
Stop hunting across scattered repos. Search by task and install the best prompts and orchestrators in one command.

Community-built prompts and orchestrators, organised around the work you need Claude Code to do.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
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.
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
Look up ACRIS property transaction records for any NYC property — deeds, mortgages, satisfactions, liens, and ownership history. Use when the user asks who owns a building, when it last sold or for how much, or whether there are mortgages or liens against it.
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
CSI outline specification writer — takes a materials or products list and generates structured specs with MasterFormat divisions, performance criteria, and acceptable manufacturers.
Generate a polished HTML slide deck from a topic, outline, or data. Outputs a self-contained .html file with keyboard/touch navigation, responsive typography, and the ALPA (Alpaca Labs) design system — Helvetica, editorial layout, clean white backgrounds.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Clean up an FF&E schedule — normalize casing, dimensions, units, language, materials, and formatting for consistency.
Look up HPD violations, complaints, and building registration for residential buildings.
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
Use when you need to resolve an in-progress git merge/rebase conflict.
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
Set up hierarchical Intent Layer (AGENTS.md files) for codebases. Use when initializing a project, adding context infrastructure, setting up AGENTS.md, or scaffolding AI-friendly project documentation.
Neighborhood context and history — adjacent uses, architectural character, landmarks, commercial activity, and planned development from an address.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data)…
Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
Find visually or functionally similar products from an image, name, or description.
Download, resize, and remove backgrounds from product images at scale
Analyze and optimize tweets for maximum reach using Twitter's open-source algorithm insights. Rewrite and edit user tweets to improve engagement and visibility based on how the recommendation system ranks content.
Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic…
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Capture a project decision as an ADR-style record in decisions/NNNN-slug.md — context, options considered, the call, consequences, status.
Teach the user a new skill or concept, within this workspace.
Auto-tag FF&E products with categories, colors, materials, and style tags using AI.
Compact the current conversation into a handoff document for another agent to pick up. Captures decisions, constraints, and file references without lossy summarisation.
Ask which skill or flow fits your situation. A router over the skills in this repo.
Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel…
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in…
Batch-resize images for web (WebP at 1920/1200/400px), social (center-cropped WebP at Instagram square/portrait, Twitter/X, LinkedIn), slides (center-cropped JPEG at 1024×768 and 1920×1080), and print (300 DPI JPEG at ARCH A 9×12, ARCH B 12×18, ARCH C 18×24).
Look up open and resolved DOB and ECB violations for any NYC building, with class, status, and penalty detail. Use when the user asks whether a building has violations, stop-work orders, or outstanding ECB penalties. NYC only; for housing-code violations use /nyc-hpd.
Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space analysis, strategic recommendations, and team alignment trigger questions.
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
A relentless interview to sharpen a plan or design.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
Look up Board of Standards and Appeals (BSA) variances and special permits for any NYC property. Use when checking whether a lot carries zoning relief — variances, special permits, appeals — that modifies its as-of-right envelope.
AI workplace strategy consultant that builds office space programs through conversation — area splits, room schedules, seat counts, and reports.
Fetch structured FF&E product specs from a list of URLs. Extracts name, brand, dimensions, materials, price, and images into a standardized schedule.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content.
Color palette generator — creates harmonious color palettes from descriptions, moods, or images. Outputs a self-contained HTML file with swatches, hex/RGB/HSL codes, contrast ratios, and example pairings.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Implement a piece of work based on a spec or set of tickets.

Spellbook replaces repo hunting with a repeatable flow: search in the language of the job, inspect the skill, then install it.
npx skills add spellbook/<skill>Describe the task, not the package name.
Review the prompt, author, and intended trigger.
Bring the skill into your workflow in one command.