Claude Skills by bg-szy

Upload approved local HTML, markdown, or image assets to a Stitch project using direct MCP for small DESIGN.md files or the bundled API script for larger files.

Delegate routine work to subagents — boilerplate generation, data transformation, file analysis, documentation drafting. Use when splitting tasks into independent subtasks for parallel subagent execution.

Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks

Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pg_cron, pgmq), vector/semantic search (pgvector), and restoring dumps (pg_restore) or im...

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, declarative schemas, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector); ...

Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.

Inspect CSV datasets for schema, quality, modeling readiness, and feature analysis.

Build or review production-ready Tavily SDK and API integrations for web search, extraction, crawling, mapping, and research. Use when implementing Tavily in an agent, RAG pipeline, or application rather than only running one CLI command.

Route Tavily web-search, extraction, mapping, crawling, and cited-research requests to the narrowest `tvly` command. Use for command-line Tavily work, installation checks, authentication setup, or choosing among the specialized Tavily skills.

Crawl and extract a bounded set of pages from one website through Tavily. Use for documentation downloads, site-section collection, or semantic multi-page extraction when map plus individual extract calls are insufficient.

Run programmatic Tavily search and extraction while filtering raw results outside the main agent context. Use for multi-step or high-volume research where titles, snippets, and selected passages should be curated before synthesis.

Extract clean Markdown or text from one or more known URLs through Tavily. Use when the user supplies specific pages and needs their content, including query-focused chunks or JavaScript-rendered pages.

Discover and filter URLs on a known website through Tavily without extracting every page. Use to locate a specific subpage, inspect site structure, or prepare a bounded map-then-extract workflow.

Run Tavily's multi-source research workflow for comparisons, market analysis, literature-oriented exploration, or detailed cited reports. Use only when bounded search and extraction are insufficient.

Search the web through Tavily with bounded depth, domains, dates, and result counts. Use when the user needs current information or source discovery and does not already have a specific URL.

Write the test first, watch it fail, write minimal code to pass

Never test mock behavior. Never add test-only methods to production classes. Understand dependencies before mocking.

RED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes

Understand how ideas evolved over time to find old solutions for new problems and avoid repeating past failures

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selecti...

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

Create isolated git worktrees with smart directory selection and safety verification

Skills wiki intro - mandatory workflows, search tool, brainstorming triggers

Legacy compatibility entry for prompts or documentation that explicitly name `using-superpowers`. Route new skill-discovery workflows to `using-skills`; do not activate both entrypoints for the same task.

Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. \"deploy to vercel\", \"set up vercel\", \"add environment variables to vercel\".

Deploy applications and websites to Vercel. Use when the user requests deployment actions like \"deploy my app\", \"deploy and give me the link\", \"push this live\", or \"create a preview deployment\".

Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core W...

Run verification commands and confirm output before claiming success

Vite 8.0.10 build tooling — HMR, fast builds, plugins, and optimized production assets. Use when configuring Vite, setting up React/Vue projects with Vite, or optimizing frontend build performance.

Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".

Visual inspection of live websites to find and fix design issues. Use when reviewing UI layout/design, checking responsive design visually, detecting visual inconsistencies, or diagnosing CSS/accessibility problems at the source code level. Not for automated E2E testing.

Trigger when the user asks for explanations of web development concepts, code breakdowns, or learning guidance.

Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to \"audit my site\", \"review web quality\", \"run lighthouse audit\", \"check page quality\", or \"optimize my website\".

Playwright automation, Chrome DevTools debugging, and browser interaction testing. Use for E2E/unit tests, capturing screenshots, inspecting network/console logs, or validating user flows in web applications.

Dispatch to the right problem-solving technique based on how you're stuck

Word (.docx) manipulation via MCP server. Use for reading, creating, editing, formatting Word documents including tables, footnotes, comments, images, headers, styles, and PDF conversion.

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

Review docs/prose for Writing Guidelines compliance. Use when asked to \"review my docs\", \"check writing style\", \"audit prose\", \"review docs voice and tone\", or \"check this page against the writing handbook\".

Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context

TDD for process documentation - test with subagents before writing, iterate until bulletproof

X (Twitter) Scraper API and X API Alternative instructions for Xquik scraping and connected X account action planning. Also use for Xquik Radar or Xquik support tickets only when the user names that feature. Do not load or use this Skill for official X developer setup unless the user compares it with Xquik. Trigger when an X or Twitter task asks about posts, replies, likes, follows, messages, search, users, timelines, followers, exports, giveaways, draws, monitors, Xquik webhooks, MCP setup, ...

Use this skill any time a spreadsheet file is the primary input or output. Covers reading, editing, cleaning, modeling, formula repair, workbook generation, and converting tabular data into validated spreadsheet deliverables.

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, coverage-bounded integrity checks, two-stage peer review, and auditable quality-assurance artifacts. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end p...

Cell-free DNA analysis pipeline from plasma sequencing to tumor monitoring. Preprocesses cfDNA reads, analyzes fragment patterns, estimates tumor fraction from sWGS, and optionally detects mutations from targeted panels. Use when analyzing liquid biopsy samples for cancer detection or monitoring.

Align long reads using minimap2 for Oxford Nanopore and PacBio data. Supports various presets for different read types and applications. Use when aligning ONT or PacBio reads to a reference genome for variant calling, SV detection, or coverage analysis.

Polish assemblies and call variants from Oxford Nanopore data using medaka. Uses neural networks trained on specific basecaller versions. Use when improving ONT-only assemblies or calling variants from Nanopore data without short-read polishing.

Quality control for long-read sequencing data using NanoPlot, NanoStat, and chopper. Generate QC reports, filter reads by length and quality, and visualize read characteristics. Use when assessing ONT or PacBio run quality or filtering reads before assembly or alignment.

Detect structural variants from long-read alignments using Sniffles, cuteSV, and SVIM. Use when detecting deletions, insertions, inversions, translocations, or complex rearrangements from ONT or PacBio data, especially those missed by short-read methods.

Perform geometric calculations on protein structures using Biopython Bio.PDB. Use when measuring distances, angles, and dihedrals, superimposing structures, calculating RMSD, or computing solvent accessible surface area (SASA).