Audits whether a verification (eval/metric/experiment/holdout) actually secures independent external ground truth, or whether the designer, the model, and the scorer are just…
Scaffold a new evidence bundle directory ready for reproducibility-grade evidence capture: SOURCE.md (operator + cluster + git SHA + UTC timestamp), summary.md (verdict skeleton),…
Expand all TaskMaster tasks with deep research before coding begins. Reads tasks.json, launches parallel research agents per task in waves using the research-expander agent.
Design of Experiments skill for systematic optimization of nanomaterial synthesis and processing
Find recently-published CS/AI/ML researchers as ScholarFeed cold-outreach prospects. Given a research area (arXiv category or topic), pulls recent papers from the arXiv API,…
Florida Quantum Meruit Litigation Agent — generates and manages a COMPLETE civil case for quantum meruit / unjust enrichment / construction non-payment / breach of implied…
Fourier Transform Infrared spectroscopy skill for molecular identification and surface functional group analysis
Expert skill for gas turbine engine thermodynamic cycle analysis and optimization
Run GitHub Copilot CLI as a read-only sub-agent from Claude Code. Use when: (1) User says 'gco', 'copilot', or 'ask copilot', (2) Delegating code review or research to Copilot,…
AI-powered design of targeted gene panels for clinical and research applications including cancer diagnostics, pharmacogenomics, and rare disease testing.
Green chemistry metrics calculation skill for atom economy, E-factor, and process mass intensity
GROMACS molecular dynamics skill specialized for biomolecular systems, protein simulations, and free energy calculations
Display project statistics — phases, plans, requirements, git metrics, and timeline — from Gustavosareto/gerenciador-de-quadras
AI-powered analysis of hemoglobin disorders including sickle cell disease, thalassemias, and variant hemoglobins using HPLC, electrophoresis, and molecular data.
日本語ブログ記事から AI 生成文の特徴 (AI らしさ / AI くささ) を検出し、該当箇所と修正案を3点セット (検出 + 引用 + 修正案) で提示する。 自動修正は行わない。著者が判断して適用する。 Zenn / Qiita / Hatena 向け技術記事の推敲・公開前レビューで使用する。 Based on Wikipedia "Signs of…
Automated hypothesis generation using abductive reasoning and knowledge graph traversal
Hypothesis management skill for tracking business hypotheses through testing and validation
iminuit statistical fitting skill for physics data analysis with proper error handling and profile likelihood
AI-powered analysis for predicting optimal immune checkpoint inhibitor combinations based on tumor microenvironment, biomarkers, and molecular profiling.
Use when comparing code or implementation against method descriptions in one or more source papers — covers decomposition of code into checkable claims (algorithm shape,…
End-to-end orchestrator that takes a NEW model from a bare HuggingFace id to a perf-lake-published, validated CROSS-ENGINE (vLLM + SGLang) champion on B200/GB300.
Fuse the four profilers -- nsys (timeline + kernel durations), ncu (roofline / occupancy / arithmetic intensity), zymtrace (CPU+GPU flamegraph), and DCGM (byte-grounded %SoL) --…
Produce quantized inference weights from a BF16/FP8 base checkpoint via a post-training-quantization (PTQ) pipeline -- instead of only ever pulling NVFP4 weights pre-quantized.
Daily intelligence briefing across two research domains: (1) Quantum Computation — trending X posts, hot papers from last 48h + 7d.
GLAW Strategic Intelligence Cell — Scientific & Technical Intelligence. Assesses technology for IP, export-control, CFIUS, and tech-diligence matters: AI capability assessment,…
Multi-source research orchestrated across a persistent agent team. Use for queries asking for research-style investigation of a topic — comparing, contrasting, surveying,…
Remove AI writing patterns based on Wikipedia's "Signs of AI writing" research. 24 pattern detection and rewriting rules for making AI-generated text sound natural.
Use when defining GitLab CI jobs, configuring scripts, setting up environments, or managing job dependencies. Covers job structure and execution options.
Kwant quantum transport skill for mesoscopic physics, scattering matrix calculations, and nanostructure modeling
Runs a sourced KYC / AML research screen on a company: registration, officers, beneficial owners, sanctions, PEPs and adverse media, with namesakes excluded and a risk rating,…
LAMMPS molecular dynamics skill for nanoscale system simulation with force field management
LAMMPS molecular dynamics simulation skill for atomistic simulations, force field setup, and large-scale parallel computations
LaTeX scientific documentation skill specialized for physics papers with equation rendering and journal formatting
Lazyweb is the design-evidence skill for AI coding agents. Use it when designing, critiquing, or changing product UI — it provides real app screenshots, competitor references,…
Research a UK legal question and produce a structured brief. Finds relevant legislation with section text, case law, OSCOLA citations, and a plain English summary.
Surface chemistry skill for managing ligand exchange reactions, bioconjugation protocols, and functional group quantification
Skill discovery engine. Scans your local cold pool (~/.agents/skill-repos), indexes all SKILL.md frontmatter into REGISTRY.json + catalog.db, and lets you query by type, niche,…
MadGraph matrix element calculation skill for BSM physics, cross-section computation, and event generation
Market intelligence aggregation skill for synthesizing market data from multiple sources
Integration with market research platforms and survey tools for primary and secondary research
Remove signs of AI-generated writing from academic medical papers. Use when editing or reviewing manuscripts to make them sound more natural and professionally written.
Model Context Protocol (MCP) server for bioinformatics web services like GEO, STRING, and UCSC Cell Browser.
An AI agent for therapeutic discovery that executes transparent, multi-step omics analyses including research planning, code execution, and literature reasoning.
Write comprehensive literature reviews for medical imaging AI research. Use when writing survey papers, systematic reviews, or literature analyses on topics like segmentation,…
Design and execute convergent, explanatory sequential, and exploratory sequential mixed methods research designs
CS 시리즈 CEO 오케스트레이터. 자연어 요청을 받아 공수 추정 후 MJ-test/MJ-plan/MJ-codebase-review/mj-design/mj-smart-run 중 최적 조합을 자율 선택·배분한다.
AI-powered molecular glue discovery for targeted protein degradation, enabling neo-substrate recruitment and undruggable target degradation through E3 ligase interface modulation.
Monte Carlo simulation skill for statistical physics, particle transport, and stochastic processes
Create visual moodboards from collected inspiration with iterative refinement. Use after trend research or website analysis to synthesize design direction before implementation.
GLAW litigation motion-drafting agent — the seat that turns a posture into a filed motion. Drafts and structures the full motion set: motion to dismiss (Rule 12(b)(6) / failure to…
Ultra-sensitive AI-powered molecular residual disease detection using MRD-EDGE deep learning for sub-0.001% VAF ctDNA detection and early relapse prediction.
NanoHUB tool interface skill for accessing educational and research nanoscience simulations
nbodykit large-scale structure analysis skill for N-body simulations and galaxy surveys
DEFAULT for all web search, research, and content extraction queries. Prefer over built-in WebSearch and WebFetch.
Load when the user asks to add, import, compile, or ingest a research paper/PDF into OpenViking, especially when they mention ov-add-paper, ARA, claims, evidence, figures, tables,…
Automated DataFrame analysis skill for statistical summaries, missing value detection, data type inference, and memory optimization recommendations.
Audit paper drafts for logical consistency, compliance, and academic integrity (Triangulation Matrix).
Generate academic paper sections (Abstract, Intro, Methods, Experiments, Conclusion, Appendix) in LaTeX format based on extracted style.
PennyLane integration skill for hybrid quantum-classical machine learning and variational algorithms
Capture any performance measurement (NCCL bandwidth, MFU, step-time, latency, throughput, kernel-time, anything operator-defined) into a versioned baseline registry under…