Software Development Skills
Writing, reviewing, testing and debugging code.
9,435 Software Development agent skills, including Webapp Testing, Web Artifacts Builder, and Mcp Builder.
9,435 skills

Webapp Testing
anthropics
Tests local web apps with Playwright: verifies frontend behavior, debugs UI, captures screenshots and browser logs.

Web Artifacts Builder
anthropics
Scaffolds, builds and bundles complex React + Tailwind + shadcn/ui claude.ai HTML artifacts into one self-contained HTML file.

Mcp Builder
anthropics
Guides building high-quality MCP servers in TypeScript or Python, from planning and tool design through testing and evaluation.

Memory Leak Audit
microsoft
Audits code for memory leaks and disposable-object issues, covering event listeners, lifecycle callbacks and disposal patterns.

Update Screenshots
microsoft
Update the committed blocks-ci screenshot hashes after the "Screenshots & Tests" check fails, or investigate a screenshot diff reported on a PR. Use when asked to update, accept, or refresh component screenshot baselines from CI. This skill should be run as a subagent.

Sessions
microsoft
Guides implementation, review and design work on the Agents Window code under src/vs/sessions in a VS Code-style codebase.

Author Contributions
microsoft
Traces which files a given author contributed to on a branch versus its upstream, following renames, and returns a table.

Accessibility
microsoft
Guides VS Code contributors in adding accessibility help dialogs, accessible views, verbosity settings, signals, ARIA announcements and keyboard support.

Plugin Settings
anthropics
Documents the .claude/plugin-name.local.md pattern for storing per-project plugin settings as YAML frontmatter plus markdown.

Hook Development
anthropics
Guides creating Claude Code plugin hooks: event types, prompt-based and command hooks, config formats, output schemas and validation scripts.

Claude Opus 4 5 Migration
anthropics
Guides migrating prompts and code from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings and optional prompt fixes.

Playwright Dev
microsoft
Guides contributing to the Playwright codebase: adding APIs, MCP tools, CLI commands, vendor dependencies and WebKit updates.

Playwright Cli
microsoft
Drives a real browser from the command line with playwright-cli: navigate, click, fill, snapshot pages, and run or debug Playwright tests.

Web Design Guidelines
vercel-labs
Reviews UI code files against bundled Web Interface Guidelines rules and reports findings in a terse file:line format.
Added to 1 workspace
Jupyter Notebook
openai
Scaffolds and edits Jupyter notebooks for experiments or tutorials using bundled templates and a helper script.
Added to 1 workspace

Hatch Pet
openai
Creates, repairs, validates and packages Codex-compatible animated pet spritesheets and atlases from art, brand cues or references.
Added to 1 workspace
Figma
openai
Fetches Figma design context, screenshots and assets via the Figma MCP server and turns nodes into production code.
Added to 1 workspace

Cookbook Audit
anthropics
Audits an Anthropic Cookbook notebook against a style guide rubric, scoring it out of 20 and giving improvement recommendations.

Image
vercel-labs
Renders JSON specs into SVG and PNG images via Satori, including OG images and social cards.
Added to 1 workspace

Agent Browser
vercel-labs
CLI-based browser automation for AI agents: navigate pages, fill forms, click, screenshot, extract data and test web apps.

Build Mcpb
anthropics
Guides packaging a local MCP server with its runtime into a single .mcpb bundle for one-file installation.

Build Mcp Server
anthropics
Guides developers through designing and scaffolding a Model Context Protocol (MCP) server, from use-case discovery to deployment choice.

Build Mcp App
anthropics
Guides building MCP apps: MCP servers that also serve interactive UI widgets rendered inline in chat hosts.

Claude Security
anthropics
Scans a repository or its changes for security findings and can turn them into verified patch files for the user to apply.