Model safety teams need reproducible evidence about when prefills make exploit behavior more likely. This skill guides Claude, Codex, and Claude Code through trajectory and logprob analysis.

Sales teams often lose time researching accounts that do not match their market. This skill builds focused lead lists with fit scores and outreach guidance.

Competitive ad research can be slow and inconsistent. This skill extracts ad examples and turns messaging, creative patterns, and campaign themes into clear insights.

Manual web checks are slow when an AI assistant needs page context. This skill gives Claude, Codex, and Claude Code local Chrome controls for navigation, screenshots, evaluation, and element selection.

Fresh web information can be hard to collect and format for LLM work. This skill runs Tavily searches and returns concise results for research and RAG workflows.

AI agents often need current web results with clear search intent. This skill lets Claude, Codex, and Claude Code query Exa.ai through a simple Node.js wrapper.

Developers lose time searching scattered GitHub issues, pull requests, discussions, and code examples. This skill guides focused repository searches for bugs, dependencies, and implementation patterns.

Video transcripts are hard to collect and clean by hand. This skill guides Claude, Codex, and Claude Code through subtitle extraction, cleanup, and summary preparation.

Researchers need fast access to preprints that may not appear in journal indexes yet. This skill searches arXiv and returns concise paper titles, summaries, and links.

Complex projects fail when teams plan from assumptions and miss known risks. This skill guides evidence collection, task planning, and pre-mortem review before implementation.

Web pages can be difficult for agents to read and extract consistently. This skill retrieves a URL and returns focused content in several formats.

Current technical answers often require live web sources and focused code references. This skill runs Exa searches from the CLI and returns web or programming context for review.

Protein searches and identifier mapping often require careful UniProt REST syntax. This skill provides focused guidance and a Python client for reliable retrieval.

Drug discovery teams need reliable choices among molecular datasets, graph models, and evaluation methods. This skill provides focused TorchDrug guidance for complete research workflows.

Protein interaction analysis requires specialized databases and careful identifier handling. This skill queries STRING to map proteins, retrieve networks, and assess enrichment.

Search teams need clear guidance for content, metadata, schema, and page performance. This skill provides practical SEO checklists, examples, and optimization patterns for Claude, Codex, and Claude Code.

Scientific manuscripts require precise structure, evidence, and reporting standards. This skill guides drafting, revision, citations, visuals, and journal preparation through a structured workflow.

Scientific talks often overload audiences with dense text and poor pacing. This skill structures, designs, and validates clear PowerPoint, PDF, or Beamer presentations.

Scientific claims can overstate what methods and data support. This skill applies structured checks for validity, bias, statistics, reasoning, and evidence quality.

Academic reviews can be inconsistent and difficult to compare across drafts. This skill applies structured ScholarEval criteria to produce clear scores, evidence-based feedback, and revision priorities.