Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 80 149 files from 1 774 authors, of which 62 489 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Student database processing tools. Includes grade calculation, duplicate name detection, recommendation letter filtering, and TOEFL score filtering.
Critical patterns for cross-platform path handling in this VS Code extension. Windows vs POSIX path bugs are the #1 source of issues. Use this skill when reviewing or writing path-related code.
Environment manager-specific discovery patterns and known issues. Use when working on or reviewing environment discovery code for conda, poetry, pipenv, pyenv, or venv.
Debug a failing test using an iterative logging approach, then clean up and document the learning.
Generate a codebase health snapshot for technical debt tracking and planning. Analyzes git history, code complexity, debt markers, and dependencies to identify hotspots and refactoring priorities.
Run smoke tests to verify extension functionality in a real VS Code environment. Use this when checking if basic features work after changes.
Run integration tests to verify that extension components work together correctly. Use this after modifying component interactions or event handling.
Run the mandatory pre-commit checks before committing code. Includes lint, type checking, and unit tests. MUST be run before every commit.
Run E2E tests to verify complete user workflows like environment discovery, creation, and selection. Use this before releases or after major changes.
VS Code settings precedence rules and common pitfalls. Essential for any code that reads or writes settings. Covers getConfiguration scope, inspect() vs get(), and multi-workspace handling.
Judgment rules for user-facing text and docs: CLI and diagnostic output, error and help text, README and docs structure, code comments, titles, and generated reports, decks, or exports. Use when writing or changing any user-visible string, when adding or restructuring docs or deciding which page owns a fact, when a page is about to record a version, a deployment state, or a value the code already owns, when a comment, title, or artifact could carry the reasoning or an abandoned option behind the change, when a behavior change needs its copy sites swept, or when reviewing a diff that touches copy or docs.
按 scarletkc 本人的自然表达习惯撰写、改写、润色和翻译文本，覆盖推文、微博、评论、聊天消息、技术观点、项目介绍、GitHub 文本（README、issue、PR、发布说明）和正式通信。当用户要求用自己的口吻写东西、把 AI 腔文字改自然、发推、回评论、点评模型或开发工具、写项目公告、写礼貌但直接的客服或正式邮件，或要求翻译时保留语气和立场，都使用本 skill，即使用户没有点名 scarletkc 或提出风格要求。
Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls to action, press-style announcements, and the naming of a product for another language or market. Covers what may be disclosed publicly, keeping claims traceable to shipped changes, and writing a headline that carries information instead of hype. Use when drafting or revising anything aimed at people who do not use the product yet, and when deciding whether a link, key, price, or unreleased detail can appear in public copy.
When handing work to the Codex CLI earns its cost, and how to size the run: second-model review, bounded implementation hand-offs, sandbox permissions, model and reasoning effort. Use when the user asks for Codex or `codex exec`, when a change is complex or high-stakes enough that an independent reviewer would change the outcome, or when a delegated run needs its model, effort, or permissions chosen. For agents other than Codex itself.
Decide whether a task deserves its own git worktree and, if chosen, run it end to end: branch from the integration branch rather than the current tree, keep the main working copy untouched while the task runs, compare the result against the untouched baseline before declaring it done, and prepare it for a pull request instead of merging. Use when a request says to do the work in a new worktree or branch, when a change is large or risky enough that the main tree should stay usable, when several tasks need to run in parallel on one repository, when a result has to be diffed against current behavior, and when deciding where screenshots, builds, and other artifacts produced in a worktree should end up.
Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it. Use when scope is ambiguous, a diff touches neighboring surfaces, required dependent edits are unclear, or a proposed compatibility layer, migration, fallback, flag, abstraction, or parallel implementation may exceed the request.
Memory management system for Claude Code — Student Loop, Smart Context, Auto Learn, Session Handoff, Correction Cycle. Triggered by memory commands (/save, /reflect, /handoff, /check) or memory-related questions. Not for general programming tasks.
> Goal-oriented binder design campaign planning and health assessment. (2) Converting high-level goals into runnable pipelines, (3) Assessing campaign health and pass rates, (4) Diagnosing why designs are failing QC, (5) Estimating time, cost, and expected yields, (6) Selecting between design tools for a specific target. This skill orchestrates the other protein design tools. For individual tool parameters, use the specific tool skills.
> (1) Planning binding kinetics experiments, (2) Troubleshooting poor/no binding signal, (3) Interpreting kinetic data artifacts, (4) Choosing between SPR vs BLI platforms.
> Guidance for choosing the right protein binder design tool. (2) Planning a binder design campaign, (3) Understanding trade-offs between different approaches, (4) Selecting tools for specific target types. For specific tool parameters, use the individual tool skills (boltzgen, bindcraft, rfdiffusion, etc.).
> (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm. For QC thresholds, use protein-qc.
> (1) Need side-chain aware design from the start, (2) Designing around small molecules or ligands, (3) Want all-atom diffusion (not just backbone), (4) Require precise binding geometries, (5) Using YAML-based configuration. For backbone-only generation, use rfdiffusion. For sequence-only design, use proteinmpnn. For structure validation, use boltz.
> (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high experimental success rate. For backbone-only generation, use rfdiffusion. For QC thresholds, use protein-qc. For tool selection guidance, use binder-design.
> Structure prediction using Boltz-1/Boltz-2, an open biomolecular structure predictor. (2) Validating designed binders, (3) Need open-source alternative to AF2, (4) Predicting protein-ligand complexes, (5) Using local GPU resources. For QC thresholds, use protein-qc. For AlphaFold2 prediction, use alphafold. For Chai prediction, use chai.
> Binder design ranking using ipSAE (interprotein Score from Aligned Errors). (2) Filtering BindCraft or RFdiffusion outputs, (3) Comparing AF2/AF3/Boltz predictions, (4) Predicting binding success rates, (5) Need better ranking than ipTM or iPAE. For structure prediction, use chai or alphafold. For QC thresholds, use protein-qc.
> Structure prediction using Chai-1, a foundation model for molecular structure. (2) Validating designed binders, (3) Predicting protein-ligand complexes, (4) Using the Chai API for high-throughput prediction, (5) Need an alternative to AlphaFold2. For QC thresholds, use protein-qc. For AlphaFold2 prediction, use alphafold. For ESM-based analysis, use esm.
> End-to-end guidance for protein design pipelines. (2) Need step-by-step workflow guidance, (3) Understanding the full design pipeline, (4) Planning compute resources and timelines, (5) Integrating multiple design tools. For tool selection, use binder-design. For QC thresholds, use protein-qc.
> Ligand-aware protein sequence design using LigandMPNN. (2) Enzyme active site design, (3) Ligand binding pocket optimization, (4) Metal coordination site design, (5) Cofactor binding proteins. For standard protein design, use proteinmpnn. For solubility optimization, use solublempnn.
> Quality control metrics and filtering thresholds for protein design. (2) Setting filtering thresholds for pLDDT, ipTM, PAE, (3) Checking sequence liabilities (cysteines, deamidation, polybasic clusters), (4) Creating multi-stage filtering pipelines, (5) Computing PyRosetta interface metrics (dG, SC, dSASA), (6) Checking biophysical properties (instability, GRAVY, pI), (7) Ranking designs with composite scoring. This skill provides research-backed thresholds from binder design competitions and published benchmarks.
> (1) Finding similar structures in PDB/AFDB databases, (2) Structural homology search, (3) Database queries by 3D structure, (4) Finding remote homologs not detected by sequence, (5) Clustering structures by similarity. For sequence similarity, use uniprot BLAST. For structure prediction, use chai or boltz.
> ESM2 protein language model for embeddings and sequence scoring. (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships. For structure prediction, use chai or boltz. For QC thresholds, use protein-qc.
> (1) Designing sequences for RFdiffusion backbones, (2) Redesigning existing protein sequences, (3) Fixing specific residues while designing others, (4) Optimizing sequences for expression or stability, (5) Multi-state or negative design. For backbone generation, use rfdiffusion or bindcraft. For ligand-aware design, use ligandmpnn. For solubility optimization, use solublempnn.
ATAC-seq processing with assay QC, MACS3 peak calling, consensus peak matrices, differential accessibility, and motif or footprint follow-up.
> (1) User is new and hasn't run any tools yet, (3) Modal authentication errors occur, (4) User asks how to get started or set up the environment, (5) biomodals directory is missing or tools aren't working.
> Access UniProt for protein sequence and annotation retrieval. (2) Finding functional annotations, (3) Getting domain boundaries, (4) Finding homologs and variants, (5) Cross-referencing to PDB structures. For structure retrieval, use pdb. For sequence design, use proteinmpnn.
>- Discover and invoke 1,676 deduplicated biomedical AI agent skills from the Awesome Bio Agent Skills repository (20 source repos, 15 categories). Use this skill as a router whenever a user needs a bioinformatics/biomedical task (genomics, transcriptomics, single-cell, proteomics, protein design, clinical, epigenomics, multi-omics, pathway, metagenomics, database queries, fetch its SKILL.md, and follow it.
> Generate protein backbones using RFdiffusion, a diffusion-based generative (1) Designing binder scaffolds for a target protein, (2) Generating novel protein backbones from scratch, (3) Scaffolding functional motifs into new proteins, (4) Specifying hotspot residues for interface design, (5) Creating symmetric oligomers. For sequence design after backbone generation, use proteinmpnn. For structure validation, use alphafold or chai. For QC thresholds, use protein-qc.
> Solubility-optimized protein sequence design using SolubleMPNN. (2) Optimizing solubility of designed proteins, (3) Reducing aggregation propensity, (4) Need high-yield expression, (5) Avoiding inclusion body formation. For standard design, use proteinmpnn. For ligand-aware design, use ligandmpnn.
Run BLAST sequence similarity searches. Use when the user asks to BLAST a sequence, find similar sequences, identify a gene/protein, or do homology search. Triggers on "blast", "sequence similarity", "homology", "identify sequence".
Automated and marker-guided single-cell cell type annotation using CellTypist, marker review, reference transfer, and confidence-aware label curation.
Biology research tools reference. Always available inside agent containers.
Shotgun metagenomics workflow with host-depletion-aware QC, taxonomic profiling, functional profiling, AMR follow-up, and reproducible community output tables.
ChIP-seq peak calling and downstream interpretation with MACS3, signal track export, annotation, motif analysis, and differential binding review.
Bulk transcriptomics differential expression with count-aware modeling, design validation, contrast handling, thresholded exports, and publication-ready DE figures.
Mass spectrometry proteomics QC, quantification, comparative analysis, and export for DDA, DIA, and protein-level result tables.
Query ClinVar for clinical variant significance. Use when user asks about variant pathogenicity, genetic variants, clinical significance, or disease-causing mutations. Triggers on "clinvar", "pathogenic", "variant significance", "clinical significance", "disease variant", "mutation pathogenicity".
Query Ensembl for genomic data. Use when user asks about gene coordinates, genomic sequences, variants, gene structure, exons, transcripts, or species comparison. Triggers on "ensembl", "gene coordinates", "genomic location", "exon", "transcript", "variant location", "rsid", "rs number".
Query AlphaFold protein structure predictions. Use when user asks about protein structure, 3D structure, protein folding, or structure prediction. Triggers on "alphafold", "protein structure", "3D structure", "folding", "pLDDT", "structure prediction".
Query NCBI GEO for gene expression datasets. Use when user asks about RNA-seq datasets, microarray data, expression data, GEO accessions, or finding public datasets. Triggers on "geo", "gene expression omnibus", "expression dataset", "RNA-seq dataset", "microarray dataset", "GSE", "GDS".
Query KEGG for biological pathways and gene info. Use when user asks about metabolic pathways, signaling pathways, pathway genes, or KEGG IDs. Triggers on "kegg", "pathway", "metabolic pathway", "signaling pathway", "pathway genes".
Query InterPro for protein domains and families. Use when user asks about protein domains, functional sites, protein families, domain architecture, or motifs. Triggers on "interpro", "protein domain", "domain architecture", "protein family", "functional site", "motif".
Query OpenTargets for drug targets, disease associations, and therapeutic evidence. Use when user asks about drug targets, disease mechanisms, target validation, or drug-disease associations. Triggers on "opentarget", "drug target", "target validation", "disease association", "therapeutic target", "drug for disease".
Query RCSB PDB for experimental protein structures. Use when user asks about crystal structures, X-ray, cryo-EM, NMR structures, or PDB IDs. Triggers on "pdb", "crystal structure", "cryo-em", "x-ray structure", "protein crystal", "experimental structure".
Query STRING for protein-protein interactions. Use when user asks about protein interactions, interaction networks, binding partners, or interactome. Triggers on "string", "protein interaction", "interaction network", "binding partners", "interactome", "PPI".
Query Reactome for biological pathways and reactions. Use when user asks about signaling cascades, biological processes, pathway diagrams, or reaction details. Triggers on "reactome", "signaling cascade", "biological pathway", "pathway diagram", "reaction mechanism".
Query UniProt protein database. Use when user asks about protein sequences, functions, annotations, domains, or protein identifiers. Triggers on "uniprot", "protein function", "protein sequence", "gene product", "protein info".
Standard scRNA-seq preprocessing and clustering with Scanpy. Use for QC, normalization, HVG selection, PCA, neighbor graph construction, UMAP, Leiden clustering, and export of an analysis-ready AnnData object.
SEC (size-exclusion chromatography) analysis with peak detection, oligomer classification, and publication-quality PDF report generation via Typst templates. Triggers on "SEC", "size exclusion", "chromatography", "oligomer analysis", "protein assembly", "SEC report".
Review SDS-PAGE or protein purification gel images using DNA sequence, protein sequence, base-pair length, expected protein size, and lane labels. Use when the user wants to judge whether a gel ran well, whether the main band matches the expected product, or whether there may be impurities, degradation, aggregation, or low expression.
Analyze DNA/RNA/protein sequences. Use when the user provides a sequence and asks for analysis, translation, GC content, ORFs, motifs, restriction sites, or primer design. Triggers on "sequence", "translate", "GC content", "ORF", "primer", "restriction", "complement", "reverse complement".
Claude Skills — questions
Answers built from the skills we actually parsed.