skills_2026

Create academic and executive scientific briefing slide outlines or finished PPTX decks from summaries, proposals, progress reports, or user-provided templates. Use when the deliverable is a leadership-facing or expert-facing presentation in Chinese or bilingual form, especially for PI / academician / reviewer briefings, direct “输出PPT” requests, template-derived deck generation, JSON-first briefing workflows, or template-constrained PPTX rewriting.

为科研、课题、基金、申报或项目管理场景撰写和压缩中文项目概述、项目描述、项目说明、摘要与简介。适用于有严格字数上限、固定格式（markdown/单段/分段）、学术表述要求，或需要从零散项目信息中提炼核心内容的任务。

Umbrella skill for research-grounded worldbuilding and narrative analysis using anthropology, geography, history, narratology, and psychology. Use for fictional societies, settings, cultures, maps, historical consistency, character psychology, rituals, social systems, story structure, or realism checks grounded in academic methods.

Skilled in academic writing and paper revision

Operate and troubleshoot the local AI-Scientist-v2 / AI Scientist Cloud project at /home/qiao/dockerai/AI-Scientist-v2. Use when the user asks to run AI-Scientist-v2, generate or manage research ideas, launch BFTS paper-generation experiments, configure OpenAI/Semantic Scholar keys, use the Streamlit AI Scientist Cloud console, inspect experiment outputs/logs/PDFs/reviews, debug this project’s launcher/web app/configuration, or run paper queries/citation searches that should use the s2-api skill with S2_API_KEY from /home/qiao/dockerai/AI-Scientist-v2/.env.

Retrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment. Do not use if the user only has a protein name, gene name, or amino acid sequence — ask for a UniProt ID first.

Access AlphaFold's 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.

Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API. Use when the user asks about non-coding variant effects, pathogenicity, clinical significance, disease associations, functional effects, gene expression changes, splicing disruption, or regulatory effects in promoters and enhancers. Also use for resolving biological terms to tissue/cell-type ontologies (UBERON/CL) or analyzing variants in chr:pos:ref>alt format.

Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.

Class-level umbrella for reviewing, updating, and composing agent workflows and skill libraries from observed behavior, session learnings, and overlapping agent skills. Use when a task is about improving the agent itself, not just completing one user deliverable.

Configure, extend, or contribute to Hermes Agent.

Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.

Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.

Access BRENDA enzyme database via SOAP API. Retrieve kinetic parameters (Km, kcat), reaction equations, organism data, and substrate-specific enzyme information for biochemical research and metabolic pathway analysis.

Query ChEMBL's bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.

Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures. Use when the user asks about compounds, targets, IC50/Ki values, drug mechanisms, or structure searches.

Query ClinicalTrials.gov via APIv2. Use when you want to search for trials by condition, drug, location, status, or phase; retrieve trial details by NCT ID; check eligibility/inclusion criteria; count trials across conditions or time periods; identify a sponsor's trial portfolio; find recruiting trials for patient matching.

Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.

Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.

Query NCBI ClinVar for variant clinical significance. Search by gene/position, interpret pathogenicity classifications, access via E-utilities API or FTP, annotate VCFs, for genomic medicine.

Use when needing clinical significance, pathogenicity classifications (e.g., Pathogenic, Benign, VUS), clinical evidence rationales, or finding "hard positive" benchmark controls for human genomic variants.

Access COSMIC cancer mutation database. Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions, for cancer research and precision oncology. Requires authentication.

Create high-quality ToolUniverse skills following test-driven, implementation-agnostic methodology. Integrates tools from ToolUniverse's 1,264+ tool library, creates missing tools when needed, tests thoroughly, and produces skills with Python SDK + MCP support.

Use when working with the local /home/qiao/qiao_design/academic_visulization workspace for academic graphical abstracts, scientific image generation, professional portrait generation, paper-to-PPT conversion, or APIMart/OpenRouter video apps. Routes requests to the correct subproject and provides the right path, port, startup command pattern, and API-key expectations.

Build production-grade, LLM-ready access layers for massive structured corpora (patents, literature, clinical data, etc.). Converts raw multi-GB/GB-scale tabular or semi-structured data into a hybrid retrieval + analytical stack (Parquet columnar + SQLite FTS5 + optional vector) with first-class support for LLM context preparation, FastAPI backends, and minimal frontends.

Systematic compression and multi-layer indexing of massive patent CSV databases (50M+ rows) into Parquet + SQLite/FTS5 structures optimized for LLM retrieval and analytics.

Build LLM-ready retrieval and interaction layers on top of massive structured patent/scientific databases (50M+ records). Covers CSV→Parquet compression, SQLite+FTS5 sparse retrieval, FastAPI backend, minimal frontend, and context preparation for LLMs.

Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use this skill when working with demographic data, economic indicators, health statistics, environmental data, or any public datasets available through Data Commons. Applicable for querying population statistics, GDP figures, unemployment rates, disease prevalence, geographic entity resolution, and exploring relationships between statistical entities.

Use when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database. Resolves between rsIDs, genomic coordinates in VCF format, and HGVS strings. For an rsID, returns variant type, gene associations, clinical significance, allele frequencies, and genomic coordinates (GRCh38).

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

Umbrella skill for product design and creative direction including brand guardianship, UI design, UX architecture, UX research, visual storytelling, inclusive visuals, image prompt engineering, and whimsy/micro-delight. Use for interface design, design systems, brand consistency, UX reviews, creative direction, accessibility/inclusion, image prompts, or improving product experience quality.

Optimize ToolUniverse skills for better report quality, evidence handling, and user experience. Apply patterns like tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output. Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills.

Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git. References and dispatches to all other devtu skills. Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.

Document toolkit (.docx). Create/edit documents, tracked changes, comments, formatting preservation, text extraction, for professional document processing.

PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.

Presentation toolkit (.pptx). Create/edit slides, layouts, content, speaker notes, comments, for programmatic presentation creation and modification.

Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data, visualization, recalculate formulas, for spreadsheet processing and analysis.

Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways, chemical structures, and pharmacology data. This skill should be used when working with pharmaceutical data, drug discovery research, pharmacology studies, drug-drug interaction analysis, target identification, chemical similarity searches, ADMET predictions, or any task requiring detailed drug and drug target information from DrugBank.

Query and search the EMBL-EBI Ontology Lookup Service (OLS) for biomedical ontology terms, definitions, and hierarchies across 250+ ontologies (e.g., GO, DOID, HP). Use when the user asks to search for terms, retrieve details, navigate hierarchies (parents, children, ancestors), look up properties and individuals, get autocomplete suggestions, or access ontology metadata and statistics.