66 tagged mcpb, measured the same way as everything else here.
Browse within: science-research 60
silverstein/claude-scientific-skills-desktop
Skill Claude CodeCodex
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
silverstein/claude-scientific-skills-desktop
Skill Claude CodeCodex
Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.
silverstein/claude-scientific-skills-desktop
Skill Claude CodeCodex
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and…
Skill Claude CodeCodex
Follow-up questions ("what's the market cap?", "what do analysts say?") should use data from earlier tool responses before making new calls. If you already fetched a company profile or financials, surface that data directly.
Skill Claude CodeCodex
Follow-up questions ("this IP", "that one", "is it a VPN?") → reuse IP from prior result.
alesdrobysh/readability-claude
Skill Claude CodeCodex
Local readability checker for substantial English prose such as docs, PR descriptions, commit bodies, blog posts, and explanations. Measures Flesch Reading Ease (0-100, higher is easier), MTLD, and TTR. Use when the user asks to check, simplify, or rewrite prose. Aim for 60 unless the user specifies a different…
Skill Claude CodeCodex
All tools that accept meeting identifiers use meetingid (not docid, id, or documentid). The meetingid value comes from the id field in search results and meeting lists.
Skill Claude CodeCodex
The prompt is sent to an LLM along with the page's markdown. Specific prompts get better results.