LLM Mart Basic
@llm-mart · Joined Jun 2026
Query the CZ CELLxGENE Census (200M+ cells) programmatically via cellxgene-census and TileDB-SOMA, slicing expression by tissue, disease, or cell type and returning AnnData. Use when pulling reference single-cell RNA-seq data from the largest curated public atlas, running populat
Predict biomolecular complexes with Chai-1, an open AlphaFold3-style model that folds multi-entity assemblies (proteins, ligands, nucleic acids) from a single typed FASTA — strong on antibody–antigen and protein–ligand complexes, with optional MSA and restraint inputs. Use when p
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phen
Process and visualize deep-sequencing coverage with the deepTools CLI — convert BAM to bigWig (bamCoverage), build log2 ratio tracks (bamCompare), run QC (multiBamSummary correlation, PCA, plotFingerprint), apply the ATAC-seq Tn5 shift (alignmentSieve --ATACshift), and make TSS/p
Run ESM protein language models — ESMC for embeddings and representations, ESMFold2 for structure prediction, and ESM3 for generative multimodal protein design across sequence, structure, and function — locally or through the hosted Biohub Platform API (formerly Forge). Use when
Manipulate, annotate, and render phylogenetic trees programmatically with the ETE Toolkit (ete3) — parse and edit Newick/NHX, detect duplication/speciation events, infer orthology and paralogy, query NCBI taxonomy, and export PDF/SVG figures. Use when traversing or reformatting t
Parse and write FCS (Flow Cytometry Standard) files v2.0-3.1 with FlowIO — extract event data as NumPy arrays, read $-keyword metadata and channel/parameter definitions, and convert events to CSV or pandas DataFrame. Use when loading raw .fcs flow-cytometry files, inspecting chan
Run fast one-liner queries to 20+ bioinformatics databases from the gget CLI or Python — gene info (Ensembl), BLAST, AlphaFold structures, Enrichr enrichment, and more. Use for quick interactive lookups of genes, sequences, structures, or pathways — for batch processing or advanc
Analyze and engineer protein glycosylation — scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and reach curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). Use when identifying or designing glycosylation sites, optimizing
Extract and preprocess tiles from whole-slide images (WSI) with histolab — OpenSlide-backed slide loading, tissue detection and masks, Random/Grid/Score tile extraction, and image/morphological filters for H&E preprocessing. Use when the user needs lightweight WSI slide preproces
Manage, annotate, and trace biological data with LaminDB, an open-source FAIR data framework that makes datasets queryable, versioned, and reproducible. Use when registering or querying biological datasets (scRNA-seq, spatial, flow cytometry), validating and curating data against
Design protein sequences around bound ligands, metals, and nucleic acids with LigandMPNN (Dauparas 2023) — inverse folding that conditions on non-protein context, so binding-pocket and metal-site residues are chosen to fit the actual ligand. Use when designing a small-molecule or
Analyze Neuropixels 1.0/2.0 extracellular electrophysiology with SpikeInterface — load SpikeGLX/Open Ephys recordings, preprocess and motion-correct, run Kilosort4 spike sorting, compute quality metrics, apply Allen/IBL curation, and do AI-assisted visual inspection. Use when wor
Runs FASTQ-to-VCF germline and somatic variant calling via the Nextflow nf-core/sarek pipeline pinned to -r 3.10.0 — builds the samplesheet.csv (patient, sex, status, sample, lane, fastq_1, fastq_2), runs bwa-mem/bwa-mem2/dragmap alignment plus GATK4 MarkDuplicates and BQSR again
Run full computational-pathology workflows with PathML — whole-slide-image (WSI) analysis across 160+ slide formats, multiplexed immunofluorescence (CODEX, Vectra, MERFISH), nucleus segmentation/classification (HoVer-Net, HACTNet), tissue- and cell-graph construction, HDF5 datase
Build phylogenetic trees end-to-end from raw sequences — MAFFT multiple sequence alignment, optional TrimAl trimming, IQ-TREE 3 maximum-likelihood inference with model selection and bootstraps, FastTree for large datasets, then visualize with ETE3 or FigTree. Use when reconstruct
Design protein sequences for a fixed backbone with ProteinMPNN (Dauparas 2022) — message-passing inverse folding that outputs sequences predicted to fold to a given structure, with fixed positions, tied/symmetric chains, amino-acid bias, and a soluble-model variant. Use when inve
Run differential gene expression analysis on bulk RNA-seq count matrices with PyDESeq2, the Python port of DESeq2 — size-factor normalization, dispersion estimation, Wald tests, FDR (Benjamini-Hochberg) correction, and volcano/MA plots. Use when identifying differentially express
Build complete mass-spectrometry workflows with pyOpenMS — feature detection, peptide identification, protein quantification, and full LC-MS/MS pipelines across many MS file formats (mzML, mzXML) and algorithms. Use for comprehensive proteomics and MS data processing — for simple
Read and write genomic alignment and variant files in Python with pysam (htslib bindings) — SAM/BAM/CRAM alignments, VCF/BCF variants, and FASTA/FASTQ sequences, plus region extraction and per-base coverage/pileup. Use when scripting NGS data-processing pipelines that parse, filt
A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.
A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.
None of the safety came from the model. It came from six boring habits.
Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.
Six hours in, one step left, everything green, and the incident that didn't happen
CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.
Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it
An API request routing a model's tool call through an approval gate to a remote MCP server
31 config keys, two audits, and why the first one was wrong in both directions
The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.
Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.
Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.
"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks
stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.
The most important rule wasn't about what I could change. It was about what I was allowed to display.
Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.
Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.
Build an MCP server in TypeScript with focused tools, validated schemas, local and remote transports, Inspector tests, and production security controls.
An MCP server exposes tools, resources, or prompts through a standard protocol so an AI application can discover and use external capabilities.
Treat an AI agent skill as both an instruction package and a software dependency: inspect what it says, what it runs, what it can access, and how it updates.
/lit-review
lit-review
Run a systematic, reproducible literature review on a topic and return an APA 7.0 annotated bibliography with a documented search strategy. Invokes the alterlab-deep-research pipeline in lit-review mode.
/review-paper
review-paper
Run a full multi-perspective peer review of a manuscript, simulating an Editor-in-Chief plus three peer reviewers and a Devil's Advocate, and produce a structured editorial decision and revision roadmap. Invokes the alterlab-paper-reviewer skill.
/research-pipeline
research-pipeline
Orchestrate the end-to-end academic research-to-publication workflow (research, write, integrity check, review, revise, re-review, finalize) with mandatory integrity gates and two-stage peer review. Invokes the alterlab-research-pipeline orchestrator.
/audit-infra
Audit infra
Infrastructure-first security audit — secrets, supply chain, CI/CD, LLM/skill security, OWASP, STRIDE. Complements /audit-solana (program-level)
/audit-solana
Audit solana
Security audit for Solana programs (Anchor/native)
/benchmark
Benchmark
Benchmark CU usage and compare against baseline for regression detection
/build-app
Build app
Build web client application (Next.js, React, Vite)
/build-program
Build program
Build Solana program (Anchor or native)
/build-unity
Build unity
Build Unity project (WebGL, Desktop, or PSG1)
/cleanup
Cleanup
Initialize forked template — setup CLAUDE.md and remove config repo scaffolding
/commit-claude-config
Commit claude config
Version the Solana AI Kit config in git (un-ignores .claude/, CLAUDE.md, .mcp.json, .gitmodules and commits them)
/debug-user-tx
Debug user tx
Reproduce and debug a user-reported failing transaction against forked cluster state, mapping the failure back to source code
/deploy
Deploy
Deploy Solana program (devnet first, then mainnet)
/diff-review
Diff review
AI-powered diff review for Solana-specific issues and code quality
/doctor
Doctor
Health check for the dev environment and solana-ai-kit config — read-only, with one exact fix-it command per failure
/dream
Dream
Memory consolidation — dedupe, contradiction-check, prune, and re-rank MEMORY.md + CLAUDE.md Project Learnings. Run after major refactors
/explain-code
Explain code
Explain complex Solana/blockchain code with visual diagrams and step-by-step breakdowns
/generate-idl-client
Generate idl client
Generate TypeScript client from Solana program IDL using Codama or Anchor
/migrate-web3
Migrate web3
Migrate from @solana/web3.js to @solana/kit
/plan-feature
Plan feature
Plan feature implementation with technical specifications for Solana projects
LLM-powered toolkit for skill analysis, AI interviews, resume scoring, and job structuring. Automates professional skill taxonomy and interview processes with a…
13 views 0 likes【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试资源平台。涵盖AIGC、LLM大模型、AI Agent、具身智能、传统深度学习、计算机视觉、自然语言处理、自动驾驶、机器学习、强化学习、大数据挖掘、世界模型、元宇宙、AGI等AI行业面试笔试干货经验与核心跨周期知识。
9 views 0 likesEasiest and laziest way for building multi-agent LLMs applications.
16 views 0 likesDrive Claude Code or OpenAI Codex from your phone — resume sessions, stream output, approve tool permissions remotely. End-to-end encrypted, zero-knowledge rela…
14 views 0 likesMCP server for autonomous agent economies: wallets, signed RTC micropayments, bounty discovery, BoTTube video publishing, and Beacon agent-to-agent messaging. G…
14 views 0 likesFree, open-source alternative to Microsoft Office with built-in AI agents — Word (.docx), Excel (.xlsx), PowerPoint (.pptx), PDF and Markdown editing for macOS,…
14 views 0 likesNSE BSE Indian Stock Market Data MCP server — search, screen & analyze all 8,200+ NSE/BSE stocks with 34 tools: live quotes, financials, technicals, 326-ratio s…
10 views 0 likes全流程 智能招投标 Agent:标书生成 · 招投标解读 · 标书检查 · 标书文档ai排版 · 商机发现 一键完成。 21 项合规检查 · 多模型切换 · RAG 知识库 · OCR 抽取。 从招标公告到可交付 docx 文档,全流程 AI 自动化。
14 views 0 likesBenzi is AI-native code intelligence infrastructure. Claude Code greps; Cursor embeds; Aider maps signatures; Benzi resolves — and answers in O(1). Every langua…
17 views 0 likesFrom ticket to reviewed pull request. Free and open-source, on your machine.
12 views 0 likesGet web data for AI agents and LLMs - fast, efficient, and reliable with Rust
13 views 0 likesOpen-source, license-free MCP server for RTL waveform debug: reads FST waveforms (VCD/FSDB auto-convert) plus a SystemVerilog netlist, with 34 tools covering dr…
19 views 0 likesOpen-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real des…
13 views 0 likesParallel, isolated dev environments for humans and AI coding agents. Real containers. Real databases. Zero collisions.
17 views 0 likesOpenCode goal plugin for Codex-style goal mode, /goal slash commands, persistent objectives, and AI coding agent focus.
8 views 0 likesBattle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, search, web scraping & more. No trial-and-error, no ex…
18 views 0 likesDeep Code 是专为 deepseek-v4 模型优化的终端 AI 编码助手,支持深度思考、推理强度控制以及 Agent Skills。
6 views 0 likesChina Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intel…
17 views 0 likes⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.
15 views 0 likesMCP-NixOS - Model Context Protocol Server for NixOS resources
12 views 0 likes