3.2K skills · sorted by relevance
Audit and improve a website’s search visibility by fixing technical issues, refining page titles and headings, adding structured data that describes content to search engines, and planning keywords and internal links.
Generate model responses in defined formats for data extraction and classification. Use JSON schemas, Pydantic data models, regular expressions, or fixed choices to produce structured results that other programs can parse and validate.
Extract information from text into defined fields, then check types and values with Pydantic, a Python data validation library. The skill covers structured LLM responses, automatic retries after validation failures, and streaming results as they are generated.
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.
Turn rough ideas into developed designs through structured questions and exploration of alternatives. Use it early in concept work to clarify an initial idea, consider different directions, and shape a more concrete design.
Plan market, competitor, consumer, or financial research with chapter outlines, data requirements, and chart plans. Then turn collected evidence into a structured Markdown report with comparisons, citations, and strategic implications, while clearly identifying missing data.
Add or review Product structured data, machine-readable product details, on shop pages. Check names, images, prices, availability, and ratings against visible content, then validate the markup for eligibility to show enhanced Google search results.
Audit structured data for businesses serving a physical location or geographic area. Check or add LocalBusiness JSON-LD, a machine-readable format for business details, verify addresses against visible page content, and validate the markup with Google's Rich Results Test.
Add FAQ sections to landing pages or blog posts and generate FAQPage structured data, a format search engines can read. Check required question and answer fields, valid syntax, and consistency with content visitors can see.
Audit breadcrumb structured data, a machine-readable description of a page’s navigation path. Check that BreadcrumbList matches the visible trail and site hierarchy, then guide JSON-LD changes using the rendered HTML and HTTP response.
Audit whether author profiles clearly present relevant experience, qualifications, and professional links. Review rendered pages, metadata, structured data, and HTTP responses to identify specific places where author expertise needs clearer presentation and explain how to verify improvements.
Check a Twenty pull request through real browser scenarios derived from its changes. Verify database effects and server logs alongside visible results, then produce screenshots, a structured verdict, and a report of any failures or uncertainty.
Delegate a clearly scoped coding task to Qoder in a specified project without opening its interactive interface. Read the structured JSON response and check its error flag before accepting the result.
Compare a UI screenshot with reference images and receive a structured JSON assessment. Get a score, pass or revision status, concrete visual differences, and suggested edits for layout, spacing, typography, colors, and visual hierarchy.
Use Outlines to make language models produce data in a defined format. The skill covers extracting information into JSON, restricting classification labels, and applying Pydantic models, which define fields and data types, with local model backends.
Build Python workflows that constrain language model output using text patterns and grammar rules. Generate structured JSON, restrict classifications to allowed labels, extract information, and combine reusable generation steps with loops and tool selection.
Set up LLM serving with structured responses, including JSON and outputs restricted to specified patterns. Covers reusing shared prompt calculations, tool calling, and multi-turn conversations through SGLang, with examples for server setup and application integration.
Extract figures and fields from emails, websites, and APIs into source-linked tracking tables. Configurable recipes guide collection, preserve original material, and check duplicates for records such as investor updates, expenses, and company metrics.
Create a structured hiring interview kit with questions tied to job skills, clear scoring criteria, interviewer assignments, and a discussion template. Use shared questions and evidence from candidates’ answers to support consistent evaluations.
Examine strategic decisions through a structured meeting of AI agents representing executive roles. Gather independent recommendations, challenge assumptions, summarize disagreements, and record approved decisions with action owners and deadlines after the founder reviews the proposal.
Turn game bug descriptions or suspected code problems into structured reports with reproduction steps, severity, and priority. Follow reported bugs through fix verification and closure, recording test results or manual checks before marking an issue closed.
Build custom calculation and parsing tools that an n8n AI Agent can call. This skill covers JavaScript or Python inputs, structured arguments, string results, tool descriptions, and fixes for invocation and output errors.
Design AI agents and chatbots in n8n, choosing suitable nodes and connecting models, tools, conversation memory, and structured JSON output. Includes guidance on document retrieval and human approval before tool execution.
Turn a meeting transcript into structured notes and one Linear ticket per action item. Assign owners from the discussion or the team’s ownership map, and flag unclear assignments in unassigned tickets for follow-up.