NeVibeCode · 599 items
Claude Code skills, plugins, subagents and slash commands
Everything that installs into Claude Code: skills, plugins, subagents and slash commands. Each card has an install command and example prompts.
frontend-design
official skill This skill guides intentional visual design for new interfaces and redesigns. Use it when a generic generated UI is not enough.
Claude.ai
1,025,790installs
skill-creator
official skill Creates and refines skills, then tests them with prompts, evaluations, and performance checks.
Claude.ai
414,180installs
grill-me skill grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts.
1,424,476installs
grill-with-docs skill This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition.
1,219,756installs
improve-codebase-architecture skill This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review.
1,163,035installs
tdd skill Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details.
1,141,062installs
setup-matt-pocock-skills skill Sets up a repository for Matt Pocock engineering skills with issue tracking, triage labels, and domain-document rules. Run it before using the other engineering skills.
1,052,851installs
handoff skill Creates a handoff document from the current conversation so another agent can continue the work. Use it when a task moves to a new session or agent.
1,038,491installs
triage skill This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue.
990,453installs
prototype skill Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase.
986,201installs
grilling skill Stress-test a plan, decision, or idea through structured rounds of questions. Use it when you need to expose assumptions before acting.
979,543installs
domain-modeling skill This skill sharpens project terminology, maintains GLOSSARY.md, and records selected architecture decisions in ADRs. Use it while the domain model is changing.
876,391installs
teach skill Turns the current directory into a learning workspace and keeps progress across sessions. Use it when learning needs to support a concrete goal in your project.
862,247installs
codebase-design skill This skill helps design modules with small interfaces and hidden complexity. Use it when refactoring code, choosing a seam, or making tests easier to write.
850,344installs
pptx
official skill Handles .pptx and .potx files for creating, reading, editing, and validating presentations. Use it whenever an agent needs to touch slide files or templates.
Claude.ai
241,433installs
diagnosing-bugs skill This skill guides an agent through reproducible diagnosis of hard bugs and performance regressions. Use it when code fails, produces wrong results, or becomes slow.
834,802installs
code-review skill Reviews changes from a chosen reference point against repository standards and the originating spec. Use it for a branch, PR, or work in progress.
789,521installs
implement skill Implements work from a specification or tickets, following a test-driven flow and ending with review and a commit. Use it when a coding task needs a defined delivery routine.
774,700installs
ask-matt skill Routes you to the right Matt Pocock skill or flow for the task at hand. Use it when you need a starting point for a feature, prototype, incoming issue, or hard bug.
766,587installs
pdf
official skill This skill lets an agent read, create, and edit PDF files, including forms and scanned documents. Use it when PDF work is part of the task.
Claude.ai
216,041installs
docx
official skill This skill creates, reads, and edits Word documents and templates. Use it for reports, letters, and files that need headings, tables, or page numbers.
Claude.ai
206,304installs
wayfinder skill Maps large, uncertain work as decision tickets in an issue tracker. Use it when the route to a goal needs more than one agent session to clarify.
718,005installs
to-spec skill Turns the current conversation and repository context into a spec, then publishes it to the project issue tracker. Use it when a feature discussion is ready to hand off to an agent.
715,388installs
research skill Researches a question through primary sources and saves the findings as a Markdown file in the repository. Use it for API facts, documentation checks, and delegated reading.
711,295installs
to-tickets skill Turns a plan, spec, or conversation into linked tickets with blocking dependencies. Use it when work needs to be handed to agents or published to a tracker.
711,230installs
xlsx
official skill Creates, reads, edits, and converts spreadsheet files. Use it when the requested deliverable is an Excel workbook or another tabular file.
Claude.ai
187,223installs
webapp-testing
official skill This skill tests local web apps with Playwright, helping agents debug UI behavior, capture screenshots, and inspect browser logs.
Claude.ai
186,758installs
wizard skill This skill creates an interactive bash wizard for manual setup steps, CI secrets, third-party dashboards, and one-off migrations.
553,369installs
git-guardrails-claude-code skill This skill adds a Claude Code hook that stops risky Git commands before they run. Use it when an agent must not push or discard working-tree changes.
499,069installs
to-questionnaire skill Creates a Markdown questionnaire for someone who holds context you need. Use it when a colleague or client must answer before you can make a decision.
498,319installs
setup-pre-commit skill This skill configures pre-commit checks for a JavaScript repository, running Prettier, type checking, and tests before each commit.
489,289installs
scaffold-exercises skill This skill builds course exercise directories with sections, problems, solutions, and explainers. Use it when starting a new course section or creating exercise stubs.
480,196installs
migrate-to-shoehorn skill Replaces as type assertions in tests with helpers from @total-typescript/shoehorn. Use it when tests need partial objects or deliberately invalid data.
475,388installs
writing-for-agents skill Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them.
466,719installs
mcp-builder
official skill This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions.
Claude.ai
130,949installs
wait-what skill This skill asks Claude Code to re-pitch an unclear explanation with more context. It suits repositories that maintain a shared technical vocabulary.
448,541installs
canvas-design
official skill Builds posters and visual art in .png and .pdf by first writing a design philosophy, then expressing it on the canvas.
Claude.ai
121,543installs
brainstorming skill This skill clarifies a task before implementation by asking questions, checking context, and comparing approaches. Use it for new features and other creative work.
CX Codex
404,045installs
web-artifacts-builder
official skill This skill builds complex claude.ai HTML artifacts with React, Tailwind CSS, and shadcn/ui. Use it for interfaces with state or routing.
Claude.ai
112,122installs
brand-guidelines
official skill Applies Anthropic's official brand colors and fonts to documents, slides and other artifacts. Useful whenever something needs to match the company look.
Claude.ai
109,043installs
1–40 of 599
Claude Code is the Anthropic agent for the terminal and IDEs, and it has the widest extension set of any platform we track: CLAUDE.md and .claude/rules/, skills in .claude/skills/, subagents in .claude/agents/, hooks on 33 events, output styles, MCP servers, plugins and marketplaces. Slash commands from .claude/commands/ have been merged into skills, and old files still work.
Since version 2.1.277 Claude Code reads AGENTS.md natively, but only when the project has no CLAUDE.md (a CLAUDE.local.md counts too). Its skills and subagents travel well: Cursor and Copilot read .claude/skills/ and .claude/agents/ directly. Project MCP servers from .mcp.json need your approval, and tool output is capped at 25,000 tokens.
Where to start: installing skills, plugins, subagents, hooks.
