Coding standards, frameworks, refactoring, and code review (15.2K skills)
Integrate single-page extraction into an application using Firecrawl scrape. Retrieve Markdown, HTML, links, screenshots, metadata, or structured data from a known URL, and configure how recently cached content may be reused.
Build web search, page content retrieval, structured data extraction, and browser interactions into applications with Firecrawl. The skill guides endpoint selection, credentials, SDK or REST integration, and verification with a real request.
Build web discovery into applications and agent workflows with Firecrawl search. Turn a query into candidate URLs, select useful sources, and decide whether to retrieve page content for further extraction or answers with cited sources.
Provides a minimal starting file for defining a skill, with a name field and placeholders for its description and instructions. The supplied template contains no implemented task or workflow.
Guides implementation and maintenance of Claude applications using language-specific references and official SDKs, the libraries used to call the API. Covers tool integration, streaming responses, model migration, cost reviews, prompt audits, and evaluation workflows.
Build MCP servers, connectors that let AI models use external services through tools. This skill guides API research, tool design, implementation in TypeScript or Python, testing, and evaluation with realistic questions that require multiple tool calls.
Build complex interactive artifacts for claude.ai with React, Tailwind CSS, and shadcn/ui. Start from a configured project, develop interfaces with state management or navigation, and bundle the result into one shareable HTML file.
Create reusable agent skills from recurring tasks, or improve existing ones through test prompts and user feedback. Compare outputs with and without a skill, measure performance, and refine descriptions so skills are invoked for the right requests.
Review code changes and connected code for bugs, security risks, load problems, missing tests, slowdowns, and unnecessary complexity. Get prioritized findings with concrete failure scenarios, small fixes, and the consequences of leaving each issue unresolved.
Guide coding tasks toward the smallest complete change by reusing existing code, platform features, and installed dependencies. Address affected callers and necessary checks, then explain skipped work, unchecked areas, and risks in a brief reply.
Collect comments marking deferred improvements into a ledger grouped by file. Record what was simplified, its stated limit, and when to revisit it, while flagging entries that lack a trigger for future action.
Review code changes for bugs, security risks, failures under expected usage, missing tests, slow paths, and unnecessary code. Receive prioritized findings with concrete failure cases, small fixes, and the consequences of leaving each issue unresolved.
Display a text scoreboard of published Ponytail 5 benchmark results, comparing code volume, generated text tokens, cost, time, and check results against an agent without the skill. The figures describe benchmark averages, not savings in the current project.
Look up ponytail’s three operating levels, related skills, and commands in one reference card. Find how to activate or stop it, set the default mode, and update it in supported environments.
Look up ponytail’s three operating modes, related skills, and commands in a single reference card. Find how to invoke skills, stop or resume the mode, configure defaults, and update the plugin.
Collect comments marking deliberate coding shortcuts into a file-by-file debt ledger. The report shows each shortcut’s stated limit and revisit trigger, flags missing triggers, and leaves the code unchanged.
View published benchmark results comparing ponytail with the same agent without the skill. A simple bar chart shows code volume, output tokens, cost, time, and quality checks, clearly separated from results for the current project.
Guide coding tasks toward the smallest complete change by checking affected code, reusing existing features, and avoiding unnecessary additions. It also calls for relevant checks and concise explanations of what changed, what remains unchecked, and any risks.
Audit an entire code repository or a selected folder for bugs, security risks, load problems, missing tests, slow paths, and excess code. Get up to 20 prioritized findings explaining concrete problems, minimal fixes, and consequences.
Fix Python type checking failures found locally or in CI, the automated checks run on code changes. It identifies affected files, applies targeted fixes to type declarations and checks, then reruns validation.
Create Hookify rules that warn Claude or block operations when commands or file edits match specified conditions. The skill explains rule files, text matching patterns, multiple conditions, and how to test and refine the rules.
Make Claude Code plugin behavior configurable per project using local Markdown files. Learn to store structured settings and notes, read them from hooks or commands, and handle defaults, validation, and user-local configuration.
Connect external services to Claude Code plugins through MCP, a protocol that exposes service functions as tools. Get guidance on server configuration, connection methods, authentication, tool permissions, and testing connections and tool calls.
Build and organize Claude Code plugins with guidance on directory layout, configuration files, commands, agents, skills, and hooks. Learn how automatic component discovery works and how to reference bundled files across different installation locations.