Setup Pre-Commit
Matt PocockSets up Husky pre-commit hooks with lint-staged, type checking and tests in the current repo.
By agent · Cursor
Skills in the open SKILL.md format that Cursor reads. Each one has a plain-language summary and the command to install it.
$ npx skills add <author>/<skill> --agent cursorReplace the placeholder with the author and skill name from the skill's page. Start a new Cursor session afterwards so the skill is picked up.
Sets up Husky pre-commit hooks with lint-staged, type checking and tests in the current repo.
Grills you about a plan, decision or idea to stress-test your thinking.
Compacts the current conversation into a handoff document that another agent can pick up.
Teaches you a new skill or concept inside the current workspace.
Turns a decision you cannot fully answer into a questionnaire for someone else to fill in.
Guides writing documents meant for agents, such as skills, AGENTS.md and CLAUDE.md.
Behavioural guidelines that reduce common LLM coding mistakes: avoid overcomplication, make surgical changes and state assumptions.
Creates generative art in p5.js with seeded randomness and interactive parameters, such as flow fields and particle systems.
Applies Anthropic's brand colours and typography to slides, documents and other artifacts.
Designs posters and other static visual pieces as PNG or PDF files, starting from a written design philosophy.
Reference for the Claude API and Anthropic SDKs: model ids, pricing, parameters, streaming, tool use, MCP, caching and model migration.
Guides you through co-authoring a document such as a proposal, technical spec or decision doc in structured stages.
Creates, reads and edits Word documents (.docx) and Word templates, including formatting, tracked changes and comments.
Writes internal communications such as status reports, leadership updates and incident reports in the formats a company already uses.
Guides the creation of MCP servers whose tools let an LLM work with external APIs and services.
Reads, creates and edits PDF files: extract text and tables, merge, split, rotate, watermark and fill forms.
Creates, reads and edits PowerPoint files (.pptx), from new slide decks to changes in an existing presentation or template.
Creates animated GIFs sized for Slack, with validation tools for its constraints and a set of animation concepts.
Styles slides, documents, reports and landing pages with one of ten preset themes of colours and fonts, or a custom one.
Builds multi-component claude.ai HTML artifacts with React, Tailwind CSS and shadcn/ui, for work that needs state or routing.
Tests local web applications with Playwright: verify frontend behaviour, debug the UI, capture screenshots and read browser logs.
Opens, edits, fixes and creates spreadsheets (.xlsx, .xlsm, .csv, .tsv), including formulas, formatting and charts.
Designs banners for social media, ads, website heroes and print, with several art direction options.
Covers brand voice, visual identity, messaging frameworks and brand consistency for branded content.
Questions
Often. A skill is a folder of instructions and scripts in the open SKILL.md format, which Cursor reads. A skill that depends on tools only one agent provides will not carry over, so read the skill's source before you rely on it.
Each skill page has an install command. Run it in a terminal, then start a new Cursor session so the skill is picked up.
An instructions file is loaded in every session and describes the project. A skill is loaded only when a task calls for it, so it can be long and specific without costing context on every turn.