AI skills, ranked by what actually works in production.

Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata.

[Deprecated] Use when building frontend Web apps that talk to CloudBase Relational Database via @cloudbase/js-sdk – provides the canonical init pattern so you can then use Supabase-style queries from the browser. New environments should use PostgreSQL with app.rdb() — see postgresql-development skill instead.

Plan A/B testing platform strategy, architecture, and build-vs-buy decisions for product engineering teams. Use when deciding whether to build or buy an experimentation platform, scoping feature flagging, targeting, assignment, exposure logging, metrics pipelines, dashboards, governance, or evolving a simple testing setup into a durable platform.

Use when triaging an inbound abuse or terms-of-service report — turns the reported behavior into one severity tier and one bounded enforcement action (no-action, warn, restrict, suspend, ban, or escalate to Trust & Safety/Legal), applying proportionality and the mandatory-escalation carve-outs a model does not reach for on its own. Do NOT use for writing the notice sent to a user, routing a general support ticket, or drafting community guidelines.

Reviews TypeScript for the escape hatches that silently defeat the type checker — `any`, `as` assertions, non-null `!`, `@ts-ignore`, bare `object`/`Function`/`{}`, and unchecked index access — and names the type-safe replacement for each (unknown + narrowing, a validated type guard, generics, a precise shape). Use when reviewing or hardening TypeScript code for type safety. Do NOT use for tsconfig setup, non-TypeScript code, or debugging a compile error you are trying to make go away.

Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities are per-token bounding boxes, page raster output, and fully local processing with no cloud API.

Turns company records into structured company research summaries. Use when the user provides company names or records and wants a consistent overview, market position, and relevance assessment.

Testing patterns for unit, integration, and end-to-end tests. Use when writing tests, setting up test fixtures, or validating RLS enforcement. Routes to existing test conventions.

Implement ElevenLabs speech-to-speech, sound effects, audio isolation, and speech-to-text. Use when converting one voice to another, generating sound effects from a text description, removing background noise from a recording, or transcribing audio. Trigger with "elevenlabs speech to speech", "voice changer", "sound effects", "audio isolation", "remove background noise", "elevenlabs transcribe".

Create and manage routing combos with 14 strategies (priority, weighted, round-robin, Auto-combo, etc.). Configure fallback chains, test routing outcomes, and retrieve combo metrics.

Kubernetes execution platform — submits TAO container jobs as single-pod k8s Jobs with NVIDIA GPU scheduling. Use when running on EKS / GKE / AKS / on-prem clusters with the NVIDIA GPU Operator installed, or when integrating TAO into an existing k8s-native ML platform.

Use when producing the recurring at-risk / red-account review row — the one compact line-per-field entry (account, ARR, health band, top risk, play in flight, ask, next milestone and date) that a CS team reads down a save list, instead of a status paragraph. Do NOT use for a one-off escalation up to leadership (escalation-summary), scoring one renewal go/watch/at-risk (renewal-risk-flag), or a full QBR writeup (qbr-summary).

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

Reference-grade guide to getting reliable structured output and tool/function calls out of LLMs — JSON mode vs constrained/grammar-guided decoding, response_format json_schema and tool-schema coercion, Zod/Pydantic validation at the boundary, the validate→repair→escalate→fallback loop, tool-argument validation, idempotency for safe retries, fallback chains, and evals. Use when an LLM must return parseable JSON, fill typed tool arguments, or drive deterministic downstream code.

Fetch brand SVG logos and cloud architecture icons (AWS, Azure, GCP) from theSVG. Use when the user asks for a brand logo, company icon, framework mark, service icon, or any "icon/logo for X" where X is a real brand or cloud service. Returns ready-to-use CDN URLs or raw SVG markup.

MIME type detection and extractor routing in core/mime.rs and core/extractor/bytes.rs — the extension→EXT_TO_MIME→validate→registry→extractor flow, key detection functions, the 115 case-insensitive extension map, priority-based registry selection, wildcard MIME families, and how to add a new MIME type. Load when adding a format, wiring an extractor to a MIME type, or debugging why a file routes to the wrong (or no) extractor.

Provides comprehensive code review capability for Next.js applications, validates Server Components, Client Components, Server Actions, caching strategies, metadata, API routes, middleware, and performance patterns. Use when reviewing Next.js App Router code changes, before merging pull requests, after implementing new features, or for architecture validation. Triggers on "review Next.js code", "Next.js code review", "check my Next.js app".

Review a pull request or diff like a thoughtful senior engineer — prioritized, kind, and focused on what matters. Use when reviewing code, giving PR feedback, or asked to 'review this change'. Produces a structured review: a correctness/design pass, comments ranked by severity (blocking → nit), what's done well, and a clear approve / request-changes call — feedback that improves the code and the author.

Standardizes a free-form postal address into one canonical mailing form — uppercased, punctuation stripped, USPS-approved street-suffix and directional abbreviations, secondary-unit designators, two-letter state, ZIP+4, one element per line. Use when normalizing, deduplicating, or cleaning mailing addresses for storage, matching, or bulk import. Do NOT use for geocoding an address to coordinates, verifying an address is deliverable, or parsing an address into typed fields without reformatting.

Compress tool outputs, logs, and JSON before they enter the context window — structural compression via a deterministic stdlib script (schema + samples + stats instead of 300 raw rows), no API, no summarization loss. Use when asked shrink this tool output, my context is full of JSON, compress these logs before analysis, or stop wasting tokens on raw data. Produces the crushed artifact with its token math shown, the crush-or-keep decision rules, and the fetch-the-original escape hatch.