Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkillsScience & Research › Page 53

Claude Science & Research Skills (Page 53 of 118)

Research automation, paper analysis, hypothesis testing, data science, biology, physics, and academic writing skills for Claude Code.

7,076 skills · updated 2026-07-12 · showing 3121–3180 of 7,076 by quality score

Sub-topics:Research Methods (1,844)Biology Medicine (1,070)Math Stats (901)Physics (297)Chemistry (109)Data Science Research (101)Earth Environment (57)Ml Research (27)

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

Writes a structured flag to vault/health/open-loops.md when a lab biomarker falls outside its clinical reference range.
Read, write, and query Apple Health data using HealthKit. Covers HKHealthStore authorization, sample queries, statistics queries, statistics collection queries for charts, saving…
Assist with Israeli legal research including legislation lookup, case law concepts, Hebrew legal terminology, and legal document preparation guidance.
Query the OFR (Office of Financial Research) Hedge Fund Monitor API for hedge fund data including SEC Form PF aggregated statistics, CFTC Traders in Financial Futures, FICC…
Build, evaluate, and document per-measure HEDIS extraction pipelines (NLP engineering, not chart review).
Heme/Onc consultant: Rapid clinical decision support for hematology and oncology with multi-level analysis.
Estimate SNP heritability and partition it across functional annotations, cell types, and loci from GWAS summary statistics or individual-level genotypes.
Generates structured legal briefings on cultural heritage protection developments. Synthesizes judicial decisions, legislation, treaty updates, and regulatory changes across…
Multi-phase context compression — prune old tool results, protect head/tail, LLM summarize with structured template, iterative updates, graceful fallback.
Production-grade agent conversation loop — iteration budget with grace call, stale-stream detection (90s), chunked retry on truncation, continuation prompt, jittered backoff (base…
Single-integration-point memory orchestrator — delegates to multiple providers, one external allowed, background async sync so slow providers never block a turn.
Use when you need to find, retrieve, or research anything across vaults, repos, or the web — executes semantic search with full provenance, deduplicates across sources, flags…
Scrub tags from LLM streaming output before displaying to UI — prevents internal memory blocks leaking into user-visible text. Stateful across chunk boundaries.
Build system prompts in three tiers — stable (identity+tools, prefix-cache-friendly), context (session CWD files), volatile (memory+date-only) — to maximize upstream prompt cache…
Detect and stop within-turn tool-call failure loops and no-progress idempotent loops. Three detectors — exact failure (same tool+args), same-tool failure, no-progress (idempotent…
Produce a weekly "What's new in Hermes" digest by summarizing merged PRs + active issues from NousResearch/hermes-agent
Homer L6 — Sleep-time learning distillation agent. Mines every `_learnings.md` file across skills + `~/.claude/shared/_shared_learnings.md` + `Toke/research/` + Mnemos archival.
Hessische Besonderheit: Obergermanisch-Raetischer Limes (Welterbe seit 2005, gemeinsam mit Bayern und Rheinland-Pfalz und Baden-Wuerttemberg), Bergpark Wilhelmshoehe in Kassel…
Use when when building a Graph Transformer model for continuous property prediction on molecules with associated experimental or instrumental metadata (e.g., retention time…
Research Hex packages (Sobelow, Phoenix, Ecto, Credo, Ash, etc). Use when investigating packages, understanding integration patterns, or finding module/function docs and usage…
Structured ideation primitive for hex. Ingests evolution/observations.md, todo.md backlog, project contexts, and raw/captures/ — then thematically clusters them into candidate…
Reference for hexagonal grid algorithms and coordinate systems. Use when implementing movement, pathfinding, range calculations, or line of sight.
Browse trending papers, search by keyword, and get paper details from Hugging Face Papers. Use when the user wants to find ML research, asks about recent AI papers, trending…
Detect horizontal gene transfer (HGT / LGT) using compositional methods (GC%, codon usage, tetranucleotide z-scores via SIGI-HMM, AlienHunter, IslandViewer 4, IslandPath- — from…
Use when you have a cooler file (.cool or .mcool) from a Hi-C experiment and need to generate a genome-wide track of per-bin sequencing depth to assess coverage uniformity,…
Use when you have a cooler-format Hi-C contact matrix and need to establish a genome-wide baseline contact frequency by genomic distance.
Use when you have raw Hi-C FASTQ files from a sequencing experiment and need to generate kilobase-resolution Hi-C contact maps conforming to ENCODE reference standards.
Discovers off-the-beaten-path experiences at travel destinations using a structured research and verification method.
Use when you have a methylBase object containing aligned methylation calls across multiple samples and need to verify whether samples cluster by expected experimental condition…
Hierarchical memory architecture combining short-term, long-term, and episodic memory layers. Based on Mem0 research showing 26% accuracy improvement.
Use when immediately after parsing and validating raw LC-MS/MS data files (mzML, mzXML, or vendor formats) when you need to prepare spectral data for fragmentation tree…
Use this when the user wants to solve a large, multi-faceted project by breaking a distal goal into a sequence of abstract middle-states, sub-goals, or typed nodes like research…
Run the heavier pre-apply verification harness for a SENSITIVE change, one that is gate-blind on correctness (a fit or semantic property no existence gate can check), delicate at…
High-performance data processing patterns from 5 repos. O(n log n) array algorithms, lazy evaluation chains, statistical computation on raw data, streaming JSON parsing for large…
Use when you have implemented or are evaluating an algorithmic or system optimization (e.g., MASST+) that claims to reduce execution time, and you need to quantify and…
Use when you have high-resolution MS2 data in .ms2 format from lipid A samples and need to perform automated structure annotation to identify lipid A molecular variants and their…
Quickly judges whether a biomedical paper is worth deep reading by screening for question fit, design quality, sample adequacy, methodological novelty, and reproducibility value.
Extract slide visual grammar from high-end web and design references for HTML-first academic or technical decks, focusing layout, whitespace, evidence imagery, color rhythm,…
Comprehensive, research-backed Hinge dating profile optimization. Use when someone wants to improve their Hinge profile, audit an existing profile, write better prompts/captions,…
Detect hints about unreleased AI research or capabilities from lab researcher communications. Use when analyzing tweets, posts, or interviews from people at major AI labs to…
Implements HIPAA Privacy Rule requirements for research uses of protected health information under 45 CFR §164.512(i).
Use when the user asks Codex for HippocampusMD vault statistics, graph metrics, growth, link density, inbox state, queue state, or a shareable snapshot.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images.
WSI processing for digital pathology. Tissue detection, tile extraction (random, grid, score-based), filter pipelines for H&E/IHC. For dataset prep, tile-based DL, slide QC.
Statistical methods for calling hits in CRISPR screens. Covers MAGeCK, BAGEL2, drugZ, and custom approaches for identifying essential and resistance genes.
Use when when you need to establish a reproducible inventory of compounds for LC-MS/MS simulation studies, particularly to determine how many unique molecular formulas fall within…
Use when when you need to create in silico LC-MS/MS experiments with diverse chemical backgrounds for testing fragmentation strategies or acquisition controllers, and you want the…
Supreme diagnose-research-implement-verify engine. Combines devTeam (calibrated diagnosis with regression guard) and profTeam (adaptive agents with ROI tracking) in a convergent…
Use when changing, debugging, or reviewing homelab Ceph, Ceph CSI, RGW, RBD StorageClasses, PVCs, S3 buckets, object storage credentials, or storage-related backup paths.
Automated service deployment with validation, templating, and verification - use when deploying new services, updating existing deployments, or troubleshooting deployment issues
Use when working with Proxmox homelab infrastructure - Terraform provisioning, Ansible configuration, or Nix devshells. Covers LXC containers, services, secrets, and IaC workflows.
Readiness checklist for homelab VLAN segmentation, local DNS filtering, and WireGuard-style remote access before changing router, firewall, DHCP, or VPN configuration.
Home network architecture from scratch — gateway placement, switch and AP selection, IP addressing scheme design, DHCP scoping, and common setup mistakes for homelab beginners.
Pi-hole installation, blocklist management, DNS-over-HTTPS setup, DHCP integration, local DNS records, and troubleshooting broken DNS resolution on a home network.
Use when planning, documenting, or debugging Proxmox, PBS, Ceph, VM/LXC, node, storage, or backup operations in this homelab.
Segmenting home networks into VLANs for IoT, guest, trusted, and server traffic using UniFi, pfSense/OPNsense, and MikroTik — including switch trunk config, firewall rules, and…
WireGuard VPN server setup, peer configuration, key generation, split tunneling vs full tunnel routing, and remote access to a home network from mobile and laptop clients.
De novo and known TF motif enrichment in ChIP-seq/ATAC-seq peaks via HOMER. findMotifsGenome.pl finds over-represented patterns vs background; annotatePeaks.pl assigns context…
Review homework notebooks for completeness, reproducibility, safe execution, and academic-integrity boundaries.
Generate 5-10 hook variations for any post, thread, or caption across X, LinkedIn, Instagram, and TikTok — using different styles (question, contrarian, statistic, story,…
Search all 7,076 Science & Research skills →