Reusable better-chatbot patterns for custom deployments. Use for server action validators, tool abstraction, multi-AI providers, or encountering auth validation, FormData parsing, workflow execution errors.

better-chatbot project conventions and standards. Use for contributing code, following three-tier tool system (MCP/Workflow/Default), or encountering server action validators, repository patterns, component design errors.

Work with Leavn Bible features - chapter rendering, verse search, translations, reading modes, AI transformations, Scripture database

Interactive skill for creating new bible study tools that generate AI-readable commentary data. Guides users through defining practical tasks, setting up proper file structure, and establishing self-learning loops for data generation.

Expert assistance for Azure Bicep infrastructure-as-code. Provides best practices for authoring Bicep templates, Azure resource type discovery with API versions, resource schema retrieval, and Azure Verified Modules (AVM) guidance. Use when writing Bicep files, deploying Azure resources, looking up resource types/schemas, or working with AVM modules.

Standards and tools for creating, maintaining, and refactoring NIDM-integrated BIDSapps that run through BABS. Use when working with sensein BIDSapp repositories (freesurfer_bidsapp, mriqc-nidm_bidsapp, ants_bidsapp) or creating new BIDSapps. Helps with repository structure consistency, NIDM integration patterns, CLI argument standardization, BIDS-compliant output structures, and BABS configuration.

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Use this skill when creating or updating Bigeye monitoring configurations (bigconfig.yml files) for BigQuery tables. Works with metadata-manager skill.

The core skill for working within the bigquery-etl repository. Use this skill when understanding project structure, conventions, and common patterns. Works with model-requirements, query-writer, metadata-manager, sql-test-generator, and bigconfig-generator skills.

Fast, cloud-based patent searching across 76 million+ worldwide patents using Google BigQuery - keyword search, CPC classification, patent details retrieval

Use bigquery CLI (instead of `bq`) for all Google BigQuery and GCP data warehouse operations including SQL query execution, data ingestion (streaming insert, bulk load, JSONL/CSV/Parquet), data extraction/export, dataset/table/view management, external tables, schema operations, query templates, cost estimation with dry-run, authentication with gcloud, data pipelines, ETL workflows, and MCP/LSP server integration for AI-assisted querying and editor support. Modern Rust-based replacement for the Python `bq` CLI with faster startup, better cost awareness, and streaming support. Handles both small-scale streaming inserts (<1000 rows) and large-scale bulk loading (>10MB files), with support for Cloud Storage integration.

Create and read bigWig browser tracks for visualizing continuous genomic data. Convert bedGraph to bigWig, extract signal values, and generate coverage tracks using UCSC tools and pyBigWig. Use when preparing coverage tracks for genome browsers or extracting signal at specific regions.

Classify BIM elements using AI and standard classification systems. Map elements to UniFormat, MasterFormat, OmniClass, and CWICR codes.

Advanced binary exploitation and mitigation bypass

Generate reproducible bioinformatics/data-science Methods + run documentation from workflow run artifacts (Nextflow/Snakemake/CWL), including a top-of-doc workflow summary, exact executed commands, tool versions, parameters, QC, and outputs.

Set up and execute phylogenetic biogeographic analyses using BioGeoBEARS in R. Use when users request biogeographic reconstruction, ancestral range estimation, or want to analyze species distributions on phylogenies. Handles input file validation, data reformatting, RMarkdown workflow generation, and result visualization.

Use when implementing data analysis pipelines, statistical tests, or bioinformatics workflows in code (Python/R), particularly for genomics, transcriptomics, proteomics, or other -omics data.

Orchestrate hypothesis-driven bioinformatics research projects.

Update Biome linting rules, formatting configs, and import organization settings. Use when adding new lint rules, customizing code style, or fixing workspace-specific linting issues.

Use when biome configuration including biome.json setup, schema versions, VCS integration, and project organization.

Use when formatting JavaScript/TypeScript code with Biome's fast formatter including patterns, options, and code style management.

Use when applying Biome's linting capabilities, rule categories, and code quality enforcement to JavaScript/TypeScript projects.

Biome linter/formatter setup. Use when configuring Biome as an alternative to ESLint + Prettier.

Biome 2.x linting and formatting patterns. Use when configuring code quality tools, setting up linting rules, formatting code, or integrating with CI/CD. Covers migration from ESLint/Prettier.

Validates jump metrics against physiological norms. Use when analyzing CMJ or drop jump results, discussing RSI values, jump heights, ground contact times, or when metrics seem unusual.

Generate thematic, prose-style narrative digests from GitHub activity

This skill enables interaction with BitBucket Server REST API for Pull Request management. Use when the user wants to create, review, comment on, merge, list pull requests, read comments, or manage tasks on BitBucket Server.

Manage repositories, check pipelines, review PRs, and collaborate on Bitbucket

Use when exploring Bknd's auto-generated API endpoints. Covers REST endpoint patterns, route listing, module base paths, SDK method mapping, admin panel API explorer, and understanding the API structure.

Use when assigning permissions to roles in Bknd. Covers permission syntax (simple strings, extended format), permission effects (allow/deny), policies with conditions, entity-specific permissions, and fine-grained access control patterns.

Use when setting up Bknd SDK in a frontend application. Covers Api class initialization, token storage, auth state handling, React integration with BkndBrowserApp and useApp hook, framework-specific setup (Vite, Next.js, standalone), and TypeScript type registration.

Use when inserting new records into a Bknd entity via the SDK or REST API. Covers createOne, createMany, creating with relations ($set), response handling, error handling, and common patterns for client-side record creation.

Use when creating custom API endpoints in Bknd. Covers HTTP triggers with Flows, plugin routes via onServerInit, request/response handling, sync vs async modes, accessing request data, and returning custom responses.

Use when troubleshooting Bknd issues, debugging errors, fixing common problems, or diagnosing why something isn't working. Covers CLI debug commands, error codes, logging, common issues and solutions.

Use when deploying a Bknd application to production hosting. Covers Cloudflare Workers/Pages, Node.js/Bun servers, Docker, Vercel, AWS Lambda, and other platforms.

Use when configuring environment variables for Bknd projects. Covers .env files, secrets management, env injection in config, platform-specific variables, and production security.

Use when modifying existing Bknd schema. Covers renaming entities, renaming fields, changing field types, altering field constraints, handling destructive changes, data migration strategies, and the sync workflow.

Use when preparing a Bknd application for production deployment. Covers security hardening, environment configuration, isProduction flag, JWT settings, Guard enablement, CORS, media storage, and production checklist.

Use when securing specific API endpoints in Bknd. Covers protecting custom HTTP triggers, plugin routes, auth middleware for Flows, checking permissions in custom endpoints, and role-based endpoint access.

Use when setting up user registration flows in a Bknd application. Covers registration configuration, enabling/disabling registration, default roles, password validation, registration forms, and custom fields.

Use when implementing row-level security (RLS) in Bknd. Covers filter policies, user ownership patterns, public/private records, entity-specific RLS, multi-tenant isolation, and data-level access control.

Use when populating a Bknd database with initial or test data. Covers the seed function in options, ctx.em.mutator() for insertOne/insertMany, conditional seeding, environment-based data, and common patterns for dev/test fixtures.

Use when writing tests for Bknd applications, setting up test infrastructure, creating unit/integration tests, or testing API endpoints. Covers in-memory database setup, test helpers, mocking, and test patterns.

Apply Eskil Steenberg's black box architecture principles to build modular, maintainable software. Automatically refactors code into replaceable components, designs system architectures with clean boundaries, and debugs with modular isolation.

Blender 3D creation suite for modeling, animation, rendering, compositing, video editing, and game development. Use for 3D modeling, sculpting, animation, shading, rendering, simulation, video editing, and Python scripting.

Blind peer review for code - multiple agents critique independently, then synthesize privately to avoid groupthink

Systematically identify what's missing in non-fiction writing—both blind spots (inherent limitations) and blank spots (gaps that could be addressed). Use before finalizing non-fiction or when feedback feels incomplete.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Parallelizes multi-issue sprints by running independent Claude agents in isolated git worktrees. Each agent creates a PR, self-reviews to 10/10 with 100% issue coverage, then PRs are sequentially merg

Create working, tested Bloblang transformation scripts from natural language descriptions.