The directory for
Claude Code skills
Stop hunting across scattered repos. Search by task and install the best prompts and orchestrators in one command.
Find the right skill for the task
Community-built prompts and orchestrators, organised around the work you need Claude Code to do.
Intent Layer
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.
Karpathy Guidelines
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.
Caveman
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user needs terse responses or invokes /caveman.
Meeting Insights Analyzer
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to…
Scaffold Exercises
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
Setup Pre Commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
Migrate To Shoehorn
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.
Writing Great Skills
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
Handoff
Compact the current conversation into a handoff document for another agent to pick up. Captures decisions, constraints, and file references without lossy summarisation.
Twitter Algorithm Optimizer
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.
Content Research Writer
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
Teach
Teach the user a new skill or concept, within this workspace.
Skill Creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's…
Grilling
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.
Git Guardrails Claude Code
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Grill Me
A relentless interview to sharpen a plan or design.
Deep Research
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional…
One path from task to working skill
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.