gaps, parameter logging completeness, metric capture, artifact management, and pipeline orchestration. Covers MLflow, Weights and Biases, DVC, Sacred, Neptune, Hydra configs, model registries, and produces a reproducibility scorecard (0-30) with actionable fixes for data science teams.

Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.

Use to isolate a bug from a large application into a standalone, runnable script or single test case.

Review healthcare software for operational efficiency: appointment scheduling and resource allocation, clinical workflow burden (order entry clicks, documentation templates, alert fatigue), EHR/LIS/pharmacy/PACS integrations (HL7v2, FHIR, NCPDP SCRIPT, EDI 837/835), patient flow (ADT, bed management, wait times, throughput), quality reporting (CMS, HEDIS, MIPS), staff credentialing and workload ba

Verify database migrations are safe before running them. Checks that migrations apply cleanly, reverse cleanly, preserve data integrity, are idempotent, and will not lock tables or cause downtime on large datasets. Supports Prisma, Knex, Alembic, Django, ActiveRecord, Flyway, TypeORM, Sequelize, and raw SQL. Use when you need to review migrations, check migration safety, validate schema changes, a

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Set up automated releases with semantic versioning, changelog generation, and package publishing. Configures semantic-release, changesets, release-please, goreleaser, or cargo-release based on stack. Generates GitHub Actions CI workflow for automated version bumps, git tags, and npm/PyPI/crates.io publishing. Use when you want automated versioning, need to publish packages, want changelogs from co

Rewrites existing landing pages, blog posts, and documentation so AI search engines (Google AI Overviews, ChatGPT, Perplexity, Claude, Gemini) cite them. Applies the 2026 AEO pattern: 40-80 word direct answer at top, 4-intent classification (definitional / process / comparative / decision), Article + FAQPage + Organization schema, verified authorship, entity-consistent claims. Use when an existing

Provision free LLM API keys from 20+ providers. Health-checks existing keys, opens signup pages, validates new keys, and saves them to your project.

Use when reproducing, isolating, and fixing a bug with the smallest safe change.

Use when adding or reviewing data quality tests for dbt models in warehouse-backed analytics projects. Covers dbt generic tests, singular tests (assert_*.sql), accepted-values macros, dbt_utils patterns, cross-system consistency tests, and warehouse-oriented validation. Use when writing data tests, creating assert_*.sql files, testing business logic, or validating referential integrity.