6.3K skills · sorted by relevance
Create and review Kubernetes configuration files with examples for health checks, access permissions, resource limits, and automatic scaling. Use the included kubectl commands to investigate container crashes, memory shortages, and deployment problems.
Build and maintain MCP servers that let AI assistants use tools, read data, and access reusable prompts. Covers Node/TypeScript implementation, input validation, transport choices for local or remote clients, and registration or connection troubleshooting.
Update JSON translation files using each string’s actual screen context and project terminology. Review missing translations and source-copy changes, preserve file structure and dynamic-value placeholders, and prepare focused edits with validation results for review.
Research a topic across multiple web sources, break it into focused questions, and read key pages in depth. Produce a report with source links, confidence levels, practical findings, and clear distinctions between facts and estimates.
Find Claude Academy learning resources that closely match questions about using Claude, its features, or team adoption. It supplements direct answers with a small selection of relevant courses, tutorials, worked examples, or product learning hubs.
Build MCP servers that let AI access actions and data using mcp-use. The guide covers project setup, reusable prompts, interactive React interfaces, authentication, error handling, and deployment, with reference files for each area.
Turn an English description or mermaid source into a diagram with source files, an Excalidraw editing file, and SVG and PNG images. Rendering works offline, and flowcharts and sequence diagrams support editing individual shapes and arrows.
Check project dependency versions and consult the relevant official documentation before writing framework-specific code. Produce implementations with source links, identify deprecated APIs, and flag unverified approaches or conflicts between documentation and existing project patterns.
Answer questions using Paperclip wiki pages and original sources, with citations for each claim. Identify missing information clearly and, with user approval, save useful comparisons or explanations as linked wiki pages for future reference.
Collect design tokens—reusable values for colors, typography, spacing, corners, and shadows—from source code, screenshots, or Figma exports. Organize them in a JSON file with source and usage references for later mapping to a design system.
Build an HTML dashboard for a public GitHub repository, showing stars, forks, contributors, issues, pull requests, and recent activity. Choose a standalone page or source files that support updates and record where the data came from.
Research current public information by checking original sources, recording relevant passages, dates, and URLs, and using browser interaction when needed. Cross-check important claims and clearly separate supported facts from inference.
Review external links in articles to identify unsupported factual claims and suggest authoritative sources. Check link attributes used for security and for identifying paid, affiliate, or untrusted links, then guide corrections to citations and markup.
Review web content for factual claims, figures, and quotations that need reliable sources. Identify missing citations, suggest relevant external links with clear link text, and check the rendered page and HTTP response.
Migrate existing Remotion video compositions to HyperFrames HTML and GSAP. Checks source code for unsupported patterns, maps animation and media features, compares rendered videos for visual similarity, and documents translation gaps.
Design multi-agent workflows for research, reviews, and migrations. Organize work across different evidence sources, add independent checks, and combine findings while preserving source references, unresolved questions, and limits on what was examined.
Research current web sources through multiple searches and primary documents. Cross-check key figures, explain conflicting evidence, and produce a single-file HTML report with linked sources, dates, and clear distinctions between findings and inference.
Migrate an existing Remotion video composition to HyperFrames HTML and GSAP animation. Check the source for unsupported patterns, translate compatible scenes, compare rendered videos for visual differences, and document anything that could not be preserved.
Regenerate downloadable PDFs for four Remotion legal documents after updating their MDX source pages. The workflow covers generation, checking content and page layout, and committing the updated sources together with the PDFs.
Research recent discussions about a topic across social platforms, communities, and the web. Collect posts and engagement from the last 30 days, summarize supported findings with source links, and diagnose unavailable or broken research sources.
Plan free resources that encourage email signups and attract relevant prospects. Choose a format and topic, outline the content, and organize access requirements, delivery, promotion, and measurement around the audience’s buying stage.
Work with NotebookLM through an installed command-line tool to list notebooks, add URL sources, ask questions, generate artifacts, and download results. It also provides commands for checking authentication, conversation history, and sharing status.
Find facts and data with web search, prioritizing primary or authoritative sources. Record exact figures, units, time periods, and source URLs in shared history so later calculation, coding, or writing can use traceable evidence.
Organize research sources in self-hosted Open Notebook, then search them, ask questions with citations, create notes, transform text, or generate podcasts with multiple speakers. Supports REST API automation and configuration of local or cloud AI providers.