AI & ML

mims-harvard Skill

Cross-species genetic analysis using model organism databases (MGI mouse, ZFIN zebrafish, FlyBase fruit fly, WormBase worm, SGD yeast, RGD rat, GBIF taxonomy). Maps human genes to orthologs, retrieves phenotype/expression/functional data, assesses gene function conservation, and identifies the best animal model for studying a human gene or disease.

mims-harvard Bundle

Spatial transcriptomics analysis — Visium, MERFISH, seqFISH, Slide-seq. Maps gene expression to tissue architecture, identifies spatially variable genes (SVGs), tissue-domain segmentation, and cell-cell interaction inference. Use for spatial gene-expression questions, tissue architecture analysis, and SVG identification.

mims-harvard Bundle

Cross-species gene comparison and ortholog analysis. Integrates Ensembl Compara orthologs, NCBI Gene, UniProt, OLS, Monarch, and OpenTargets to identify orthologs, paralogs, sequence conservation, functional conservation across species, and lineage-specific gene gains/losses. Use for phylogenetic gene tracing, model-organism mapping, and evolutionary-genomics queries.

mims-harvard Skill

Gene regulatory network analysis — TF-target inference (JASPAR motifs, ChIP-seq), motif scanning, eQTL integration, perturbation evidence (knockout/overexpression). Use for 'which TF regulates gene X', 'which genes does TF Y target', regulatory pathway reconstruction. Distinguishes direct (binding) vs indirect (co-expression) regulatory evidence.

mims-harvard Bundle

Retrieve gene expression and omics datasets from ArrayExpress and BioStudies with gene disambiguation and quality assessment. Use for finding RNA-seq/microarray datasets by organism/tissue/condition, comparing across studies (case-control, time-series, dose-response), and assessing dataset suitability before downloading. Always uses English search terms.

mims-harvard Skill

Find and retrieve proteomics datasets from MassIVE and ProteomeXchange. Search by species, keyword, or accession; retrieve detailed metadata (instruments, publications, species, PTMs studied). Use for locating public proteomics datasets to reanalyze, comparing instrument/protocol coverage across studies, and pre-download dataset evaluation.

duc01226 Bundle

[Testing] Use when you need to drive an integration-test suite to fully green — each round runs /integration-test-verify (whole system by default, or the target named in the prompt), and on ANY failure combines /debug-investigate + /integration-test-review (report-only) to adjudicate the fault (test wrong · test not optimal · source wrong), then /fix to resolve it at the owning layer, then /changes-review on that round's fix diff, then re-runs a FRESH full verify — looping until the whole suite passes its 2-consecutive-green-runs gate with zero failures.

mims-harvard Skill

End-to-end variant-to-mechanism analysis — trace a variant (rsID/coordinates) through regulatory context, target gene(s), molecular pathway(s), and phenotypic consequences. Integrates 7+ databases across 3 evidence layers (regulatory, molecular, disease) for a mechanistic model. Use for GWAS-hit-to-mechanism, eQTL-causal-gene tracing, and full causal-chain reports.

mims-harvard Skill

Propose the mechanism by which a missense variant causes loss-of-function (LoF), synthesizing evidence from 5 independent layers: AlphaMissense pathogenicity, AlphaFold structural context, ESMC sequence likelihood, SAE feature disruption, and DynaMut2 stability ΔΔG. Distinguishes 'structural stability LoF' (mis-folding) from 'direct functional disruption' (catalytic / binding / PTM site damage). Use for coding missense variants where you need a mechanistic causal model, not just a pathogenicity score.

mims-harvard Bundle

Build AI scientist systems with the ToolUniverse Python SDK for scientific research. Covers the 3 calling patterns (`tu.run` portable dict API, `tu.tools.X` function API, direct class instantiation), tool loading, batch execution, MCP server integration, and embedding-based tool search. Use for SDK programming, custom tool composition, benchmarking pipelines, and integrating ToolUniverse into research workflows.

mims-harvard Bundle

Install and configure ToolUniverse for any use case — MCP server (chat-based), CLI (command line with 14 subcommands), or Python SDK (Coding API with 3 calling patterns). Covers uv/uvx setup, MCP configuration for 12+ AI clients (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, etc.), full CLI reference (tu list/grep/info/find/run/test/status/build/remote/doctor/serve/connect/connections/disconnect), Coding API quickstart, agentic tools, code executor, API key walkthrough, skill installation, and upgrading. Use when user asks how to set up ToolUniverse, which access mode to use (MCP vs CLI vs SDK), configuring MCP servers, using the CLI, troubleshooting installation, upgrading, or mentions installing ToolUniverse or setting up scientific tools. Also triggers for "how do I use ToolUniverse", "what's the best way to access tools", "command line", "tu command", "coding API", "tu build".

rjmurillo Bundle

Detect infrastructure and security-critical file changes to trigger security agent review recommendations ensuring proper security oversight for sensitive modifications. Use when you ask "did I touch security-critical files", "should the security agent review this". Detection only. Do NOT use to scan source for injection patterns (use security-scan).

rjmurillo Bundle

Autonomous meta-skill for creating high-quality custom slash commands using 5-phase workflow with multi-agent validation and quality gates. Use when user requests new slash command, reusable prompt automation, or wants to convert repetitive workflows into documented commands.

asiaostrich Bundle

防止 AI 幻覺，確保分析程式碼或提出建議時給出以證據為基礎的回應。 Use when: 分析程式碼、提出建議、提供選項，或使用者詢問把握度／確定性時。 Not for: 撰寫 AI 指令檔本身——請用 /ai-instruction-standards；審查具體的 diff——請用 /code-review。 Keywords: certainty, assumption, inference, evidence, source, 證據, 假設, 推論, 確定性, 反幻覺.

gitwalter Bundle

Web scraping with agents, browser automation, content extraction, and ethical scraping practices

gitwalter Bundle

Guide users through selecting appropriate MCP servers during project generation

gitwalter Bundle

Send emails using the cached Google Workspace credentials.

gitwalter Bundle

Model Context Protocol overview, server creation, tool exposure, and common integrations

gitwalter Skill

Unified management of episodic, semantic, procedural, and relational memory within the factory workspace.

gitwalter Skill

Automated release management using semantic versioning and automated changelog maintenance.

gitwalter Bundle

JPA entity design (relationships, inheritance, embedded), Spring Data JPA repositories (derived queries, @Query, Specifications), Transaction management, N+1 query prevention (EntityGraph, JOIN FETCH), Auditing, Flyway/Liquibase migrations

gitwalter Skill

DSPy integration for declarative prompt optimization, prompt versioning, A/B testing, few-shot optimization, chain-of-thought patterns, prompt caching

gitwalter Bundle

Image analysis with multi-modal LLMs (GPT-4V, Gemini Vision), object detection integration, image generation pipelines, and visual question answering

gitwalter Bundle

Debugging and tracing LangChain/LangGraph with LangSmith MCP

gitwalter Bundle

Token streaming from LLMs, event streaming with astream_events, WebSocket agent patterns, and real-time UI updates

gitwalter Bundle

Entity Framework Core patterns for data access, migrations, and query optimization

gitwalter Bundle

Graph RAG patterns, entity extraction with LLMs, relationship mapping, and Neo4j integration

gitwalter Bundle

Dataset preparation for ML, HuggingFace datasets, custom loaders, data validation with Great Expectations, feature engineering, data versioning with DVC, preprocessing pipelines

thebeardedbearsas Skill

Orchestrate dozens-to-hundreds of subagents from a script Claude writes (Claude Code Dynamic Workflows, trigger `ultracode`). Use when a task exceeds a single agent's context or needs more than ~4 concurrent workers — large audits, migrations, multi-source research, fan-out reviews. Distinct from Agent Teams (synchronous, ≤4 workers) and ralph-run (sequential single-context loop).

gitwalter Bundle

Prompt management with LangSmith Hub - versioning, testing, and evaluation

gitwalter Bundle

Factual claim verification - the canonical profile of grounding-verification

gitwalter Bundle

Build multi-agent workflows using CrewAI patterns

fierzone Bundle

Standards for creating new High-Density Agent Skills with optimal token economy.

thebeardedbearsas Skill

Onboard a Paperclip instance — install, bootstrap CEO operator, create a company via dashboard, hire the first agent, install a plugin. Use when bootstrapping or wiring Claude Code into Paperclip.

stevenke1981 Skill

當使用者需要「遊戲設計師」處理遊戲開發相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準，再把玩法、內容、技術限制與玩家體驗轉成可測試的遊戲開發規格，並輸出證據、風險、下一步與需要人工覆核的事項。

asiaostrich Bundle

[UDS] 系統考古——從邏輯、資料、執行環境三個維度對既有系統做反向工程。 Use when: 為沒有文件的系統補上文件、從既有程式碼回推規格、繪製未知的資料模型或執行環境拓樸。 Not for: 動工前評估健康度與風險——請用 /discover；從已核准的規格正向推導測試——請用 /spec-derive。 Keywords: reverse engineering, system archeology, legacy code, spec extraction, data model, runtime, 反向工程, 系統考古, 規格提取, 資料模型.