Read historical Agentic SWMM experiment audit artifacts and summarize repeated assumptions, QA issues, failures, missing evidence, run-to-run differences, lessons learned, and…
Parameter and forcing uncertainty propagation and sensitivity analysis for EPA SWMM. Use when an agent needs to (1) propagate parameter uncertainty through SWMM (fuzzy alpha-cut…
科研模式触发：群论分析、不变量计算、Galois理论、Noether定理、轨道分类、商空间推理、对称性破缺分析。 English (Research mode): Trigger for group theory analysis, invariant computation, Galois theory, Noether's theorem, orbit…
Synchronize documents to Google NotebookLM for AI-powered research and content generation
Detect syntenic blocks and structural rearrangements between genomes using MCScanX (Wang 2012), JCVI/MCScan (Tang 2008 Python), GENESPACE (Lovell 2022) for orthology-anch — from…
Master research synthesis including qualitative analysis, affinity diagramming, theme identification, pattern recognition, and insight extraction.
Merge, deduplicate, rank, and format research findings from multiple channels into a coherent report. Use after research agents return their results.
Synthesize all prior research into a unified GTM narrative. Run after `analyzing-contradictions` to prepare for slide deck generation (Phase 5).
Probe system resources — CPU, RAM, disk, GPU/CUDA/MPS — and translate findings into experiment design recommendations. Run this at the start of any compute-intensive project.
Write system prompts, tool docs, and agent definitions. Combines research-backed prompt engineering (+15-30% measured improvements) with project XML conventions.
Domain patterns for ML/AI serving and training systems — model serving, feature stores, training pipelines, experiment tracking, A/B testing, GPU scheduling, and failure modes.
Systematic debugging techniques for unclear root causes. Use when a bug's origin is unknown, multiple hypotheses need testing, you need to narrow down a failing area, end-to-end…
Use when the user describes a note by vibe, concept, or paraphrase rather than literal terms — "find notes about the feeling of X", "that idea I had about Y and Z", "something…
Use when the user wants to explore, trace, map, or synthesize their thinking across multiple notes on a topic — "how have I thought about X?", "trace Y through my notes", "map…
TA（主题分析）研究全流程AFP工作流协调器。采用心跳信号、HUD仪表盘、 原子级单步输出、硬停止确认、多方案选择等AFP设计理念，共12个检查点。 关键决策节点（理论定位、叙事结构、标题/摘要/关键词）提供多方案+理由供选择。 每步暂停等待用户确认，所有写作工作由专项skill完成。 当用户明确提到主题分析（TA）相关的全流程时触发，例如：…
Use when the user asks to find, search, or look up a note in their Zettelkasten with specific named terms — "find my note about X", "search for Y in my notes", "list everything…
Create multiplayer spatial board games using TabletopKit on visionOS. Use when building tabletop game experiences with boards, pieces, cards, and dice, managing player seats and…
Use when wiring LLM APIs to bioinformatics analysis result tables in this repository, especially when users ask to interpret DEG, enrichment, ssGSEA, pathway-map, or…
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages.
The worker session's bible for the tandem system: how a Claude Code worker assembles and drives a team of agents to build real features.
Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with
Performs gap analysis on NVIDIA TAO Visual ChangeNet (VCN) Classify experiments by invoking the data-services
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train…
Use when the research design and identification strategy are the bottleneck for a The Accounting Review (TAR) manuscript — choosing the setting, shock, and design that cr — from…
Use when building or cleaning the exhibits for a The Accounting Review (TAR) manuscript — descriptive, correlation, and regression tables, event-study and discontinuity figures,…
Use when choosing or sharpening a research question for a The Accounting Review (TAR) manuscript — testing whether the question is contribution-driven, identifiable with…
Convergent need-alignment system. Before executing any non-trivial request, ask questions (1–3 per turn, each with a recommended answer) until the user's outcome, constraints, and…
Use when creating implementation-ready beads tasks that need testing strategy, optimal implementation approach, and documentation requirements baked in — composes /create-task…
Task-type-specific planning workflows for Finesse — defines phases for features, bug fixes, chores, testing, performance, and research work
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substant — from…
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substant — from…
Plan, research, and prepare for tattoos with artist discovery, design exploration, cultural research, and aftercare guidance.
AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries.
Web search, content extraction, crawling, and research capabilities using Tavily API. Use when you need to search the web for current information, extracting content from — from…
Web search, content extraction, crawling, and research capabilities using Tavily API — from majiayu000/claude-skill-registry
Use when targeting 《税务研究》(Taxation Research — 中国税务杂志社主办的税务学术月刊, 在线投约稿系统 tg.ctax.org.cn) or deciding whether a Chinese tax/public-finance manuscript fits this venue.
生物作业生成 Skill是面向班级作业的产品级 Hermes Skill，年级、册别、单元、知识点和难度通过参数传入。 Workflow: teacher_biology_homework_generation.run.
生物单元复习 Skill是面向单元复习的产品级 Hermes Skill，年级、册别、单元、知识点和难度通过参数传入。 Workflow: teacher_biology_unit_review.run.
Analyze roster fit and personality dynamics. Leadership assessment, role clarity, locker room culture, trade/signing impact.
Unified team skill for interactive component crafting. Vanilla JS + CSS interactive components with zero dependencies. Research -> interaction design -> build -> a11y test.
Unified team skill for UI design team. Research -> design tokens -> audit -> implementation. Uses team-worker agent architecture with roles/ for domain logic.
Исследование технологий RAG/ML/Python: embeddings, vector search, reranking, chunking, Qdrant, sentence-transformers, ColBERT, sparse vectors.
Research and recommend libraries, technologies, or software solutions for specific use cases or project requirements.
【强制】所有技术文档查询必须使用本技能，禁止在主对话中直接使用 mcp__context7-mcp 工具。触发关键词：查询/学习/了解某个库或框架的文档、API用法、配置参数、错误解释、版本差异、代码示例、最佳实践。本技能通过 context7-researcher agent 执行查询，避免大量文档内容污染主对话上下文，保持 token 效率。
Write clear technical analysis, system architecture documents, decision records, and research synthesis.
Use when a technical unknown needs a small throwaway experiment before committing to a plan
Research a technology, library, API, or approach to inform an architecture or implementation decision.
Translate technical analysis into business language. Use when explaining statistical concepts to non-analysts, simplifying technical findings, or bridging communication between…
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualizatio — from…
Expert guidance for ClearML, the open-source MLOps platform for experiment tracking, pipeline orchestration, data management, and model deployment.
Expert guidance for Comet ML, the platform for tracking machine learning experiments, managing models, and monitoring production ML systems.
Expert guidance for Malloy, the experimental data language from Google that replaces SQL for analytics with a composable, reusable, and more readable syntax.
Expert guidance for user research, helping product teams conduct interviews, create personas, design surveys, run usability tests, and synthesize findings into actionable…
Termination review — high-risk flag detection, severance + release, and final pay timing by jurisdiction.
A local text formatting organizer for biomedical/academic writing; use it when you need to clean whitespace/line endings while preserving Markdown structures or when normalizing…
textstat is a Python package that calculates readability statistics for text content, including Flesch Reading Ease, Gunning Fog Index, SMOG Index, Coleman-Liau Index, and…
Use when targeting The Astronomical Journal (AJ) or deciding whether an observational astronomy manuscript fits this AAS/IOP venue.
Use when targeting The EMBO Journal (EMBO J) or deciding whether a mechanistic molecular biology manuscript fits this venue.
Use when targeting The Lancet Neurology or deciding whether a clinical neurology manuscript fits this venue.
Use when targeting The Plant Cell or deciding whether a plant biology manuscript fits this venue. Encodes the journal's fit, framing, method-and-evidence bar, house style,…