#362 by GitHub stars
google-deepmind/science-skills
GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/alphafold_database_fetch_and_analyze/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/alphagenome_atlas_website_links/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/alphagenome_single_variant_analysis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/alphagenome_variant_impact_score/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/chembl_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/clinical_trials_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/clinvar_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/credentials/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/dbsnp_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/embl_ebi_ols/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/encode_ccres_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/ensembl_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/foldseek_structural_search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/gnomad_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/gtex_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/human_protein_atlas_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/interpro_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/jaspar_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/literature_search_arxiv/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/literature_search_biorxiv/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/literature_search_europepmc/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/literature_search_openalex/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/ncbi_sequence_fetch/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/openfda_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/opentargets_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/pdb_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/predictingthepast/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/protein_sequence_msa/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/protein_sequence_similarity_search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/pubchem_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/pubmed_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/pymol/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/quickgo_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/reactome_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/string_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/ucsc_conservation_and_tfbs/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/unibind_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/uniprot_database/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/uv/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4de6786171f1
No earlier version was observed for comparison.
skills/workflow_skill_creator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4de6786171f1 → 4de6786171f1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4de6786171f1
No earlier version was observed for comparison.
Heat
6.7- Star growth, last 7 daysAhead of 90% of tracked repositories
- Star growth, last 24 hoursAhead of 85% of tracked repositories
- Rank movement, last 7 daysAhead of 52% of tracked repositories
- Commits, last 30 daysAhead of 64% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- alphafold-database-fetch-and-analyze
skills/alphafold_database_fetch_and_analyze - alphagenome-atlas-website-links
skills/alphagenome_atlas_website_links - alphagenome-single-variant-analysis
skills/alphagenome_single_variant_analysis - alphagenome-variant-impact-score
skills/alphagenome_variant_impact_score - chembl-database
skills/chembl_database - clinical-trials-database
skills/clinical_trials_database - clinvar-database
skills/clinvar_database - credentials
skills/credentials - dbsnp-database
skills/dbsnp_database - embl-ebi-ols
skills/embl_ebi_ols - encode-ccres-database
skills/encode_ccres_database - ensembl-database
skills/ensembl_database - foldseek-structural-search
skills/foldseek_structural_search - gnomad-database
skills/gnomad_database - gtex-database
skills/gtex_database - human-protein-atlas-database
skills/human_protein_atlas_database - interpro-database
skills/interpro_database - jaspar-database
skills/jaspar_database - literature-search-arxiv
skills/literature_search_arxiv - literature-search-biorxiv
skills/literature_search_biorxiv - literature-search-europepmc
skills/literature_search_europepmc - literature-search-openalex
skills/literature_search_openalex - ncbi-sequence-fetch
skills/ncbi_sequence_fetch - openfda-database
skills/openfda_database - opentargets-database
skills/opentargets_database - pdb-database
skills/pdb_database - predictingthepast
skills/predictingthepast - protein-sequence-msa
skills/protein_sequence_msa - protein-sequence-similarity-search
skills/protein_sequence_similarity_search - pubchem-database
skills/pubchem_database - pubmed-database
skills/pubmed_database - pymol
skills/pymol - quickgo-database
skills/quickgo_database - reactome-database
skills/reactome_database - string-database
skills/string_database - ucsc-conservation-and-tfbs
skills/ucsc_conservation_and_tfbs - unibind-database
skills/unibind_database - uniprot-database
skills/uniprot_database - uv
skills/uv - workflow-skill-creator
skills/workflow_skill_creator
How it works
alphafold-database-fetch-and-analyze
When your agent uses it
Retrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment. Do not use if the user only has a protein name, gene name, or amino acid sequence — ask for a UniProt ID first.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
1,110 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Overview
- Core Rules
- Utility Scripts
- Interpreting the Output
Scripts executed separately
scripts/analyze_pae.pyscripts/analyze_plddt.pyscripts/fetch_structure.py
Files
SKILL.mdcore4,760 bytesSKILL.mdcore4,760 bytesSKILL.mdcore4,760 bytesSKILL.mdcore4,760 bytesreferences/citation.bibasset10,493 bytesscripts/analyze_pae.pyruns6,223 bytesscripts/analyze_plddt.pyruns3,940 bytesscripts/fetch_structure.pyruns5,018 bytes
Read SKILL.md
# AlphaFold Database: Fetch and Analyze
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If
.licenses/alphafold_database_fetch_and_analyze_LICENSE.txt does not already
exist in the workspace root directory then (1) prominently notify the user
to check the terms at https://alphafold.ebi.ac.uk/, then (2) create the file
recording the notification text and timestamp.
## Overview
View the complete source on GitHubalphagenome-atlas-website-links
When your agent uses it
Constructs deep-links and URLs for the AlphaGenome Atlas website. Supports generating single-variant exploration links (1-based VCF-style coordinates), genomic locus views (1-based closed chr:start-end), candidate summary tables, and AlphaGenome reference vs. alternate predictions. Use when visualizing, exploring, charting, or linking genetic variants and genomic loci on the AlphaGenome Atlas, or when asked to inspect, view, or link predictions for a genomic variant. Don't use for computing raw AlphaGenome variant predictions directly without Atlas URLs (use alphagenome-single-variant-analysis or alphagenome-variant-impact-score).
What it loads into context
Frontmatter
150 tokensAlways available to the agent
SKILL.md
3,415 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- 2. URL Query Parameters
- 3. Multi-Modality Filtering & The Assay Group Gotcha (`f`)
- 4. Layout Configuration, AVI Scores, & Pinned Tracks (`lItems`)
- 5. Track Predictions & Ref vs. Alt Comparisons (`/atlas/track-predictions`)
Scripts executed separately
scripts/alphagenome_atlas_links.py
Files
SKILL.mdcore12,565 bytesSKILL.mdcore12,565 bytesSKILL.mdcore12,565 bytesSKILL.mdcore12,565 bytespyproject.tomlasset215 bytesscripts/alphagenome_atlas_links.pyruns36,863 bytes
Read SKILL.md
# AlphaGenome Atlas Deep-Linking & URL Configuration
Construct and validate deep-links for the AlphaGenome Atlas web application
(`https://deepmind.google.com/science/alphagenome/atlas`).
Base URL: `https://deepmind.google.com/science/alphagenome/atlas`
> [!IMPORTANT] **Mandatory Atlas Deep-Linking with Variant Scores**: Whenever
> presenting, discussing, or scoring genetic variants, you **MUST always provide
> clickable deep-links to the
> [AlphaGenome Atlas](https://deepmind.google.com/science/alphagenome/atlas)**.
> Use `scripts/alphagenome_atlas_links.py` to automate link and table
> generation.
View the complete source on GitHubalphagenome-single-variant-analysis
When your agent uses it
Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API. Use when the user asks about non-coding variant effects, pathogenicity, clinical significance, disease associations, functional effects, gene expression changes, splicing disruption, or regulatory effects in promoters and enhancers. Also use for resolving biological terms to tissue/cell-type ontologies (UBERON/CL) or analyzing variants in chr:pos:ref>alt format.
What it loads into context
Frontmatter
138 tokensAlways available to the agent
SKILL.md
2,925 tokensWhen the skill is activated
Reference documents
15,623 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Environment Setup & Troubleshooting
- References
- Code Patterns
- Workflow Checklist
- Multi-Variant Workflow
Scripts executed separately
scripts/analyze_ism.pyscripts/generate_ontology_mapping.pyscripts/interpret_splicing.pyscripts/lookup_gene_info.pyscripts/resolve_ontology_terms.pyscripts/visualize_genome_tracks.pyscripts/visualize_variant_effects.py
Files
SKILL.mdcore11,977 bytesSKILL.mdcore11,977 bytesSKILL.mdcore11,977 bytesSKILL.mdcore11,977 bytesSKILL.mdcore11,977 bytesSKILL.mdcore11,977 bytesdocs/alphagenome-api.mddoc13,586 bytesdocs/examples/model_limitation_RNU4ATAC/README.mddoc1,773 bytesdocs/examples/model_limitation_RNU4ATAC/ism_skeletal_muscle_RNA_SEQ.pngasset12,364 bytesdocs/examples/model_limitation_RNU4ATAC/plot_skeletal_muscle_RNU4ATAC_detail.pngasset78,094 bytesdocs/examples/model_limitation_RNU4ATAC/plot_skeletal_muscle_RNU4ATAC_effects.pngasset74,636 bytesdocs/examples/model_limitation_RNU4ATAC/plot_skeletal_muscle_RNU4ATAC_wholegene.pngasset80,148 bytesdocs/examples/model_limitation_RNU4ATAC/report.mddoc3,788 bytesdocs/examples/negative_result_GATA4/README.mddoc1,098 bytesdocs/examples/negative_result_GATA4/ism_heart_DNASE.pngasset11,999 bytesdocs/examples/negative_result_GATA4/plot_heart_GATA4_detail.pngasset75,300 bytesdocs/examples/negative_result_GATA4/plot_heart_GATA4_effects.pngasset71,841 bytesdocs/examples/negative_result_GATA4/plot_heart_GATA4_wholegene.pngasset80,112 bytesdocs/examples/negative_result_GATA4/report.mddoc3,685 bytesdocs/examples/negative_result_TGFB3/README.mddoc1,192 bytesdocs/examples/negative_result_TGFB3/ism_heart_ATAC.pngasset6,670 bytesdocs/examples/negative_result_TGFB3/ism_heart_RNA_SEQ.pngasset10,589 bytesdocs/examples/negative_result_TGFB3/plot_heart_TGFB3_detail.pngasset52,720 bytesdocs/examples/negative_result_TGFB3/plot_heart_TGFB3_effects.pngasset65,556 bytesdocs/examples/negative_result_TGFB3/plot_heart_TGFB3_wholegene.pngasset44,945 bytesdocs/examples/negative_result_TGFB3/report.mddoc3,091 bytesdocs/examples/polyadenylation_HBA2/README.mddoc1,139 bytesdocs/examples/polyadenylation_HBA2/ism_K562_RNA_SEQ.pngasset11,019 bytesdocs/examples/polyadenylation_HBA2/plot_K562_HBA2_effects.pngasset162,282 bytesdocs/examples/polyadenylation_HBA2/plot_K562_HBA2_wholegene.pngasset163,085 bytesdocs/examples/polyadenylation_HBA2/report.mddoc3,222 bytesdocs/examples/regulatory/README.mddoc1,245 bytesdocs/examples/regulatory/apoa1_promoter/ism_heart_left_ventricle_RNA_SEQ.pngasset8,846 bytesdocs/examples/regulatory/apoa1_promoter/ism_liver_RNA_SEQ.pngasset8,810 bytesdocs/examples/regulatory/apoa1_promoter/plot_heart_left_ventricle_APOA1_effects.pngasset74,776 bytesdocs/examples/regulatory/apoa1_promoter/plot_liver_APOA1_effects.pngasset226,856 bytesdocs/examples/regulatory/apoa1_promoter/report.mddoc3,499 bytesdocs/examples/splicing/README.mddoc1,282 bytesdocs/examples/splicing/col6a2_exon_extension.pngasset103,832 bytesdocs/examples/splicing/col6a2_report.mddoc2,271 bytesdocs/examples/splicing/dlg1_exon_skipping.pngasset74,883 bytesdocs/examples/splicing/dlg1_report.mddoc1,977 bytesdocs/interpretation-guide.mddoc17,785 bytesdocs/report-templates.mddoc2,909 bytespyproject.tomlasset269 bytesreferences/citation.bibasset823 bytesscripts/analyze_ism.pyruns10,378 bytesscripts/generate_ontology_mapping.pyruns4,965 bytesscripts/interpret_splicing.pyruns9,726 bytesscripts/lookup_gene_info.pyruns9,999 bytesscripts/resolve_ontology_terms.pyruns5,601 bytesscripts/visualize_genome_tracks.pyruns12,743 bytesscripts/visualize_variant_effects.pyruns37,866 bytes
Read SKILL.md
# Variant Analysis using AlphaGenome
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If
.licenses/alphagenome_single_variant_analysis_LICENSE.txt does not already
exist in the workspace root directory then (1) prominently notify the user
to check the terms at https://deepmind.google.com/science/alphagenome/, then
(2) create the file recording the notification text and timestamp.
3. **`.env` file**: Make sure the `.env` file exists in your home directory.
Create one if it does not exist.
4. **`ALPHAGENOME_API_KEY`**: This skill requires an API key to function.View the complete source on GitHubalphagenome-variant-impact-score
When your agent uses it
Score, annotate, and analyze the functional impact of genetic variants using AlphaGenome Variant Impact (AVI) scores. Query variants in chr:pos:ref>alt format, annotate VCF/tabular callsets, perform saturation mutagenesis window scans (1-based closed chr:start-end), and extract GENCODE v46 GTF gene/exon/junction coordinates all via the AlphaGenome Atlas API.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
4,566 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Programmatic Python SDK Usage
- Output Schemas & Response Structures
- Score Metrics & Interpretation
- Visualizations & Atlas Deep-Linking
Scripts executed separately
scripts/alphagenome_atlas_avi.py
Files
SKILL.mdcore16,713 bytesSKILL.mdcore16,713 bytesSKILL.mdcore16,713 bytesSKILL.mdcore16,713 bytesSKILL.mdcore16,713 bytesSKILL.mdcore16,713 bytesSKILL.mdcore16,713 bytesSKILL.mdcore16,713 bytespyproject.tomlasset314 bytesscripts/alphagenome_atlas_avi.pyruns72,835 bytes
Read SKILL.md
# AlphaGenome Variant Impact (AVI) Analysis
Score and prioritize genetic variants using AlphaGenome Variant Impact (AVI)
models via `scripts/alphagenome_atlas_avi.py`.
> [!IMPORTANT] **Research Use Only & Clinical Safety Rules**: The AlphaGenome
> AVI Skill and the underlying AlphaGenome model/Atlas are **strictly research
> tools**. Access to outputs requires an AlphaGenome API key subject to terms of
> service prohibiting clinical use.
>
> 1. **No Medical Advice or Clinical Diagnosis**: You **MUST NOT** provide
> medical advice, clinical diagnoses, disease management strategies, or
> treatment recommendations based on outputs from this skill or the
> AlphaGenome Atlas.View the complete source on GitHubchembl-database
When your agent uses it
Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures. Use when the user asks about compounds, targets, IC50/Ki values, drug mechanisms, or structure searches.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
2,911 tokensWhen the skill is activated
Reference documents
847 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Utility Script
- Common Options
- Reference
- Workflow
Scripts executed separately
scripts/chembl_api.py
Files
SKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesSKILL.mdcore11,504 bytesreferences/api_endpoints.mddoc2,832 bytesreferences/citation.bibasset3,639 bytesscripts/chembl_api.pyruns18,842 bytes
Read SKILL.md
# ChEMBL Database Query
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/chembl_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at
https://chembl.gitbook.io/chembl-interface-documentation/about, then (2)
create the file recording the notification text and timestamp.
## Core Rules
View the complete source on GitHubclinical-trials-database
When your agent uses it
Query ClinicalTrials.gov via APIv2. Use when you want to search for trials by condition, drug, location, status, or phase; retrieve trial details by NCT ID; check eligibility/inclusion criteria; count trials across conditions or time periods; identify a sponsor's trial portfolio; find recruiting trials for patient matching.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
3,237 tokensWhen the skill is activated
Reference documents
2,854 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Overview
- Core Rules
- Context Efficiency Warning
- Response Layout Summary
- Commands
- Pagination
- Advanced Querying
- References
Scripts executed separately
scripts/clinical_trials_api.py
Files
SKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesSKILL.mdcore12,708 bytesreferences/citation.bibasset376 bytesreferences/clinical_trials_api.mddoc6,331 bytesreferences/studies_schema.mddoc5,146 bytesscripts/clinical_trials_api.pyruns11,639 bytes
Read SKILL.md
# Clinical Trials Database
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/clinical_trials_database_LICENSE.txt
does not already exist in the workspace root directory then (1) prominently
notify the user to check the terms at https://clinicaltrials.gov/, then (2)
create the file recording the notification text and timestamp.
## Overview
Access worldwide clinical trial data from ClinicalTrials.gov via the REST APIView the complete source on GitHubclinvar-database
When your agent uses it
Use when needing clinical significance, pathogenicity classifications (e.g., Pathogenic, Benign, VUS), clinical evidence rationales, or finding "hard positive" benchmark controls for human genomic variants.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
4,015 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Overview
- When to Use
- Quick Start
- Core Rules
- Utility Scripts
- Typical Workflows
- Best Practices
- Common Mistakes
Scripts executed separately
scripts/clinvar_api.py
Files
SKILL.mdcore15,724 bytesSKILL.mdcore15,724 bytesSKILL.mdcore15,724 bytesSKILL.mdcore15,724 bytesSKILL.mdcore15,724 bytesSKILL.mdcore15,724 bytesSKILL.mdcore15,724 bytesreferences/citation.bibasset1,098 bytesscripts/clinvar_api.pyruns24,359 bytes
Read SKILL.md
# ClinVar Database
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/clinvar_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://www.ncbi.nlm.nih.gov/clinvar/, then
(2) create the file recording the notification text and timestamp.
3. **`.env` file**: Make sure the `.env` file exists in your home directory.
Create one if it does not exist.
4. **`NCBI_API_KEY`** (optional): Raises the NCBI rate limit from 3 to 10
requests/second. The skill works without it, but a key is recommended if theView the complete source on GitHubcredentials
When your agent uses it
Instructions for handling API keys and credentials safely, verifying their presence, and prompting the user to add them if missing using a safe protocol.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
971 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Safe Verification (No Leaks)
- Prompting the User to Add Credentials
- Running scripts requiring credentials
Files
SKILL.mdcore4,159 bytesSKILL.mdcore4,159 bytesSKILL.mdcore4,159 bytes
Read SKILL.md
# Safe Credentials Protocol
Many skills require API keys or other credentials to function or to access
higher rate limits. This skill defines the standard safe credentials protocol
for verifying and prompting for these credentials without leaking sensitive keys
into the agent context or the conversation history.
## Safe Verification (No Leaks)
As soon as a skill that requires a credential or API key looks relevant to the
user's request, you **MUST** immediately verify if the credential is present in
the `.env` file (typically located in your home directory `~/.env` or the
project root) — **before doing any other work** for that skill.
View the complete source on GitHubdbsnp-database
When your agent uses it
Use when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database. Resolves between rsIDs, genomic coordinates in VCF format, and HGVS strings. For an rsID, returns variant type, gene associations, clinical significance, allele frequencies, and genomic coordinates (GRCh38).
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
3,688 tokensWhen the skill is activated
Reference documents
1,025 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- When to Use
- Command Selection Guide
- Quick Start
- Commands
- Typical Workflows
- Assembly Defaults and Automatic Fallback
- NCBI API Key and Rate Limiting
- Troubleshooting HTTP 500 Errors
- Common Mistakes
Scripts executed separately
scripts/dbsnp_cli.py
Files
SKILL.mdcore13,639 bytesSKILL.mdcore13,639 bytesSKILL.mdcore13,639 bytesSKILL.mdcore13,639 bytesSKILL.mdcore13,639 bytesSKILL.mdcore13,639 bytesSKILL.mdcore13,639 bytesSKILL.mdcore13,639 bytesSKILL.mdcore13,639 bytesSKILL.mdcore13,639 bytesreferences/api-notes.mddoc3,762 bytesreferences/citation.bibasset368 bytesscripts/dbsnp_cli.pyruns19,840 bytes
Read SKILL.md
# dbSNP Database Integration
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/dbsnp_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://www.ncbi.nlm.nih.gov/snp/, then (2)
create the file recording the notification text and timestamp.
3. **`.env` file**: Make sure the `.env` file exists in your home directory.
Create one if it does not exist.
4. **`NCBI_API_KEY`** (optional): Raises the NCBI rate limit from 3 to 10
requests/second. The skill works without it, but a key is recommended if theView the complete source on GitHubembl-ebi-ols
When your agent uses it
Query and search the EMBL-EBI Ontology Lookup Service (OLS) for biomedical ontology terms, definitions, and hierarchies across 250+ ontologies (e.g., GO, DOID, HP). Use when the user asks to search for terms, retrieve details, navigate hierarchies (parents, children, ancestors), look up properties and individuals, get autocomplete suggestions, or access ontology metadata and statistics.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
3,071 tokensWhen the skill is activated
Reference documents
1,340 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- When to Use — Quick Recipes
- Utility Scripts
- Reference
- Workflow
Scripts executed separately
scripts/get_individual.pyscripts/get_ontology.pyscripts/get_property.pyscripts/get_stats.pyscripts/get_term.pyscripts/ols_utils.pyscripts/search_ols.pyscripts/suggest_ols.py
Files
SKILL.mdcore11,463 bytesSKILL.mdcore11,463 bytesSKILL.mdcore11,463 bytesSKILL.mdcore11,463 bytesSKILL.mdcore11,463 bytesSKILL.mdcore11,463 bytesSKILL.mdcore11,463 bytesSKILL.mdcore11,463 bytesSKILL.mdcore11,463 bytesreferences/api_reference.mddoc5,117 bytesreferences/citation.bibasset2,037 bytesscripts/get_individual.pyruns5,387 bytesscripts/get_ontology.pyruns4,423 bytesscripts/get_property.pyruns6,743 bytesscripts/get_stats.pyruns2,085 bytesscripts/get_term.pyruns10,524 bytesscripts/ols_utils.pyruns2,761 bytesscripts/search_ols.pyruns6,577 bytesscripts/suggest_ols.pyruns3,818 bytes
Read SKILL.md
# EMBL-EBI Ontology Lookup Service (OLS)
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/embl_ebi_ols_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://www.ebi.ac.uk/ols4/api-docs, then (2)
create the file recording the notification text and timestamp.
## Core Rules
- [!IMPORTANT] **Use the Utility Scripts**: You MUST ALWAYS use the providedView the complete source on GitHubencode-ccres-database
When your agent uses it
Query the ENCODE Registry of cis-Regulatory Elements (cCREs) via the SCREEN GraphQL API, or make custom queries to the ENCODE Portal REST API for experiments and files (ChIP-seq peaks, etc.). Use when you want to query regulatory annotations or raw experimental data across human cell types.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
1,750 tokensWhen the skill is activated
Reference documents
2,938 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- ENCODE Portal REST API (Direct Access)
- Custom Queries (SCREEN GraphQL)
Scripts executed separately
scripts/encode_portal_api.pyscripts/screen_api.py
Files
SKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesSKILL.mdcore6,847 bytesreferences/citation.bibasset7,838 bytesreferences/graphql_schema.mddoc4,708 bytesreferences/json_output_structure.mddoc5,622 bytesscripts/encode_portal_api.pyruns2,099 bytesscripts/screen_api.pyruns20,490 bytes
Read SKILL.md
# ENCODE Database Skill
This skill allows you to query the ENCODE Registry of cCREs (candidate
cis-Regulatory Elements) via the SCREEN GraphQL API. It helps identify
functional non-coding DNA elements (like Promoters, Enhancers, and insulators)
by analyzing biochemical signatures (DNase, H3K4me3, H3K27ac, CTCF).
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/encode_ccres_database_LICENSE.txt does
not already exist in the workspace root directory then (1) prominently
notify the user to check the terms atView the complete source on GitHubensembl-database
When your agent uses it
Query the Ensembl database to resolve gene, transcript, and protein IDs, fetch genomic or protein sequences, retrieve gene structures (exons), and get variant consequence and effect predictions (VEP). Use this skill as a primary ID translator, genomic sequence database and variant effect prediction tool.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
2,289 tokensWhen the skill is activated
Reference documents
3,222 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Overview
- Core Rules
- Parsing Outputs
- Custom Queries
Scripts executed separately
scripts/ensembl_api.py
Files
SKILL.mdcore8,827 bytesSKILL.mdcore8,827 bytesSKILL.mdcore8,827 bytesSKILL.mdcore8,827 bytesSKILL.mdcore8,827 bytesSKILL.mdcore8,827 bytesSKILL.mdcore8,827 bytesSKILL.mdcore8,827 bytesSKILL.mdcore8,827 bytesSKILL.mdcore8,827 bytesSKILL.mdcore8,827 bytesSKILL.mdcore8,827 bytesreferences/citation.bibasset3,789 bytesreferences/ensembl_rest_api_reference.mddoc11,511 bytesscripts/ensembl_api.pyruns23,730 bytes
Read SKILL.md
# Ensembl Database: ID Mapping and Genomic Features
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/ensembl_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://useast.ensembl.org/index.html and
https://github.com/Ensembl/ensembl-rest/wiki, then (2) create the file
recording the notification text and timestamp.
## Overview
View the complete source on GitHubfoldseek-structural-search
When your agent uses it
Performs 3D structural searches of proteins against various databases (PDB, AlphaFold, CATH, MGnify, etc.) using the Foldseek API. Use ONLY when the user provides a physical 3D coordinate file (.cif, .mmcif, or .pdb) and wants to find structurally similar proteins. Do NOT use if the user only provides a protein sequence, gene name, or UniProt ID.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
1,286 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Goal
- Core Rules
- Instructions
- * If the API returns an error or the file is missing, inform the user clearly
Scripts executed separately
scripts/search.py
Files
SKILL.mdcore5,351 bytesSKILL.mdcore5,351 bytesreferences/citation.bibasset445 bytesscripts/search.pyruns8,005 bytes
Read SKILL.md
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/foldseek_structural_search_LICENSE.txt
does not already exist in the workspace root directory then (1) prominently
notify the user to check the terms at https://search.foldseek.com/search and
https://github.com/steineggerlab/foldseek, then (2) create the file
recording the notification text and timestamp.
## Goal
Submit a user-provided 3D protein structure file (`.cif`, `.mmcif`, or `.pdb`)
to the Foldseek web server API to find structurally similar proteins. Report theView the complete source on GitHubgnomad-database
When your agent uses it
Query the Genome Aggregation Database (gnomAD). Use when determining the rarity or allele frequency of specific genetic variants, retrieving gene constraint metrics (pLI, LOEUF) to assess loss-of-function intolerance, finding variants in a genomic region or gene, or querying structural variants. Don't use for analyzing individual patient genomes, tracking somatic mutations in cancer (use COSMIC), or requesting raw sequencing reads (use ENA).
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
764 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Utility Scripts
- References
Scripts executed separately
scripts/get_gene_constraint.pyscripts/get_variant_frequency.pyscripts/search_variants.py
Files
SKILL.mdcore3,098 bytesSKILL.mdcore3,098 bytesSKILL.mdcore3,098 bytesSKILL.mdcore3,098 bytesreferences/citation.bibasset5,197 bytesscripts/get_gene_constraint.pyruns2,465 bytesscripts/get_variant_frequency.pyruns4,326 bytesscripts/search_variants.pyruns5,360 bytes
Read SKILL.md
# gnomAD Database
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/gnomad_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://gnomad.broadinstitute.org/policies
and https://gnomad.broadinstitute.org/data#api, then (2) create the file
recording the notification text and timestamp.
## Core Rules
View the complete source on GitHubgtex-database
When your agent uses it
Use when you want to retrieve quantitative RNA expression data and variant eQTL information from the GTEx (Genotype-Tissue Expression) Project across 54 non-diseased tissue sites.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
1,647 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- When to Use
- Core Rules
- Command Selection Guide
- Quick Start
- Commands
- Typical Workflows
Scripts executed separately
scripts/gtex_cli.py
Files
SKILL.mdcore6,071 bytesSKILL.mdcore6,071 bytesSKILL.mdcore6,071 bytesSKILL.mdcore6,071 bytesSKILL.mdcore6,071 bytesSKILL.mdcore6,071 bytesSKILL.mdcore6,071 bytesSKILL.mdcore6,071 bytesreferences/citation.bibasset5,807 bytesscripts/gtex_cli.pyruns8,904 bytes
Read SKILL.md
# GTEx Database Integration
This skill retrieves transcriptomics data (RNA expression baselines) and
expression Quantitative Trait Loci (eQTLs) from the GTEx Portal API V2. It
provides access to median TPM (Transcripts Per Million) values for genes and
significant eQTLs for variants across 54 human tissue sites.
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/gtex_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://gtexportal.org/home/license andView the complete source on GitHubhuman-protein-atlas-database
When your agent uses it
Use when you want to retrieve semi-quantitative protein expression and spatial localisation data from the Human Protein Atlas (HPA).
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
1,644 tokensWhen the skill is activated
Reference documents
1,498 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- When to Use
- Command Selection Guide
- Quick Start
- Commands
- Core Rules
- API Versioning
- Common Errors
Scripts executed separately
scripts/hpa_cli.py
Files
SKILL.mdcore6,439 bytesSKILL.mdcore6,439 bytesSKILL.mdcore6,439 bytesSKILL.mdcore6,439 bytesSKILL.mdcore6,439 bytesSKILL.mdcore6,439 bytesSKILL.mdcore6,439 bytesSKILL.mdcore6,439 bytesreferences/citation.bibasset2,768 bytesreferences/search-api.mddoc5,893 bytesscripts/hpa_cli.pyruns8,325 bytes
Read SKILL.md
# Human Protein Atlas (HPA) Database Integration
This skill provides semi-quantitative protein expression and spatial
localisation data from the Human Protein Atlas (HPA). While RNA-seq (e.g., GTEx)
tells us if a gene is being transcribed, HPA confirms if the protein product
actually exists, where it is located within the cell (e.g. nucleus vs
cytoplasm), and its concentration in systemic blood circulation. The data is
based on Immunohistochemistry (IHC) across normal human tissues and cancer
types.
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.View the complete source on GitHubinterpro-database
When your agent uses it
Identify domains, families, and sites in proteins; find all proteins in a family or sharing a domain; explore species distribution for a domain; annotate genomes with protein families and GO terms. InterPro combines 14 databases (e.g., Pfam, CDD) into one searchable resource. InterPro-N significantly expands annotation and sequence coverage with deep learning. Includes domain architecture (IDA) search.
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
4,198 tokensWhen the skill is activated
Reference documents
1,972 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Overview
- Core Rules
- Valid Source Databases (`--source_db`)
- Quick Reference / Core Endpoints & Parameters
- InterPro Domain Architecture (IDA) Search
- InterPro Entry Types
- InterPro-N Predictions
- Strict Lookup Rules
- Quick examples
Scripts executed separately
scripts/interpro_client.py
Files
SKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesSKILL.mdcore16,977 bytesreferences/api_reference.mddoc7,898 bytesreferences/citation.bibasset3,469 bytesreferences/example_responses.tsvasset13,208 bytesscripts/interpro_client.pyruns14,796 bytes
Read SKILL.md
# InterPro Database Access
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/interpro_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://www.ebi.ac.uk/interpro/ and
https://www.ebi.ac.uk/about/terms-of-use/, then (2) create the file
recording the notification text and timestamp.
## Overview
View the complete source on GitHubjaspar-database
When your agent uses it
Query the JASPAR database for Transcription Factor (TF) binding profiles. Use when retrieving Position Frequency Matrices (PFMs) or Position Weight Matrices (PWMs) for specific TFs, resolving gene symbols to JASPAR Matrix IDs, or getting TF metadata. Supports multiple output formats (MEME, TRANSFAC, PFM, JASPAR, YAML).
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
1,189 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Utility Scripts
- Anti-Patterns
Scripts executed separately
scripts/jaspar_api.py
Files
SKILL.mdcore4,465 bytesSKILL.mdcore4,465 bytesSKILL.mdcore4,465 bytesSKILL.mdcore4,465 bytesSKILL.mdcore4,465 bytesSKILL.mdcore4,465 bytesSKILL.mdcore4,465 bytesreferences/citation.bibasset2,665 bytesscripts/jaspar_api.pyruns8,785 bytes
Read SKILL.md
# JASPAR Skill
JASPAR is the definitive open-access database for Transcription Factor (TF)
binding profiles, stored as Position Frequency Matrices (PFMs).
Use this skill to map abstract sequence motifs or genomic regions to specific
biological regulators (e.g., "what TFs bind here?" or "what is the motif for
CTCF?").
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/jaspar_database_LICENSE.txt does notView the complete source on GitHubliterature-search-arxiv
When your agent uses it
Search for scientific papers, preprints, and publications on arXiv. Extract metadata, abstracts, and download full-text PDFs or HTML versions of papers. Use when the user asks to find research papers, literature, or specific arXiv IDs.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
1,164 tokensWhen the skill is activated
Reference documents
282 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Utility Scripts
- Reference
- Workflow
Scripts executed separately
scripts/download_paper.pyscripts/download_paper_source.pyscripts/search_arxiv.py
Files
SKILL.mdcore4,628 bytesSKILL.mdcore4,628 bytesSKILL.mdcore4,628 bytesSKILL.mdcore4,628 bytesSKILL.mdcore4,628 bytesSKILL.mdcore4,628 bytesSKILL.mdcore4,628 bytesSKILL.mdcore4,628 bytesreferences/citation.bibasset366 bytesreferences/query_syntax.mddoc997 bytesscripts/download_paper.pyruns3,455 bytesscripts/download_paper_source.pyruns2,881 bytesscripts/search_arxiv.pyruns5,118 bytes
Read SKILL.md
# arXiv Search and Retrieval
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/literature_search_arxiv_LICENSE.txt does
not already exist in the workspace root directory then (1) prominently
notify the user to check the terms at
https://info.arxiv.org/help/api/index.html and to always check the license
of the papers retrieved by the skill for any restrictions, then (2) create
the file recording the notification text and timestamp.
## Core RulesView the complete source on GitHubliterature-search-biorxiv
When your agent uses it
Browse and filter life sciences, biology, and medical preprints from bioRxiv and medRxiv. Supports fetching paper metadata by DOI, and browsing by date range with category and keyword filters. Keyword filtering is local, so date ranges MUST be narrow (1-4 weeks) with a category to prevent timeouts.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
1,993 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Search Strategy Guide (Read First)
- Core Rules
- Utility Scripts
- Valid Subject Categories
Scripts executed separately
scripts/search_by_dates.pyscripts/search_by_doi.py
Files
SKILL.mdcore7,736 bytesSKILL.mdcore7,736 bytesSKILL.mdcore7,736 bytesreferences/citation.bibasset3,018 bytesscripts/search_by_dates.pyruns8,611 bytesscripts/search_by_doi.pyruns2,101 bytes
Read SKILL.md
# bioRxiv and medRxiv Literature Search
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/literature_search_biorxiv_LICENSE.txt
does not already exist in the workspace root directory then (1) prominently
notify the user to check the terms at https://api.biorxiv.org/ and
https://www.biorxiv.org/content/about-biorxiv and to always check the
license of the papers retrieved by the skill for any restrictions, then (2)
create the file recording the notification text and timestamp.
## Search Strategy Guide (Read First)View the complete source on GitHubliterature-search-europepmc
When your agent uses it
Search Europe PMC for scientific literature and download open-access full texts and PDFs. Retrieve full-text XML/plain text by PMCID, get citation lists and bibliography.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
2,295 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Utility Scripts
- Common Workflows
Scripts executed separately
scripts/europepmc_api.py
Files
SKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesSKILL.mdcore8,357 bytesreferences/citation.bibasset2,022 bytesscripts/europepmc_api.pyruns11,419 bytes
Read SKILL.md
# Europe PMC Database
A skill for searching, downloading, and exploring open-access papers from
[Europe PMC](https://europepmc.org/) — a comprehensive, free life-science
literature database with over 43 million abstracts and 9 million full-text
articles.
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/literature_search_europepmc_LICENSE.txt
does not already exist in the workspace root directory then (1) prominently
notify the user to check the terms at https://europepmc.org/ and to alwaysView the complete source on GitHubliterature-search-openalex
When your agent uses it
Query the OpenAlex scholarly database for research papers, authors, institutions, topics, sources, publishers, funders, geo-locations, and keywords. Use when searching academic papers, resolving DOIs, downloading open-access PDFs, finding an author's publications, aggregating bibliometric data (citation counts, h-index, impact factor), exploring the research taxonomies, or performing DOI lookups.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
2,176 tokensWhen the skill is activated
Reference documents
10,274 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Rate Limits
- CLI Reference
- Entity References
- Common Workflows
- Error Handling
Scripts executed separately
scripts/openalex_cli.py
Files
SKILL.mdcore8,514 bytesSKILL.mdcore8,514 bytesreferences/authors.mddoc3,703 bytesreferences/citation.bibasset299 bytesreferences/geo_and_language.mddoc1,982 bytesreferences/institutions.mddoc2,813 bytesreferences/publishers_funders.mddoc2,571 bytesreferences/sources.mddoc3,851 bytesreferences/taxonomy.mddoc2,865 bytesreferences/topics.mddoc1,188 bytesreferences/type_values.mddoc3,657 bytesreferences/works.mddoc17,281 bytesscripts/openalex_cli.pyruns23,953 bytes
Read SKILL.md
# OpenAlex Skill
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/literature_search_openalex_LICENSE.txt
does not already exist in the workspace root directory then (1) prominently
notify the user to check the terms at https://help.openalex.org/ and to
always check the license of the papers retrieved by the skill for any
restrictions, then (2) create the file recording the notification text and
timestamp.
3. **`.env` file**: Make sure the `.env` file exists in your home directory.
Create one if it does not exist.View the complete source on GitHubncbi-sequence-fetch
When your agent uses it
Retrieve protein and nucleotide sequences from NCBI databases using E-utilities. Supports direct accession lookup, CDS translation, gene+organism search, locus lookup, PubMed-linked sequences, patent protein extraction, and organism+length fallback search. Use when you need to fetch biological sequences by accession, gene name, locus tag, PubMed ID, or patent number.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
2,449 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Overview
- Utility Scripts
- Workflow
- Reference
Scripts executed separately
scripts/ncbi_fetch.py
Files
SKILL.mdcore9,073 bytesSKILL.mdcore9,073 bytesSKILL.mdcore9,073 bytesSKILL.mdcore9,073 bytesSKILL.mdcore9,073 bytesSKILL.mdcore9,073 bytesSKILL.mdcore9,073 bytesSKILL.mdcore9,073 bytesSKILL.mdcore9,073 bytesSKILL.mdcore9,073 bytesSKILL.mdcore9,073 bytesSKILL.mdcore9,073 bytesreferences/citation.bibasset1,809 bytesscripts/ncbi_fetch.pyruns35,920 bytes
Read SKILL.md
# NCBI Sequence Fetch
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/ncbi_sequence_fetch_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://www.ncbi.nlm.nih.gov/ and
https://www.ncbi.nlm.nih.gov/home/about/policies/, then (2) create the file
recording the notification text and timestamp.
3. **`.env` file**: Make sure the `.env` file exists in your home directory.
Create one if it does not exist.
4. **`NCBI_API_KEY`** (optional): Raises the NCBI rate limit from 3 to 10View the complete source on GitHubopenfda-database
When your agent uses it
Query, search, and download data from the openFDA API for drugs, devices, foods, tobacco, cosmetics, animal and veterinary products, substances, and transparency data. Use for FDA adverse events, recalls, labeling, approvals, shortages, 510(k) clearances, NDC lookups, and any FDA safety or regulatory data query across all 28 API endpoints.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
2,568 tokensWhen the skill is activated
Reference documents
2,955 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Utility Script
- Entity Resolution: Using .exact for Precision
- NDC Lookups: Hyphens & Discontinued Drugs
- MedDRA Term Resolution
- Available Endpoints (28 total)
- Reference
- Recipes
- Workflow
Scripts executed separately
scripts/openfda_query.py
Files
SKILL.mdcore9,917 bytesSKILL.mdcore9,917 bytesSKILL.mdcore9,917 bytesSKILL.mdcore9,917 bytesSKILL.mdcore9,917 bytesSKILL.mdcore9,917 bytesSKILL.mdcore9,917 bytesSKILL.mdcore9,917 bytesreferences/api_endpoints.mddoc6,414 bytesreferences/citation.bibasset2,029 bytesreferences/recipes.mddoc4,524 bytesscripts/openfda_query.pyruns14,264 bytes
Read SKILL.md
# openFDA Search and Query
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/openfda_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://open.fda.gov/apis/ and
https://open.fda.gov/license, then (2) create the file recording the
notification text and timestamp.
3. **`.env` file**: Make sure the `.env` file exists in your home directory.
Create one if it does not exist.
4. **`FDA_API_KEY`** (optional but recommended): Raises the daily request limitView the complete source on GitHubopentargets-database
When your agent uses it
Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
2,404 tokensWhen the skill is activated
Reference documents
2,099 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Prerequisites
- Core Rules
- Quick Reference
- L2G Query Usage
- Querying by Region
- Advanced GraphQL Queries
- Confidence Star Ratings
- Tips and Common Mistakes
Scripts executed separately
scripts/query_opentargets.py
Files
SKILL.mdcore9,527 bytesSKILL.mdcore9,527 bytesSKILL.mdcore9,527 bytesreferences/OpenTargets_GraphQL_Guide.mddoc7,837 bytesreferences/citation.bibasset2,489 bytesscripts/query_opentargets.pyruns18,601 bytes
Read SKILL.md
# Open Targets Database Skill
## Overview
This skill provides access to the Open Targets Platform GraphQL API. It
aggregates multi-modal evidence from genetics (GWAS/eQTL), pathways, animal
models, and clinical trials to rank target-disease associations and identify
druggable genes.
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/opentargets_database_LICENSE.txt doesView the complete source on GitHubpdb-database
When your agent uses it
Use when you want to search for or download experimentally-determined 3D structures for biomolecules (proteins, nucleic acids, bound ligands). Supports searching by sequence similarity, structure similarity, chemical and other attributes. Also use to get metadata about biomolecular structure experiments.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
2,305 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Attribute-based search workflow
- Similarity-based search workflow
- Full text search workflow
- File download workflow
- Metadata query workflow
Scripts executed separately
scripts/download_coordinate_files.pyscripts/fetch_pdb_metadata.pyscripts/fetch_schema.pyscripts/search_pdb.py
Files
SKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesSKILL.mdcore8,893 bytesreferences/citation.bibasset878 bytesscripts/download_coordinate_files.pyruns3,245 bytesscripts/fetch_pdb_metadata.pyruns1,893 bytesscripts/fetch_schema.pyruns7,720 bytesscripts/search_pdb.pyruns5,634 bytes
Read SKILL.md
# RCSB Protein Data Bank skill
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/pdb_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://www.rcsb.org/pages/usage-policy, then
(2) create the file recording the notification text and timestamp.
## Core RulesView the complete source on GitHubpredictingthepast
When your agent uses it
Ancient text restoration, attribution, dating, contextualization, and embedding via Aeneas (Latin) / Ithaca (Ancient Greek). Use when asked to "restore", "attribute", "date", "contextualize", "find parallels", "where was it written", "when was it written", "embed", or "analyze" an ancient text, inscription, or epigraphic document, or when the user mentions "Aeneas", or "Ithaca".
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
3,741 tokensWhen the skill is activated
Reference documents
1,471 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- On First Load
- Preprocessing
- Inference
- References
Scripts executed separately
scripts/preprocess.pyscripts/run_inference.pyscripts/visualize_results.py
Files
SKILL.mdcore14,683 bytesSKILL.mdcore14,683 bytesSKILL.mdcore14,683 bytesSKILL.mdcore14,683 bytesSKILL.mdcore14,683 bytesSKILL.mdcore14,683 bytesreferences/iphi-region-sub-loc.jsonasset6,382 bytesreferences/iphi-region-sub.txtdoc1,107 bytesreferences/led-proper-names.txtdoc337,928 bytesreferences/led-region-sub-loc.jsonasset4,585 bytesreferences/led-region-sub.txtdoc735 bytesreferences/output_format.mddoc5,763 bytesscripts/preprocess.pyruns8,153 bytesscripts/run_inference.pyruns27,551 bytesscripts/visualize_results.pyruns23,866 bytes
Read SKILL.md
# Predicting The Past (Aeneas / Ithaca)
Aeneas (Latin) and Ithaca (Ancient Greek) perform four tasks on ancient texts:
1. **Restoration** — fill missing/damaged characters
2. **Attribution** — geographical + chronological origin
3. **Contextualization** — retrieve parallel inscriptions
4. **Embedding** — generate text embedding vectors
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
View the complete source on GitHubprotein-sequence-msa
When your agent uses it
Performs multiple sequence alignment of proteins with EBI Clustal Omega. Use when you need to align multiple sequences to assess similarity, domain conservation, or key residue conservation. Supports up to 4000 sequences and a maximum file size of 4 MB. Do not use to search for homologous proteins in a database (use MMseqs2, BLAST), align non-protein sequences (DNA, RNA), perform structural alignment (use Foldseek, PyMOL), or if you only have a single sequence.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
1,361 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Goal
- Instructions
- References
Scripts executed separately
scripts/msa_align.py
Files
SKILL.mdcore6,113 bytesSKILL.mdcore6,113 bytesreferences/citation.bibasset4,729 bytesscripts/msa_align.pyruns4,953 bytes
Read SKILL.md
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/protein_sequence_msa_LICENSE.txt does
not already exist in the workspace root directory then (1) prominently
notify the user to check the terms at
https://www.ebi.ac.uk/jdispatcher/msa/clustalo and
https://www.ebi.ac.uk/about/terms-of-use/, then (2) create the file
recording the notification text and timestamp.
3. **`.env` file**: Make sure the `.env` file exists in your home directory.
Create one if it does not exist.
4. **`USER_EMAIL`**: Required by the wrapper script for Clustal Omega job
tracking (recommended by the EBI). You **MUST** use the safe credentialsView the complete source on GitHubprotein-sequence-similarity-search
When your agent uses it
Searches for homologous protein sequences using MMseqs2 (fast, default) or BLAST (comprehensive, fallback). Trigger this whenever the user provides a protein sequence or FASTA file and asks to find homologues, sequence matches, or wants to infer protein function based on sequence similarity, but not when the user wants to infer protein function based on structural similarity.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
2,786 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Goal
- Core Rules
- Search Method Selection
- Instructions
- Available BLAST Databases
Scripts executed separately
scripts/mmseqs2_search.pyscripts/uniprot_blast.py
Files
SKILL.mdcore10,728 bytesreferences/citation.bibasset2,128 bytesscripts/mmseqs2_search.pyruns11,107 bytesscripts/uniprot_blast.pyruns9,033 bytes
Read SKILL.md
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If
.licenses/protein_sequence_similarity_search_LICENSE.txt does not already
exist in the workspace root directory then (1) prominently notify the user
to check the terms at https://www.ebi.ac.uk/jdispatcher/sss/ncbiblast and
https://colabfold.com, then (2) create the file recording the notification
text and timestamp.
3. **`.env` file**: Make sure the `.env` file exists in your home directory.
Create one if it does not exist.
4. **`USER_EMAIL`** (optional but recommended): Recommended by the EBI for
BLAST job tracking, but the skill works without it. You **MUST** use theView the complete source on GitHubpubchem-database
When your agent uses it
Query PubChem, search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics. Use when a user asks about a specific chemical, drug, or molecule.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
1,403 tokensWhen the skill is activated
Reference documents
1,049 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Quick Start
- Core Rules
- Core Capabilities
- Advanced Context
- Complex Search & Biology
- Advanced Usage & Workflows
- Fallback Search Strategies
- Complex Queries and Multi-Step Tasks
Scripts executed separately
scripts/pubchem_api.py
Files
SKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesSKILL.mdcore5,615 bytesreferences/citation.bibasset2,042 bytesreferences/endpoints.mddoc2,448 bytesreferences/workflows.mddoc1,392 bytesscripts/pubchem_api.pyruns11,532 bytes
Read SKILL.md
# PubChem Database
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/pubchem_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at
https://pubchem.ncbi.nlm.nih.gov/docs/citation-guidelines and
https://pubchem.ncbi.nlm.nih.gov/docs/pug-rest, then (2) create the file
recording the notification text and timestamp.
## Quick StartView the complete source on GitHubpubmed-database
When your agent uses it
Search PubMed for scientific literature, including published clinical trials. Fetch abstracts and full text. Link published research to biological databases (gene, protein, nucleotide, PubChem) to discover associations between papers and specific compounds or genes. Verify medical spelling, match raw citations, and cache result sets for bulk processing. Interfaces NCBI E-utilities and PMC BioC APIs.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
2,007 tokensWhen the skill is activated
Reference documents
8,767 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Structure of the skill folder
- CLI Usage
- Essential Recipes
- Functions
Scripts executed separately
scripts/pubmed_api.py
Files
SKILL.mdcore8,343 bytesSKILL.mdcore8,343 bytesSKILL.mdcore8,343 bytesSKILL.mdcore8,343 bytesSKILL.mdcore8,343 bytesSKILL.mdcore8,343 bytesSKILL.mdcore8,343 bytesSKILL.mdcore8,343 bytesreferences/advanced-linking.mddoc5,520 bytesreferences/advanced-search.mddoc3,660 bytesreferences/bulk-workflows.mddoc3,599 bytesreferences/citation-matching.mddoc5,344 bytesreferences/citation.bibasset1,809 bytesreferences/cross-database-linking.mddoc4,025 bytesreferences/fetch-and-resolve.mddoc5,606 bytesreferences/search-and-discovery.mddoc4,948 bytesreferences/utilities.mddoc1,357 bytesscripts/pubmed_api.pyruns21,444 bytes
Read SKILL.md
# PubMed API
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/pubmed_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://pubmed.ncbi.nlm.nih.gov/disclaimer/
and https://www.ncbi.nlm.nih.gov/home/about/policies/ and to always check
the license of the papers retrieved by the skill for any restrictions, then
(2) create the file recording the notification text and timestamp.
3. **`.env` file**: Make sure the `.env` file exists in your home directory.
Create one if it does not exist.View the complete source on GitHubpymol
When your agent uses it
Visualize, analyze, and render protein and molecular structures using PyMOL. Use when the user wants to create images of protein structures, perform structural alignments or superposition, measure distances or contacts, highlight binding sites or active site residues, color by B-factor/pLDDT, or analyze protein-ligand interactions. Do not use for docking, molecular dynamics, or sequence-only analysis.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,626 tokensWhen the skill is activated
Reference documents
4,736 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Overview
- Setup (Agent Instructions)
- Core Rules
- Quick Start
- Common Recipes
- Interpreting Output
Files
SKILL.mdcore6,624 bytesSKILL.mdcore6,624 bytesSKILL.mdcore6,624 bytesSKILL.mdcore6,624 bytesreferences/PYMOL_REFERENCE.mddoc5,454 bytesreferences/RECIPES.mddoc11,357 bytesreferences/citation.bibasset143 bytes
Read SKILL.md
# PyMOL
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/pymol_LICENSE.txt does not already exist
in the workspace root directory then (1) prominently notify the user to
check the license at https://www.pymol.org/, then (2) create the file
recording the notification text and timestamp.
## Overview
All PyMOL commands run on the host via `uv` with OSMesa software rendering — noView the complete source on GitHubquickgo-database
When your agent uses it
Query the QuickGO and Evidence & Conclusion Ontology (ECO) REST API. Use this when you need to map genes to biological processes, molecular functions, or cellular components, find genes associated with a specific pathway/GO term, or explore the Gene Ontology hierarchy. Do not use for querying drug targets (use OpenTargets) or mechanistic signaling pathway diagrams (use KEGG).
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
1,437 tokensWhen the skill is activated
Reference documents
1,734 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Usage
- Core Rules
- Common Workflows
Scripts executed separately
scripts/quickgo_tool.py
Files
SKILL.mdcore5,659 bytesSKILL.mdcore5,659 bytesSKILL.mdcore5,659 bytesSKILL.mdcore5,659 bytesSKILL.mdcore5,659 bytesreferences/annotations.mddoc2,086 bytesreferences/citation.bibasset1,425 bytesreferences/eco_terms.mddoc1,450 bytesreferences/gene_products.mddoc849 bytesreferences/go_terms.mddoc2,086 bytesscripts/quickgo_tool.pyruns9,952 bytes
Read SKILL.md
# QuickGO Database Skill
GO (Gene Ontology) annotations are one of the main ways to label a gene's
function. QuickGO is a fast, web-based browser for the GO and Evidence &
Conclusion Ontology (ECO), maintained by the Gene Ontology Annotation (GOA)
group at EMBL-EBI.
It provides a centralised resource to explore the functional attributes of gene
products (proteins, RNA, and complexes). It is a primary tool for functional
annotation mapping since it allows you to link a gene (e.g., USH2A) to its
specific biological processes (e.g. sensory perception of light stimulus),
molecular functions, and cellular components.
## PrerequisitesView the complete source on GitHubreactome-database
When your agent uses it
Query the Reactome database (Analysis and Content Services). Use when the user asks about pathway analysis, gene list enrichment, retrieving results by token, finding unmapped or not-found identifiers, mapping identifiers, reaction participants (inputs, outputs), pathway hierarchy (including top-level pathways), diagram export, cross-reference mapping, or searching the knowledgebase.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
2,801 tokensWhen the skill is activated
Reference documents
1,045 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Overview
- When to Use This Skill
- Common Species IDs
- Common Pathway IDs
- Core Rules
- Tool Execution
- Feature Domains
- Recipe: Interpreting Gene Set Enrichment
- Reference
Scripts executed separately
scripts/reactome_analysis.py
Files
SKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesSKILL.mdcore11,026 bytesreferences/api_reference.mddoc4,156 bytesreferences/citation.bibasset2,284 bytesscripts/reactome_analysis.pyruns31,209 bytes
Read SKILL.md
# Reactome Analysis & Content Service
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/reactome_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://reactome.org/license and
https://reactome.org/cite, then (2) create the file recording the
notification text and timestamp.
## Overview
View the complete source on GitHubstring-database
When your agent uses it
Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
687 tokensWhen the skill is activated
Reference documents
1,607 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Tool Execution
- Feature Domains (Progressive Disclosure)
Scripts executed separately
scripts/string_cli.py
Files
SKILL.mdcore2,926 bytesSKILL.mdcore2,926 bytesSKILL.mdcore2,926 bytesreferences/citation.bibasset567 bytesreferences/enrichment.mddoc1,629 bytesreferences/interactions.mddoc2,081 bytesreferences/mapping.mddoc735 bytesreferences/valuesranks.mddoc1,668 bytesscripts/string_cli.pyruns12,068 bytes
Read SKILL.md
# STRING Database Skill
This skill allows you to query the STRING database programmatically using a
bundled Python CLI wrapper.
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/string_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://string-db.org/cgi/access, then (2)
create the file recording the notification text and timestamp.
View the complete source on GitHubucsc-conservation-and-tfbs
When your agent uses it
Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
1,981 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Rules
- Utility Scripts
- Anti-Patterns
Scripts executed separately
scripts/get_conservation.pyscripts/get_tfbs.pyscripts/list_tracks.py
Files
SKILL.mdcore7,714 bytesSKILL.mdcore7,714 bytesSKILL.mdcore7,714 bytesSKILL.mdcore7,714 bytesSKILL.mdcore7,714 bytesSKILL.mdcore7,714 bytesSKILL.mdcore7,714 bytesSKILL.mdcore7,714 bytesSKILL.mdcore7,714 bytesreferences/citation.bibasset810 bytesscripts/get_conservation.pyruns7,726 bytesscripts/get_tfbs.pyruns4,984 bytesscripts/list_tracks.pyruns4,268 bytes
Read SKILL.md
# Conservation Scores & TFBS Lookup (UCSC)
This skill provides access to evolutionary constraint scores and conserved
elements from the UCSC Genome Browser. It retrieves scores from the PHAST
package — specifically `phastCons` (identifying functional blocks) and `phyloP`
(measuring individual site constraint) — calculated from multiple alignments.
Use this skill to determine if a non-coding variant hits a site that hasn't
changed since a common ancestor (which is a strong signal for pathogenicity) or
to find conservation peaks across a regulatory element.
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensureView the complete source on GitHubunibind-database
When your agent uses it
Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED/FASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
1,419 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Quick Start
- Core Rules
- Utility Scripts
- Anti-Patterns
Scripts executed separately
scripts/unibind_api.py
Files
SKILL.mdcore5,311 bytesSKILL.mdcore5,311 bytesSKILL.mdcore5,311 bytesSKILL.mdcore5,311 bytesSKILL.mdcore5,311 bytesSKILL.mdcore5,311 bytesSKILL.mdcore5,311 bytesSKILL.mdcore5,311 bytesSKILL.mdcore5,311 bytesSKILL.mdcore5,311 bytesreferences/citation.bibasset745 bytesscripts/unibind_api.pyruns13,117 bytes
Read SKILL.md
# UniBind Database Skill
UniBind is a database of direct TF–DNA interactions across 9 species,
integrating ChIP-seq peaks with JASPAR TF binding profiles via the DAMO
framework.
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/unibind_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://unibind.uio.no/ and
https://unibind.uio.no/api/overview, then (2) create the file recording theView the complete source on GitHubuniprot-database
When your agent uses it
Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
3,144 tokensWhen the skill is activated
Reference documents
9,338 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Overview
- Core Rules
- Use Cases
- Available Tools
- Workflows
- Example Commands
- Common Mistakes
- Reference Materials
Scripts executed separately
scripts/uniprot_tools.py
Files
SKILL.mdcore12,329 bytesSKILL.mdcore12,329 bytesSKILL.mdcore12,329 bytesSKILL.mdcore12,329 bytesSKILL.mdcore12,329 bytesSKILL.mdcore12,329 bytesSKILL.mdcore12,329 bytesSKILL.mdcore12,329 bytesreferences/citation.bibasset1,457 bytesreferences/id_mapping_databases.mddoc7,262 bytesreferences/search_query_fields.mddoc18,437 bytesreferences/sparql_examples.mddoc2,891 bytesscripts/uniprot_tools.pyruns14,440 bytes
Read SKILL.md
# UniProt Database Access
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/uniprot_database_LICENSE.txt does not
already exist in the workspace root directory then (1) prominently notify
the user to check the terms at https://www.uniprot.org/help/license and
https://www.uniprot.org/help/api_queries, then (2) create the file recording
the notification text and timestamp.
## Overview
View the complete source on GitHubuv
When your agent uses it
Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
449 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Setup
Files
SKILL.mdcore1,682 bytes
Read SKILL.md
# uv (Python Package Manager)
`uv` is a fast Python package manager used by Science Skills to run their Python
CLI scripts. Many skills depend on `uv` being installed and on
PATH.
Ensure `uv` is available before running any skill that depends on it.
## Setup
1. Check if `uv` is already available: `uv --version` (or `& uv --version` in
PowerShell). If this succeeds, `uv` is ready — skip the remaining steps.
2. Check whether `uv` is installed at its default location but not on PATH:
View the complete source on GitHubworkflow-skill-creator
When your agent uses it
Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say "make this a skill", "create a skill from what we just did", "package this workflow" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
2,883 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Phase 1: Brainstorming (MANDATORY)
- Phase 2: Skill Design
- Phase 3: Implementation
- Phase 4: Validation
Scripts executed separately
references/cli_script_template.py
Files
SKILL.mdcore12,390 bytesreferences/cli_script_template.pyruns6,940 bytes
Read SKILL.md
# Workflow-to-Skill Distiller
Turns a completed workflow into a reusable agent skill. Specifically, this skill
extracts patterns from an interaction or workflow that **already happened** and
packages them.
> [!CAUTION] **You MUST complete Phase 1 (Brainstorming) before writing any code
> or SKILL.md content.** Skipping brainstorming produces skills that are either
> too rigid or too vague. The brainstorming conversation is the most important
> part of this process.
## Phase 1: Brainstorming (MANDATORY)
Have an **iterative back-and-forth conversation** with the user. Do NOT ask allView the complete source on GitHubSkills included
- alphafold-database-fetch-and-analyze
- alphagenome-atlas-website-links
- alphagenome-single-variant-analysis
- alphagenome-variant-impact-score
- chembl-database
- clinical-trials-database
- clinvar-database
- credentials
- dbsnp-database
- embl-ebi-ols
- encode-ccres-database
- ensembl-database
- foldseek-structural-search
- gnomad-database
- gtex-database
- human-protein-atlas-database
- interpro-database
- jaspar-database
- literature-search-arxiv
- literature-search-biorxiv
- literature-search-europepmc
- literature-search-openalex
- ncbi-sequence-fetch
- openfda-database
- opentargets-database
- pdb-database
- predictingthepast
- protein-sequence-msa
- protein-sequence-similarity-search
- pubchem-database
- pubmed-database
- pymol
- quickgo-database
- reactome-database
- string-database
- ucsc-conservation-and-tfbs
- unibind-database
- uniprot-database
- uv
- workflow-skill-creator
Repository facts
- License
- Apache-2.0
- Created
- May 13, 2026
- Last pushed
- Oct 23, 2026
- Forks
- 398
- Open issues
- 1
- Project activity
- Active
Rank over the last 12 weeks
Now #362 · best #307 · down 43 in 30 days
- #356 on Nov 1
- #359 on Nov 2
- #360 on Nov 3
- #359 on Nov 4
- #361 on Nov 5
- #362 since Nov 6
80 earlier periods
- #298 on Aug 2
- #300 on Aug 7
- #301 on Aug 8
- #298 on Aug 9
- #306 on Aug 10
- #305 on Aug 11
- #304 on Aug 12
- #307 on Aug 13
- #309 on Aug 14
- #307 on Aug 15
- #313 on Aug 16
- #311 on Aug 17
- #317 on Aug 18
- #315 on Aug 19
- #314 on Aug 20
- #316 on Aug 21
- #310 on Aug 22
- #316 on Aug 23
- #318 on Aug 24
- #319 from Aug 25 to Aug 26
- #316 on Aug 27
- #318 on Aug 28
- #317 on Aug 29
- #311 on Aug 30
- #318 on Aug 31
- #322 on Sep 1
- #319 on Sep 2
- #324 on Sep 3
- #318 on Sep 4
- #317 from Sep 5 to Sep 6
- #327 on Sep 7
- #321 on Sep 8
- #317 on Sep 9
- #315 on Sep 10
- #313 on Sep 11
- #314 on Sep 12
- #310 on Sep 13
- #314 on Sep 14
- #315 on Sep 15
- #312 on Sep 16
- #310 from Sep 17 to Sep 18
- #309 on Sep 19
- #317 on Sep 20
- #315 on Sep 21
- #319 on Sep 22
- #315 on Sep 23
- #314 on Sep 24
- #313 on Sep 25
- #309 on Sep 26
- #311 on Sep 27
- #315 on Sep 28
- #316 on Sep 29
- #313 on Sep 30
- #311 on Oct 1
- #315 on Oct 2
- #311 on Oct 3
- #307 on Oct 4
- #315 on Oct 5
- #314 on Oct 6
- #316 on Oct 7
- #319 on Oct 8
- #324 on Oct 9
- #319 on Oct 10
- #321 on Oct 11
- #330 on Oct 12
- #329 on Oct 13
- #330 on Oct 14
- #327 on Oct 15
- #331 on Oct 16
- #328 on Oct 17
- #333 on Oct 18
- #335 on Oct 19
- #336 from Oct 20 to Oct 21
- #337 on Oct 22
- #336 on Oct 23
- #334 on Oct 24
- #344 on Oct 25
- #352 on Oct 28
- #354 on Oct 29
- #357 from Oct 30 to Oct 31
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 2, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 291 notes
skills/alphafold_database_fetch_and_analyze/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphafold_database_fetch_and_analyze/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphafold_database_fetch_and_analyze/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_atlas_website_links/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_atlas_website_links/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_atlas_website_links/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_single_variant_analysis/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_single_variant_analysis/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_single_variant_analysis/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_single_variant_analysis/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_single_variant_analysis/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_variant_impact_score/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_variant_impact_score/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_variant_impact_score/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_variant_impact_score/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_variant_impact_score/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_variant_impact_score/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphagenome_variant_impact_score/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chembl_database/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chembl_database/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 1 dangerous shell commandin 1 file: uv/SKILL.md:37
- 967 network referencesin 145 files: predictingthepast/SKILL.md:27 predictingthepast/scripts/visualize_results.py:5 literature_search_openalex/scripts/openalex_cli.py:5 and 142 more
- No hidden or obfuscated text
- No instruction overrides
- 66 executable scriptsin 66 files: alphafold_database_fetch_and_analyze/scripts/analyze_pae.py:1 alphafold_database_fetch_and_analyze/scripts/analyze_plddt.py:1 alphafold_database_fetch_and_analyze/scripts/fetch_structure.py:1 and 63 more
- 178 references to secretsin 33 files: literature_search_openalex/scripts/openalex_cli.py:98 openfda_database/scripts/openfda_query.py:81 dbsnp_database/scripts/dbsnp_cli.py:57 and 30 more
- No requests to vote in Hot
Show all 1,212 signals by file
skills/alphafold_database_fetch_and_analyze/SKILL.md
- Network accessline 18
.licenses/alphafold_database_fetch_and_analyze_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://alphafold.ebi.ac.uk/, then (2) create the file - Network accessline 19
exist in the workspace root directory then (1) prominently notify the user to check the terms at https://alphafold.ebi.ac.uk/, then (2) create the file recording the notification text and timestamp. - Network accessline 20
to check the terms at https://alphafold.ebi.ac.uk/, then (2) create the file - Network accessline 32
- The user only has a protein name, gene name, or amino acid sequence (no UniProt ID) — ask them to look up the ID on [UniProt](https://www.uniprot.org). - Network accessline 33
UniProt ID) — ask them to look up the ID on [UniProt](https://www.uniprot.org). - The user wants to search for structural homologs (use **Foldseek**). - Network accessline 34
[UniProt](https://www.uniprot.org).
skills/alphafold_database_fetch_and_analyze/references/citation.bib
- Network accessline 1
@ARTICLE{Varadi2022, ABSTRACT = {The AlphaFold Protein Structure Database (AlphaFold DB, https://alphafold.ebi.ac.uk) is an openly accessible, extensive database of high-accuracy protein-structure predictions. Powered by AlphaFold v2.0 of - Network accessline 2
ABSTRACT = {The AlphaFold Protein Structure Database (AlphaFold DB, https://alphafold.ebi.ac.uk) is an openly accessible, extensive database of high-accuracy protein-structure predictions. Powered by AlphaFold v2.0 of DeepMind, it has enabl - Network accessline 3
AUTHOR = {Varadi, Mihaly and Anyango, Stephen and Deshpande, Mandar and Nair, Sreenath and Natassia, Cindy and Yordanova, Galabina and Yuan, David and Stroe, Oana and Wood, Gemma and Laydon, Agata and Žídek, Augustin and Green, Tim and Tuny - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkab1061}, - Network accessline 5
DATE = {2022-01}, DOI = {10.1093/nar/gkab1061}, EPRINT = {https://academic.oup.com/nar/article-pdf/50/D1/D439/43502749/gkab1061.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkab1061}, EPRINT = {https://academic.oup.com/nar/article-pdf/50/D1/D439/43502749/gkab1061.pdf}, ISSN = {0305-1048}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/50/D1/D439/43502749/gkab1061.pdf}, - Network accessline 16
@ARTICLE{Varadi2024, ABSTRACT = {The AlphaFold Database Protein Structure Database (AlphaFold DB, https://alphafold.ebi.ac.uk) has significantly impacted structural biology by amassing over 214 million predicted protein structures, expand - Network accessline 17
ABSTRACT = {The AlphaFold Database Protein Structure Database (AlphaFold DB, https://alphafold.ebi.ac.uk) has significantly impacted structural biology by amassing over 214 million predicted protein structures, expanding from the initial 30 - Network accessline 18
AUTHOR = {Varadi, Mihaly and Bertoni, Damian and Magana, Paulyna and Paramval, Urmila and Pidruchna, Ivanna and Radhakrishnan, Malarvizhi and Tsenkov, Maxim and Nair, Sreenath and Mirdita, Milot and Yeo, Jingi and Kovalevskiy, Oleg and Tuny - Network accessline 19
URL = {https://doi.org/10.1093/nar/gkad1011}, - Network accessline 20
DATE = {2024-01}, DOI = {10.1093/nar/gkad1011}, EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D368/55039845/gkad1011.pdf}, - Network accessline 21
DOI = {10.1093/nar/gkad1011}, EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D368/55039845/gkad1011.pdf}, ISSN = {0305-1048}, - Network accessline 22
EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D368/55039845/gkad1011.pdf}, - Network accessline 32
ABSTRACT = {Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort1--4, the structures of around 100,000 unique proteins have b - Network accessline 33
AUTHOR = {Jumper, John and Evans, Richard and Pritzel, Alexander and Green, Tim and Figurnov, Michael and Ronneberger, Olaf and Tunyasuvunakool, Kathryn and Bates, Russ and Žídek, Augustin and Potapenko, Anna and Bridgland, Alex and Meyer, - Network accessline 34
URL = {https://doi.org/10.1038/s41586-021-03819-2}, - Network accessline 46
ABSTRACT = {Protein structures can provide invaluable information, both for reasoning about biological processes and for enabling interventions such as structure-based drug development or targeted mutagenesis. After decades of effort, 17{\% - Network accessline 47
AUTHOR = {Tunyasuvunakool, Kathryn and Adler, Jonas and Wu, Zachary and Green, Tim and Zielinski, Michal and Žídek, Augustin and Bridgland, Alex and Cowie, Andrew and Meyer, Clemens and Laydon, Agata and Velankar, Sameer and Kleywegt, Gerar - Network accessline 48
URL = {https://doi.org/10.1038/s41586-021-03828-1},
skills/alphafold_database_fetch_and_analyze/scripts/analyze_pae.py
skills/alphafold_database_fetch_and_analyze/scripts/analyze_plddt.py
skills/alphafold_database_fetch_and_analyze/scripts/fetch_structure.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 30
CLIENT = http_client.HttpClient("https://alphafold.ebi.ac.uk", qps=1.0) - Network accessline 35
uniprot_id = uniprot_id.strip().upper() api_url = f"https://alphafold.ebi.ac.uk/api/prediction/{uniprot_id}" - Network accessline 36
api_url = f"https://alphafold.ebi.ac.uk/api/prediction/{uniprot_id}"
skills/alphagenome_atlas_website_links/SKILL.md
- Network accessline 17
Construct and validate deep-links for the AlphaGenome Atlas web application (`https://deepmind.google.com/science/alphagenome/atlas`). - Network accessline 18
(`https://deepmind.google.com/science/alphagenome/atlas`). - Network accessline 20
Base URL: `https://deepmind.google.com/science/alphagenome/atlas` - Network accessline 23
> presenting, discussing, or scoring genetic variants, you **MUST always provide > clickable deep-links to the > [AlphaGenome Atlas](https://deepmind.google.com/science/alphagenome/atlas)**. - Network accessline 24
> clickable deep-links to the > [AlphaGenome Atlas](https://deepmind.google.com/science/alphagenome/atlas)**. > Use `scripts/alphagenome_atlas_links.py` to automate link and table - Network accessline 25
> [AlphaGenome Atlas](https://deepmind.google.com/science/alphagenome/atlas)**. - Network accessline 196
* **Route**: `https://deepmind.google.com/science/alphagenome/atlas/track-predictions` - Network accessline 197
`https://deepmind.google.com/science/alphagenome/atlas/track-predictions`
skills/alphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 17
Constructs validated deep-links and multi-modality Ref vs. Alt track predictions for the AlphaGenome Atlas web application (https://deepmind.google.com/science/alphagenome/atlas). - Network accessline 19
(https://deepmind.google.com/science/alphagenome/atlas). - Network accessline 44
BASE_ATLAS_URL = "https://deepmind.google.com/science/alphagenome/atlas" - Access to secretsline 402
[Credential-related source omitted] - Access to secretsline 403
[Credential-related source omitted] - Access to secretsline 405
[Credential-related source omitted] - Access to secretsline 406
[Credential-related source omitted] - Access to secretsline 408
[Credential-related source omitted] - Access to secretsline 412
[Credential-related source omitted] - Network accessline 413
" the 'credentials' skill for the safe credentials protocol,\n or" " register for an API key at" " https://deepmind.google.com/science/alphagenome/.\n", - Network accessline 414
" register for an API key at" " https://deepmind.google.com/science/alphagenome/.\n", file=sys.stderr, - Network accessline 415
" https://deepmind.google.com/science/alphagenome/.\n", - Access to secretsline 420
[Credential-related source omitted] - Network accessline 423
GTF_URL = ( "https://storage.googleapis.com/alphagenome/reference/gencode/" - Network accessline 424
"https://storage.googleapis.com/alphagenome/reference/gencode/" - Access to secretsline 431
[Credential-related source omitted]
skills/alphagenome_single_variant_analysis/SKILL.md
- Network accessline 21
.licenses/alphagenome_single_variant_analysis_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://deepmind.google.com/science/alphagenome/, then - Network accessline 22
exist in the workspace root directory then (1) prominently notify the user to check the terms at https://deepmind.google.com/science/alphagenome/, then (2) create the file recording the notification text and timestamp. - Network accessline 23
to check the terms at https://deepmind.google.com/science/alphagenome/, then - Access to secretsline 27
[Credential-related source omitted] - Network accessline 29
You can register for a key at https://deepmind.google.com/science/alphagenome/. - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Network accessline 111
instructions in [Prerequisites](#prerequisites). - **Registry Authentication Error (401)**: If `uv` fails with 401 Unauthorized for a private registry, set `UV_INDEX_URL=https://pypi.org/simple` before - Network accessline 112
- **Registry Authentication Error (401)**: If `uv` fails with 401 Unauthorized for a private registry, set `UV_INDEX_URL=https://pypi.org/simple` before running the script. - Network accessline 113
for a private registry, set `UV_INDEX_URL=https://pypi.org/simple` before - Access to secretsline 169
[Credential-related source omitted] - Access to secretsline 170
[Credential-related source omitted] - Access to secretsline 173
[Credential-related source omitted]
skills/alphagenome_single_variant_analysis/docs/alphagenome-api.md
skills/alphagenome_single_variant_analysis/scripts/analyze_ism.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Access to secretsline 184
[Credential-related source omitted] - Access to secretsline 185
[Credential-related source omitted] - Access to secretsline 186
[Credential-related source omitted] - Access to secretsline 190
[Credential-related source omitted] - Access to secretsline 274
[Credential-related source omitted]
skills/alphagenome_single_variant_analysis/scripts/generate_ontology_mapping.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Access to secretsline 123
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted] - Access to secretsline 126
[Credential-related source omitted] - Access to secretsline 128
[Credential-related source omitted] - Access to secretsline 129
[Credential-related source omitted] - Access to secretsline 134
[Credential-related source omitted] - Access to secretsline 163
[Credential-related source omitted]
skills/alphagenome_single_variant_analysis/scripts/interpret_splicing.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Access to secretsline 114
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted] - Access to secretsline 118
[Credential-related source omitted] - Access to secretsline 271
[Credential-related source omitted]
skills/alphagenome_single_variant_analysis/scripts/lookup_gene_info.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 49
GTF_URL = ( 'https://storage.googleapis.com/alphagenome/reference/gencode/' - Network accessline 50
'https://storage.googleapis.com/alphagenome/reference/gencode/' - Access to secretsline 57
[Credential-related source omitted] - Access to secretsline 266
[Credential-related source omitted]
skills/alphagenome_single_variant_analysis/scripts/resolve_ontology_terms.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Access to secretsline 125
[Credential-related source omitted]
skills/alphagenome_single_variant_analysis/scripts/visualize_genome_tracks.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 57
GTF_URL = ( 'https://storage.googleapis.com/alphagenome/reference/gencode/' - Network accessline 58
'https://storage.googleapis.com/alphagenome/reference/gencode/' - Access to secretsline 65
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Access to secretsline 76
[Credential-related source omitted] - Access to secretsline 77
[Credential-related source omitted] - Access to secretsline 79
[Credential-related source omitted] - Access to secretsline 357
[Credential-related source omitted]
skills/alphagenome_single_variant_analysis/scripts/visualize_variant_effects.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 71
GTF_URL = ( 'https://storage.googleapis.com/alphagenome/reference/gencode/' - Network accessline 72
'https://storage.googleapis.com/alphagenome/reference/gencode/' - Access to secretsline 79
[Credential-related source omitted] - Access to secretsline 1040
[Credential-related source omitted] - Access to secretsline 1041
[Credential-related source omitted] - Access to secretsline 1042
[Credential-related source omitted] - Access to secretsline 1045
[Credential-related source omitted] - Access to secretsline 1156
[Credential-related source omitted]
skills/alphagenome_variant_impact_score/SKILL.md
- Access to secretsline 192
[Credential-related source omitted] - Access to secretsline 207
[Credential-related source omitted] - Access to secretsline 208
[Credential-related source omitted] - Network accessline 332
> single variant query, a ranked candidate table, or a genomic region scan), you > **MUST always provide a clickable deep-link to the > [AlphaGenome Atlas](https://deepmind.google.com/science/alphagenome/atlas)** - Network accessline 333
> **MUST always provide a clickable deep-link to the > [AlphaGenome Atlas](https://deepmind.google.com/science/alphagenome/atlas)** > for each variant. - Network accessline 334
> [AlphaGenome Atlas](https://deepmind.google.com/science/alphagenome/atlas)**
skills/alphagenome_variant_impact_score/scripts/alphagenome_atlas_avi.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 63
_ATLAS_TRACK_PREDICTIONS_URL = ( 'https://deepmind.google.com/science/alphagenome/atlas/track-predictions' - Network accessline 64
'https://deepmind.google.com/science/alphagenome/atlas/track-predictions' - Access to secretsline 541
[Credential-related source omitted] - Access to secretsline 542
[Credential-related source omitted] - Access to secretsline 543
[Credential-related source omitted] - Access to secretsline 545
[Credential-related source omitted] - Access to secretsline 546
[Credential-related source omitted] - Access to secretsline 548
[Credential-related source omitted] - Network accessline 875
with pysam.VariantFile(output_path, 'w', header=vcf_in.header) as vcf_out: for record in vcf_in.fetch(): - Network accessline 876
for record in vcf_in.fetch(): - Network accessline 1576
GTF_URL = ( 'https://storage.googleapis.com/alphagenome/reference/gencode/' - Network accessline 1577
'https://storage.googleapis.com/alphagenome/reference/gencode/' - Access to secretsline 1584
[Credential-related source omitted] - Access to secretsline 2017
[Credential-related source omitted]
skills/chembl_database/SKILL.md
- Network accessline 16
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://chembl.gitbook.io/chembl-interface-documentation/about, then (2) - Network accessline 17
the user to check the terms at https://chembl.gitbook.io/chembl-interface-documentation/about, then (2) create the file recording the notification text and timestamp. - Network accessline 18
https://chembl.gitbook.io/chembl-interface-documentation/about, then (2)
skills/chembl_database/references/api_endpoints.md
- Network accessline 3
Base URL: `https://www.ebi.ac.uk/chembl/api/data`
skills/chembl_database/references/citation.bib
- Network accessline 1
@ARTICLE{Zdrazil2024, ABSTRACT = {ChEMBL (https://www.ebi.ac.uk/chembl/) is a manually curated, high-quality, large-scale, open, FAIR and Global Core Biodata Resource of bioactive molecules with drug-like properties, previously described - Network accessline 2
ABSTRACT = {ChEMBL (https://www.ebi.ac.uk/chembl/) is a manually curated, high-quality, large-scale, open, FAIR and Global Core Biodata Resource of bioactive molecules with drug-like properties, previously described in the 2012, 2014, 2017 - Network accessline 3
AUTHOR = {Zdrazil, Barbara and Felix, Eloy and Hunter, Fiona and Manners, Emma J and Blackshaw, James and Corbett, Sybilla and de Veij, Marleen and Ioannidis, Harris and Lopez, David Mendez and Mosquera, Juan F and Magarinos, Maria Paula an - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkad1004}, - Network accessline 5
DATE = {2024-01}, DOI = {10.1093/nar/gkad1004}, EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D1180/55040046/gkad1004.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkad1004}, EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D1180/55040046/gkad1004.pdf}, ISSN = {0305-1048}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D1180/55040046/gkad1004.pdf}, - Network accessline 16
@ARTICLE{Davies2015, ABSTRACT = {ChEMBL is now a well-established resource in the fields of drug discovery and medicinal chemistry research. The ChEMBL database curates and stores standardized bioactivity, molecule, target and drug data e - Network accessline 17
ABSTRACT = {ChEMBL is now a well-established resource in the fields of drug discovery and medicinal chemistry research. The ChEMBL database curates and stores standardized bioactivity, molecule, target and drug data extracted from multiple - Network accessline 18
AUTHOR = {Davies, Mark and Nowotka, Michał and Papadatos, George and Dedman, Nathan and Gaulton, Anna and Atkinson, Francis and Bellis, Louisa and Overington, John P.}, URL = {https://doi.org/10.1093/nar/gkv352}, DATE = {2015-07}, - Network accessline 19
URL = {https://doi.org/10.1093/nar/gkv352}, - Network accessline 20
DATE = {2015-07}, DOI = {10.1093/nar/gkv352}, EPRINT = {https://academic.oup.com/nar/article-pdf/43/W1/W612/17435802/gkv352.pdf}, - Network accessline 21
DOI = {10.1093/nar/gkv352}, EPRINT = {https://academic.oup.com/nar/article-pdf/43/W1/W612/17435802/gkv352.pdf}, ISSN = {0305-1048}, - Network accessline 22
EPRINT = {https://academic.oup.com/nar/article-pdf/43/W1/W612/17435802/gkv352.pdf},
skills/chembl_database/scripts/chembl_api.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 40
BASE_URL = "https://www.ebi.ac.uk/chembl/api/data" - Network accessline 117
data["_license_notice"] = ( "Data from the ChEMBL Database. Please review the licensing terms at" " https://www.ebi.ac.uk/chembl/" - Network accessline 118
"Data from the ChEMBL Database. Please review the licensing terms at" " https://www.ebi.ac.uk/chembl/" ) - Network accessline 119
" https://www.ebi.ac.uk/chembl/"
skills/clinical_trials_database/SKILL.md
- Network accessline 17
2. **User Notification**: If .licenses/clinical_trials_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://clinicaltrials.gov/, then (2) - Network accessline 18
does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://clinicaltrials.gov/, then (2) create the file recording the notification text and timestamp. - Network accessline 19
notify the user to check the terms at https://clinicaltrials.gov/, then (2)
skills/clinical_trials_database/scripts/clinical_trials_api.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 36
BASE_URL = "https://clinicaltrials.gov/api/v2"
skills/clinvar_database/SKILL.md
- Network accessline 15
2. **User Notification**: If .licenses/clinvar_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ncbi.nlm.nih.gov/clinvar/, then - Network accessline 16
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ncbi.nlm.nih.gov/clinvar/, then (2) create the file recording the notification text and timestamp. - Network accessline 17
the user to check the terms at https://www.ncbi.nlm.nih.gov/clinvar/, then - Access to secretsline 21
[Credential-related source omitted] - Network accessline 22
requests/second. The skill works without it, but a key is recommended if the user plans many queries or encounters a 429 error. You can register for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** - Network accessline 23
user plans many queries or encounters a 429 error. You can register for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** use the safe credentials protocol in the `credentials` skill to check for - Network accessline 24
key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** - Access to secretsline 85
[Credential-related source omitted] - Network accessline 335
You can register for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** use the safe - Network accessline 336
https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** use the safe - Access to secretsline 359
[Credential-related source omitted]
skills/clinvar_database/scripts/clinvar_api.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 59
BASE_URL = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/' - Access to secretsline 63
[Credential-related source omitted] - Access to secretsline 64
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Access to secretsline 68
[Credential-related source omitted] - Access to secretsline 89
[Credential-related source omitted] - Access to secretsline 90
[Credential-related source omitted] - Network accessline 96
try: resp = self.client.fetch(full_url, timeout=DEFAULT_TIMEOUT_SECONDS) - Network accessline 97
resp = self.client.fetch(full_url, timeout=DEFAULT_TIMEOUT_SECONDS) - Network accessline 103
' INSTRUCTION: Pause execution and inform the user that an NCBI API' ' Key is required to increase the rate limit, providing the URL' ' https://www.ncbi.nlm.nih.gov/clinvar/docs/api_http/ for' - Network accessline 104
' Key is required to increase the rate limit, providing the URL' ' https://www.ncbi.nlm.nih.gov/clinvar/docs/api_http/ for' ' instructions on how to obtain one. The user will need to set the' - Network accessline 105
' https://www.ncbi.nlm.nih.gov/clinvar/docs/api_http/ for' - Access to secretsline 107
[Credential-related source omitted] - Access to secretsline 648
[Credential-related source omitted]
skills/credentials/SKILL.md
skills/dbsnp_database/SKILL.md
- Network accessline 17
2. **User Notification**: If .licenses/dbsnp_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ncbi.nlm.nih.gov/snp/, then (2) - Network accessline 18
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ncbi.nlm.nih.gov/snp/, then (2) create the file recording the notification text and timestamp. - Network accessline 19
the user to check the terms at https://www.ncbi.nlm.nih.gov/snp/, then (2) - Access to secretsline 23
[Credential-related source omitted] - Network accessline 24
requests/second. The skill works without it, but a key is recommended if the user plans many queries or encounters a 429 error. You can register for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** - Network accessline 25
user plans many queries or encounters a 429 error. You can register for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** use the safe credentials protocol in the `credentials` skill to check for - Network accessline 26
key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** - Network accessline 32
- **Use the Wrapper**: ALWAYS execute the provided wrapper script `scripts/dbsnp_cli.py` to query the database rather than constructing custom HTTP or curl requests. The script automatically handles rate limiting, - Network accessline 33
`scripts/dbsnp_cli.py` to query the database rather than constructing custom HTTP or curl requests. The script automatically handles rate limiting, retries, and JSON parsing. - Network accessline 34
HTTP or curl requests. The script automatically handles rate limiting, - Network accessline 302
You can register for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** use the safe - Network accessline 303
https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** use the safe
skills/dbsnp_database/references/api-notes.md
skills/dbsnp_database/scripts/dbsnp_cli.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 42
_VARIATION_BASE_URL = "https://api.ncbi.nlm.nih.gov" - Network accessline 43
_EUTILS_BASE_URL = "https://eutils.ncbi.nlm.nih.gov" - Access to secretsline 57
[Credential-related source omitted] - Access to secretsline 58
[Credential-related source omitted] - Access to secretsline 71
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted] - Access to secretsline 110
[Credential-related source omitted] - Access to secretsline 111
[Credential-related source omitted] - Access to secretsline 113
[Credential-related source omitted] - Network accessline 126
"AGENT INSTRUCTION: Pause execution and inform the user that an NCBI " "API Key is required. Direct them to " "https://ncbiinsights.ncbi.nlm.nih.gov/2017/11/02/" - Network accessline 127
"API Key is required. Direct them to " "https://ncbiinsights.ncbi.nlm.nih.gov/2017/11/02/" "new-api-keys-for-the-e-utilities/ and ask them to set the " - Network accessline 128
"https://ncbiinsights.ncbi.nlm.nih.gov/2017/11/02/" - Access to secretsline 130
[Credential-related source omitted] - Access to secretsline 554
[Credential-related source omitted]
skills/embl_ebi_ols/SKILL.md
- Network accessline 18
2. **User Notification**: If .licenses/embl_ebi_ols_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/ols4/api-docs, then (2) - Network accessline 19
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/ols4/api-docs, then (2) create the file recording the notification text and timestamp. - Network accessline 20
the user to check the terms at https://www.ebi.ac.uk/ols4/api-docs, then (2)
skills/embl_ebi_ols/references/api_reference.md
- Network accessline 3
Base URL: `https://www.ebi.ac.uk/ols4/api` - Network accessline 65
The corresponding IRI is typically: `http://purl.obolibrary.org/obo/PREFIX_NUMBER` (e.g., - Network accessline 66
`http://purl.obolibrary.org/obo/PREFIX_NUMBER` (e.g., - Network accessline 67
`http://purl.obolibrary.org/obo/GO_0005634`).
skills/embl_ebi_ols/references/citation.bib
- Network accessline 10
@ARTICLE{McLaughlin2025, ABSTRACT = {The Ontology Lookup Service (OLS) is an open source search engine for ontologies which is used extensively in the bioinformatics and chemistry communities to annotate biological and biomedical data wit - Network accessline 11
ABSTRACT = {The Ontology Lookup Service (OLS) is an open source search engine for ontologies which is used extensively in the bioinformatics and chemistry communities to annotate biological and biomedical data with ontology terms. Recently, - Network accessline 12
AUTHOR = {McLaughlin, James and Lagrimas, Josh and Iqbal, Haider and Parkinson, Helen and Harmse, Henriette}, URL = {https://doi.org/10.1093/bioinformatics/btaf279}, DATE = {2025-05}, - Network accessline 13
URL = {https://doi.org/10.1093/bioinformatics/btaf279}, - Network accessline 14
DATE = {2025-05}, DOI = {10.1093/bioinformatics/btaf279}, EPRINT = {https://academic.oup.com/bioinformatics/article-pdf/41/5/btaf279/63054843/btaf279.pdf}, - Network accessline 15
DOI = {10.1093/bioinformatics/btaf279}, EPRINT = {https://academic.oup.com/bioinformatics/article-pdf/41/5/btaf279/63054843/btaf279.pdf}, ISSN = {1367-4811}, - Network accessline 16
EPRINT = {https://academic.oup.com/bioinformatics/article-pdf/41/5/btaf279/63054843/btaf279.pdf},
skills/embl_ebi_ols/scripts/get_individual.py
skills/embl_ebi_ols/scripts/get_ontology.py
skills/embl_ebi_ols/scripts/get_property.py
skills/embl_ebi_ols/scripts/get_stats.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 42
url = "https://www.ebi.ac.uk/ols4/api/v2/stats"
skills/embl_ebi_ols/scripts/get_term.py
skills/embl_ebi_ols/scripts/ols_utils.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 37
RATE_LIMIT_DELAY = 0.2 MAX_RETRIES = 10 BASE_URL = "https://www.ebi.ac.uk/ols4/api" - Network accessline 38
MAX_RETRIES = 10 BASE_URL = "https://www.ebi.ac.uk/ols4/api" CLIENT = http_client.HttpClient(BASE_URL, qps=5.0) - Network accessline 39
BASE_URL = "https://www.ebi.ac.uk/ols4/api" - Network accessline 79
return "http://purl.obolibrary.org/obo/" + obo_id.replace(":", "_")
skills/embl_ebi_ols/scripts/search_ols.py
skills/embl_ebi_ols/scripts/suggest_ols.py
skills/encode_ccres_database/SKILL.md
- Network accessline 22
not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.encodeproject.org/help/rest-api/, then (2) create the file - Network accessline 23
notify the user to check the terms at https://www.encodeproject.org/help/rest-api/, then (2) create the file recording the notification text and timestamp. - Network accessline 24
https://www.encodeproject.org/help/rest-api/, then (2) create the file
skills/encode_ccres_database/references/citation.bib
- Network accessline 4
URL = {https://doi.org/10.1038/nature11247}, - Network accessline 26
@ARTICLE{Luo2020, ABSTRACT = {The Encyclopedia of DNA Elements (ENCODE) is an ongoing collaborative research project aimed at identifying all the functional elements in the human and mouse genomes. Data generated by the ENCODE consortium - Network accessline 27
ABSTRACT = {The Encyclopedia of DNA Elements (ENCODE) is an ongoing collaborative research project aimed at identifying all the functional elements in the human and mouse genomes. Data generated by the ENCODE consortium are freely accessibl - Network accessline 28
AUTHOR = {Luo, Yunhai and Hitz, Benjamin C and Gabdank, Idan and Hilton, Jason A and Kagda, Meenakshi S and Lam, Bonita and Myers, Zachary and Sud, Paul and Jou, Jennifer and Lin, Khine and Baymuradov, Ulugbek K and Graham, Keenan and Litto - Network accessline 29
URL = {https://doi.org/10.1093/nar/gkz1062}, - Network accessline 30
DATE = {2020-01}, DOI = {10.1093/nar/gkz1062}, EPRINT = {https://academic.oup.com/nar/article-pdf/48/D1/D882/32874907/gkz1062.pdf}, - Network accessline 31
DOI = {10.1093/nar/gkz1062}, EPRINT = {https://academic.oup.com/nar/article-pdf/48/D1/D882/32874907/gkz1062.pdf}, ISSN = {0305-1048}, - Network accessline 32
EPRINT = {https://academic.oup.com/nar/article-pdf/48/D1/D882/32874907/gkz1062.pdf},
skills/encode_ccres_database/references/graphql_schema.md
skills/encode_ccres_database/scripts/encode_portal_api.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 29
BASE_URL = "https://www.encodeproject.org"
skills/encode_ccres_database/scripts/screen_api.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 35
API_URL = "https://factorbook.api.wenglab.org/graphql" - Network accessline 38
qps=10, default_headers={ "Origin": "https://screen-v2.wenglab.org", - Network accessline 39
default_headers={ "Origin": "https://screen-v2.wenglab.org", "Referer": "https://screen-v2.wenglab.org/", - Network accessline 40
"Origin": "https://screen-v2.wenglab.org", - Network accessline 41
"Referer": "https://screen-v2.wenglab.org/",
skills/ensembl_database/SKILL.md
- Network accessline 17
2. **User Notification**: If .licenses/ensembl_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://useast.ensembl.org/index.html and - Network accessline 18
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://useast.ensembl.org/index.html and https://github.com/Ensembl/ensembl-rest/wiki, then (2) create the file - Network accessline 19
the user to check the terms at https://useast.ensembl.org/index.html and - Network accessline 20
https://github.com/Ensembl/ensembl-rest/wiki, then (2) create the file
skills/ensembl_database/references/citation.bib
- Network accessline 1
@ARTICLE{Harrison2024, ABSTRACT = {Ensembl (https://www.ensembl.org) is a freely available genomic resource that has produced high-quality annotations, tools, and services for vertebrates and model organisms for more than two decades. In - Network accessline 2
ABSTRACT = {Ensembl (https://www.ensembl.org) is a freely available genomic resource that has produced high-quality annotations, tools, and services for vertebrates and model organisms for more than two decades. In recent years, there has b - Network accessline 3
AUTHOR = {Harrison, Peter W and Amode, M Ridwan and Austine-Orimoloye, Olanrewaju and Azov, Andrey G and Barba, Matthieu and Barnes, If and Becker, Arne and Bennett, Ruth and Berry, Andrew and Bhai, Jyothish and Bhurji, Simarpreet Kaur and - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkad1049}, - Network accessline 5
DATE = {2024-01}, DOI = {10.1093/nar/gkad1049}, EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D891/55040594/gkad1049.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkad1049}, EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D891/55040594/gkad1049.pdf}, ISSN = {0305-1048}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D891/55040594/gkad1049.pdf},
skills/ensembl_database/references/ensembl_rest_api_reference.md
- Network accessline 3
This document provides a concise reference for the Ensembl REST API (`https://rest.ensembl.org`). Use it to build custom queries when the - Network accessline 4
(`https://rest.ensembl.org`). Use it to build custom queries when the - Network accessline 9
- **Base URL:** `https://rest.ensembl.org` (GRCh38). For GRCh37: - Network accessline 10
`https://grch37.rest.ensembl.org`
skills/ensembl_database/scripts/ensembl_api.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 38
BASE_URL = "https://rest.ensembl.org" - Network accessline 39
GRCH37_URL = "https://grch37.rest.ensembl.org"
skills/foldseek_structural_search/SKILL.md
- Network accessline 15
2. **User Notification**: If .licenses/foldseek_structural_search_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://search.foldseek.com/search and - Network accessline 16
does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://search.foldseek.com/search and https://github.com/steineggerlab/foldseek, then (2) create the file - Network accessline 17
notify the user to check the terms at https://search.foldseek.com/search and - Network accessline 18
https://github.com/steineggerlab/foldseek, then (2) create the file
skills/foldseek_structural_search/scripts/search.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 49
CLIENT = http_client.HttpClient("https://search.foldseek.com", qps=1) - Network accessline 110
file_path = args.input_file output_path = args.output ticket_url = "https://search.foldseek.com/api/ticket" - Network accessline 112
ticket_url = "https://search.foldseek.com/api/ticket" - Network accessline 179
"[*] Fetching results (this might take a moment for large databases)...\n" ) result_url = f"https://search.foldseek.com/api/result/{ticket_id}/0" - Network accessline 180
) result_url = f"https://search.foldseek.com/api/result/{ticket_id}/0" res = CLIENT.fetch_json(result_url, headers=headers, timeout=120) - Network accessline 181
result_url = f"https://search.foldseek.com/api/result/{ticket_id}/0"
skills/gnomad_database/SKILL.md
- Network accessline 18
2. **User Notification**: If .licenses/gnomad_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://gnomad.broadinstitute.org/policies - Network accessline 19
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://gnomad.broadinstitute.org/policies and https://gnomad.broadinstitute.org/data#api, then (2) create the file - Network accessline 20
the user to check the terms at https://gnomad.broadinstitute.org/policies - Network accessline 21
and https://gnomad.broadinstitute.org/data#api, then (2) create the file - Network accessline 72
Further documentation on the data: https://gnomad.broadinstitute.org/data#api - Network accessline 73
More general database documentation: https://gnomad.broadinstitute.org/help
skills/gnomad_database/references/citation.bib
- Network accessline 3
AUTHOR = {Karczewski, Konrad J. and Francioli, Laurent C. and Tiao, Grace and Cummings, Beryl B. and Alföldi, Jessica and Wang, Qingbo and Collins, Ryan L. and Laricchia, Kristen M. and Ganna, Andrea and Birnbaum, Daniel P. and Gauthier, La - Network accessline 4
URL = {https://doi.org/10.1038/s41586-020-2308-7},
skills/gnomad_database/scripts/get_gene_constraint.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 36
CLIENT = http_client.HttpClient("https://gnomad.broadinstitute.org", qps=0.1666) - Network accessline 44
url = "https://gnomad.broadinstitute.org/api"
skills/gnomad_database/scripts/get_variant_frequency.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 32
CLIENT = http_client.HttpClient("https://gnomad.broadinstitute.org", qps=0.1666) - Network accessline 37
url = "https://gnomad.broadinstitute.org/api" - Network accessline 77
url = "https://gnomad.broadinstitute.org/api"
skills/gnomad_database/scripts/search_variants.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 32
CLIENT = http_client.HttpClient("https://gnomad.broadinstitute.org", qps=0.1666) - Network accessline 42
url = "https://gnomad.broadinstitute.org/api" - Network accessline 118
url = "https://gnomad.broadinstitute.org/api"
skills/gtex_database/SKILL.md
- Network accessline 20
2. **User Notification**: If .licenses/gtex_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://gtexportal.org/home/license and - Network accessline 21
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://gtexportal.org/home/license and https://gtexportal.org/home/documentationPage#gtexApi, then (2) create the - Network accessline 22
the user to check the terms at https://gtexportal.org/home/license and - Network accessline 23
https://gtexportal.org/home/documentationPage#gtexApi, then (2) create the
skills/gtex_database/references/citation.bib
- Network accessline 3
AUTHOR = {{The GTEx Consortium} and Aguet, François and Anand, Shankara and Ardlie, Kristin G. and Gabriel, Stacey and Getz, Gad A. and Graubert, Aaron and Hadley, Kane and Handsaker, Robert E. and Huang, Katherine H. and Kashin, Seva and L - Network accessline 4
URL = {https://www.science.org/doi/abs/10.1126/science.aaz1776}, - Network accessline 5
DATE = {2020}, DOI = {10.1126/science.aaz1776}, EPRINT = {https://www.science.org/doi/pdf/10.1126/science.aaz1776}, - Network accessline 6
DOI = {10.1126/science.aaz1776}, EPRINT = {https://www.science.org/doi/pdf/10.1126/science.aaz1776}, JOURNALTITLE = {Science}, - Network accessline 7
EPRINT = {https://www.science.org/doi/pdf/10.1126/science.aaz1776},
skills/gtex_database/scripts/gtex_cli.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 35
BASE_URL = 'https://gtexportal.org/api/v2'
skills/human_protein_atlas_database/SKILL.md
- Network accessline 23
does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.proteinatlas.org/about/licence, then (2) create the file - Network accessline 24
notify the user to check the terms at https://www.proteinatlas.org/about/licence, then (2) create the file recording the notification text and timestamp. - Network accessline 25
https://www.proteinatlas.org/about/licence, then (2) create the file
skills/human_protein_atlas_database/references/citation.bib
- Network accessline 2
ABSTRACT = {Sequencing the human genome gave new insights into human biology and disease. However, the ultimate goal is to understand the dynamic expression of each of the approximately 20,000 protein-coding genes and the function of each p - Network accessline 3
AUTHOR = {Uhlén, Mathias and Fagerberg, Linn and Hallström, Björn M. and Lindskog, Cecilia and Oksvold, Per and Mardinoglu, Adil and Sivertsson, Åsa and Kampf, Caroline and Sjöstedt, Evelina and Asplund, Anna and Olsson, IngMarie and Edlund - Network accessline 4
URL = {https://www.science.org/doi/abs/10.1126/science.1260419}, - Network accessline 5
DATE = {2015}, DOI = {10.1126/science.1260419}, EPRINT = {https://www.science.org/doi/pdf/10.1126/science.1260419}, - Network accessline 6
DOI = {10.1126/science.1260419}, EPRINT = {https://www.science.org/doi/pdf/10.1126/science.1260419}, JOURNALTITLE = {Science}, - Network accessline 7
EPRINT = {https://www.science.org/doi/pdf/10.1126/science.1260419},
skills/human_protein_atlas_database/scripts/hpa_cli.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 35
BASE_URL = 'https://www.proteinatlas.org/' - Network accessline 89
# The XML namespace is usually specified, e.g., # xmlns="http://www.proteinatlas.org/search/download/proteinatlas.xsd" - Network accessline 90
# xmlns="http://www.proteinatlas.org/search/download/proteinatlas.xsd"
skills/interpro_database/SKILL.md
- Network accessline 18
2. **User Notification**: If .licenses/interpro_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/interpro/ and - Network accessline 19
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/interpro/ and https://www.ebi.ac.uk/about/terms-of-use/, then (2) create the file - Network accessline 20
the user to check the terms at https://www.ebi.ac.uk/interpro/ and - Network accessline 21
https://www.ebi.ac.uk/about/terms-of-use/, then (2) create the file
skills/interpro_database/references/api_reference.md
- Network accessline 4
for the InterPro API endpoints, based on the official InterPro Swagger documentation (https://www.ebi.ac.uk/interpro/api/static_files/interpro7-swagger.yml) These - Network accessline 5
documentation (https://www.ebi.ac.uk/interpro/api/static_files/interpro7-swagger.yml) These parameters can be passed into the `query_params` dictionary in - Network accessline 6
(https://www.ebi.ac.uk/interpro/api/static_files/interpro7-swagger.yml) These
skills/interpro_database/references/citation.bib
- Network accessline 1
@ARTICLE{Blum2025, ABSTRACT = {InterPro (https://www.ebi.ac.uk/interpro) is a freely accessible resource for the classification of protein sequences into families. It integrates predictive models, known as signatures, from multiple member - Network accessline 2
ABSTRACT = {InterPro (https://www.ebi.ac.uk/interpro) is a freely accessible resource for the classification of protein sequences into families. It integrates predictive models, known as signatures, from multiple member databases to classif - Network accessline 3
AUTHOR = {Blum, Matthias and Andreeva, Antonina and Florentino, Laise Cavalcanti and Chuguransky, Sara Rocio and Grego, Tiago and Hobbs, Emma and Pinto, Beatriz Lazaro and Orr, Ailsa and Paysan-Lafosse, Typhaine and Ponamareva, Irina and Sa - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkae1082}, - Network accessline 5
DATE = {2025-01}, DOI = {10.1093/nar/gkae1082}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D444/60766178/gkae1082.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkae1082}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D444/60766178/gkae1082.pdf}, ISSN = {1362-4962}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D444/60766178/gkae1082.pdf},
skills/interpro_database/references/example_responses.tsv
- Network accessline 6
uv run scripts/interpro_client.py fetch entry --limit 1 --query_params integrated=pfam next(fetch_interpro_data(endpoint='entry', query_params={'integrated': 'pfam'}, limit=1), None) [] uv run scripts/interpro_client.py fetch entry --limit - Network accessline 7
uv run scripts/interpro_client.py fetch entry --limit 1 --query_params go_term=GO:0016301 next(fetch_interpro_data(endpoint='entry', query_params={'go_term': 'GO:0016301'}, limit=1), None) {"entries": {"member_databases": {"pfam": 27208, "c - Network accessline 8
uv run scripts/interpro_client.py fetch entry --limit 1 --query_params sort_by=accession next(fetch_interpro_data(endpoint='entry', query_params={'sort_by': 'accession'}, limit=1), None) 404 Not Found: The request is incorrect. URL: https:/
skills/interpro_database/scripts/interpro_client.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 36
BASE_URL = "https://www.ebi.ac.uk/interpro/api/" - Network accessline 115
while True: try: resp = CLIENT.fetch(url, headers=headers) - Network accessline 116
try: resp = CLIENT.fetch(url, headers=headers) if resp.status_code == 204: - Network accessline 117
resp = CLIENT.fetch(url, headers=headers) - Network accessline 311
"--limit", type=int, help="Limit the number of results to fetch (highly recommended)", - Network accessline 312
type=int, help="Limit the number of results to fetch (highly recommended)", default=None, - Network accessline 313
help="Limit the number of results to fetch (highly recommended)",
skills/jaspar_database/SKILL.md
- Network accessline 24
2. **User Notification**: If .licenses/jaspar_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://jaspar.elixir.no/ and - Network accessline 25
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://jaspar.elixir.no/ and https://jaspar.elixir.no/api/, then (2) create the file recording the - Network accessline 26
the user to check the terms at https://jaspar.elixir.no/ and - Network accessline 27
https://jaspar.elixir.no/api/, then (2) create the file recording the
skills/jaspar_database/references/citation.bib
- Network accessline 1
@ARTICLE{OvekBaydar2026, ABSTRACT = {JASPAR (https://jaspar.elixir.no/) is an open-access database that has provided high-quality, manually curated, and non-redundant DNA binding profiles for transcription factors (TFs) as position freque - Network accessline 2
ABSTRACT = {JASPAR (https://jaspar.elixir.no/) is an open-access database that has provided high-quality, manually curated, and non-redundant DNA binding profiles for transcription factors (TFs) as position frequency matrices (PFMs) for ove - Network accessline 3
AUTHOR = {Ovek Baydar, Damla and Rauluseviciute, Ieva and Aronsen, Dina R and Blanc-Mathieu, Romain and Bonthuis, Ine and de Beukelaer, Herman and Ferenc, Katalin and Jegou, Alice and Kumar, Vipin and Lemma, Roza Berhanu and Lucas, Jérémy a - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkaf1209}, - Network accessline 5
DATE = {2026-01}, DOI = {10.1093/nar/gkaf1209}, EPRINT = {https://academic.oup.com/nar/article-pdf/54/D1/D184/65551692/gkaf1209.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkaf1209}, EPRINT = {https://academic.oup.com/nar/article-pdf/54/D1/D184/65551692/gkaf1209.pdf}, ISSN = {1362-4962}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/54/D1/D184/65551692/gkaf1209.pdf},
skills/jaspar_database/scripts/jaspar_api.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 33
JASPAR_URL = "https://jaspar.elixir.no/api/v1/"
skills/literature_search_arxiv/SKILL.md
- Network accessline 17
not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://info.arxiv.org/help/api/index.html and to always check the license - Network accessline 18
notify the user to check the terms at https://info.arxiv.org/help/api/index.html and to always check the license of the papers retrieved by the skill for any restrictions, then (2) create - Network accessline 19
https://info.arxiv.org/help/api/index.html and to always check the license
skills/literature_search_arxiv/references/citation.bib
- Network accessline 12
@ONLINE{arXiv2026, AUTHOR = {{arXiv}}, URL = {https://info.arxiv.org/help/api/index.html}, - Network accessline 13
AUTHOR = {{arXiv}}, URL = {https://info.arxiv.org/help/api/index.html}, TITLE = {{arXiv API Access}}, - Network accessline 14
URL = {https://info.arxiv.org/help/api/index.html},
skills/literature_search_arxiv/scripts/download_paper.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 34
_CLIENT = http_client.HttpClient("https://arxiv.org/", qps=1.0 / 3.0) - Network accessline 78
if args.format == "pdf": url = f"https://arxiv.org/pdf/{paper_id}.pdf" - Network accessline 79
url = f"https://arxiv.org/pdf/{paper_id}.pdf" - Network accessline 80
elif args.format == "html": url = f"https://arxiv.org/html/{paper_id}" else: - Network accessline 81
url = f"https://arxiv.org/html/{paper_id}"
skills/literature_search_arxiv/scripts/download_paper_source.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 34
_CLIENT = http_client.HttpClient("https://export.arxiv.org/", qps=1.0 / 3.0) - Network accessline 73
url = f"https://export.arxiv.org/e-print/{paper_id}" print(f"Attempting to download source from {url}...")
skills/literature_search_arxiv/scripts/search_arxiv.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 37
_BASE_URL = "http://export.arxiv.org/api/query?" - Network accessline 114
for entry in root.findall("{http://www.w3.org/2005/Atom}entry"): - Network accessline 121
# Extract just the ID part (e.g., http://arxiv.org/abs/2305.10601v1 - Network accessline 134
paper["published"] = child.text elif tag == "author": for name_node in child.findall("{http://www.w3.org/2005/Atom}name"): - Network accessline 135
elif tag == "author": for name_node in child.findall("{http://www.w3.org/2005/Atom}name"): authors.append(name_node.text) - Network accessline 136
for name_node in child.findall("{http://www.w3.org/2005/Atom}name"):
skills/literature_search_biorxiv/SKILL.md
- Network accessline 17
2. **User Notification**: If .licenses/literature_search_biorxiv_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://api.biorxiv.org/ and - Network accessline 18
does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://api.biorxiv.org/ and https://www.biorxiv.org/content/about-biorxiv and to always check the - Network accessline 19
notify the user to check the terms at https://api.biorxiv.org/ and - Network accessline 20
https://www.biorxiv.org/content/about-biorxiv and to always check the
skills/literature_search_biorxiv/references/citation.bib
- Network accessline 3
AUTHOR = {Sever, Richard and Hindle, Samantha and Roeder, Ted and Fereres, Sol and Fernández Gayol, Olaya and Ghosh, Sanchari and Proietti Onori, Martina and Croushore, Emma and Black, Kevin-John and Sussman, Linda and Argentine, Janet and - Network accessline 4
PUBLISHER = {Cold Spring Harbor Laboratory}, URL = {https://www.biorxiv.org/content/early/2026/02/26/833400}, DATE = {2026}, - Network accessline 5
URL = {https://www.biorxiv.org/content/early/2026/02/26/833400}, - Network accessline 6
DATE = {2026}, DOI = {10.1101/833400}, EPRINT = {https://www.biorxiv.org/content/early/2026/02/26/833400.full.pdf}, - Network accessline 7
DOI = {10.1101/833400}, EPRINT = {https://www.biorxiv.org/content/early/2026/02/26/833400.full.pdf}, JOURNALTITLE = {bioRxiv}, - Network accessline 8
EPRINT = {https://www.biorxiv.org/content/early/2026/02/26/833400.full.pdf},
skills/literature_search_biorxiv/scripts/search_by_dates.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 29
client = http_client.HttpClient(base_url="https://api.biorxiv.org/", qps=1.0) - Network accessline 135
base_url = ( f"https://api.biorxiv.org/details/{args.server}" - Network accessline 136
f"https://api.biorxiv.org/details/{args.server}"
skills/literature_search_biorxiv/scripts/search_by_doi.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 29
_CLIENT = http_client.HttpClient(base_url="https://api.biorxiv.org/", qps=1.0) - Network accessline 35
doi = args.doi.replace("https://doi.org/", "").replace("http://doi.org/", "") - Network accessline 36
url = f"https://api.biorxiv.org/details/{args.server}/{doi}"
skills/literature_search_europepmc/SKILL.md
- Network accessline 11
A skill for searching, downloading, and exploring open-access papers from [Europe PMC](https://europepmc.org/) — a comprehensive, free life-science - Network accessline 12
[Europe PMC](https://europepmc.org/) — a comprehensive, free life-science - Network accessline 20
2. **User Notification**: If .licenses/literature_search_europepmc_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://europepmc.org/ and to always - Network accessline 21
does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://europepmc.org/ and to always check the license of the papers retrieved by the skill for any restrictions, - Network accessline 22
notify the user to check the terms at https://europepmc.org/ and to always - Network accessline 49
Search Europe PMC by query. Supports DOI lookup, keyword search, author search, PMID lookup, and the full [Europe PMC search syntax](https://europepmc.org/searchsyntax). - Network accessline 51
[Europe PMC search syntax](https://europepmc.org/searchsyntax).
skills/literature_search_europepmc/references/citation.bib
- Network accessline 1
@ARTICLE{Rosonovski2024, ABSTRACT = {Europe PMC (https://europepmc.org/) is an open access database of life science journal articles and preprints, which contains over 42 million abstracts and over 9 million full text articles accessible - Network accessline 2
ABSTRACT = {Europe PMC (https://europepmc.org/) is an open access database of life science journal articles and preprints, which contains over 42 million abstracts and over 9 million full text articles accessible via the website, APIs and b - Network accessline 3
AUTHOR = {Rosonovski, Summer and Levchenko, Maria and Bhatnagar, Rajat and Chandrasekaran, Umamageswari and Faulk, Lynne and Hassan, Islam and Jeffryes, Matt and Mubashar, Syed Irtaza and Nassar, Maaly and Jayaprabha Palanisamy, Madhumietha - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkad1085}, - Network accessline 5
DATE = {2024-01}, DOI = {10.1093/nar/gkad1085}, EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D1668/55040834/gkad1085.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkad1085}, EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D1668/55040834/gkad1085.pdf}, ISSN = {0305-1048}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/52/D1/D1668/55040834/gkad1085.pdf},
skills/literature_search_europepmc/scripts/europepmc_api.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 41
_API_BASE = "https://www.ebi.ac.uk/europepmc/webservices/rest/" - Network accessline 42
_PDF_BASE = "https://europepmc.org/" - Network accessline 45
_API_BASE, qps=1.0, referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-europepmc", - Network accessline 46
qps=1.0, referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-europepmc", ) - Network accessline 47
referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-europepmc", - Network accessline 50
_PDF_BASE, qps=1.0, referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-europepmc", - Network accessline 51
qps=1.0, referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-europepmc", ) - Network accessline 52
referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-europepmc",
skills/literature_search_openalex/SKILL.md
- Network accessline 18
2. **User Notification**: If .licenses/literature_search_openalex_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://help.openalex.org/ and to - Network accessline 19
does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://help.openalex.org/ and to always check the license of the papers retrieved by the skill for any - Network accessline 20
notify the user to check the terms at https://help.openalex.org/ and to - Access to secretsline 26
[Credential-related source omitted] - Access to secretsline 49
[Credential-related source omitted] - Access to secretsline 101
[Credential-related source omitted] - Access to secretsline 104
[Credential-related source omitted] - Access to secretsline 109
[Credential-related source omitted] - Network accessline 131
For anything not covered here, or if the API behaves differently from what this skill describes, check the official docs index at https://help.openalex.org/llms.txt. - Network accessline 133
https://help.openalex.org/llms.txt. - Network accessline 145
# DOI lookup uv run scripts/openalex_cli.py get works "https://doi.org/10.1038/s41586-021-03819-2" - Network accessline 146
uv run scripts/openalex_cli.py get works "https://doi.org/10.1038/s41586-021-03819-2" - Network accessline 172
401 | Unauthorized | You MUST use safe credentials protocol in credentials skill to help user add API key to `.env` 404 | Not found | Verify ID; try `resolve` first 429 | Body sa - Network accessline 173
404 | Not found | Verify ID; try `resolve` first 429 | Body says `Plan upgrade required` | Paid-plan feature (e.g. a plan-gated filter). Do not retry; a free key won't help. Drop the filter or inform - Network accessline 174
429 | Body says `Plan upgrade required` | Paid-plan feature (e.g. a plan-gated filter). Do not retry; a free key won't help. Drop the filter or inform user; see https://openalex.org/pricing
skills/literature_search_openalex/scripts/openalex_cli.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 46
BASE_URL = "https://api.openalex.org" - Network accessline 47
PDF_BASE_URL = "https://content.openalex.org" - Network accessline 50
BASE_URL, qps=10.0, referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-openalex", - Network accessline 51
qps=10.0, referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-openalex", ) - Network accessline 52
referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-openalex", - Network accessline 55
PDF_BASE_URL, qps=1.0, referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-openalex", - Network accessline 56
qps=1.0, referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-openalex", ) - Network accessline 57
referer="https://github.com/google-deepmind/science-skills/tree/main/literature-search-openalex", - Access to secretsline 98
[Credential-related source omitted] - Access to secretsline 99
[Credential-related source omitted] - Access to secretsline 106
[Credential-related source omitted] - Access to secretsline 109
[Credential-related source omitted] - Access to secretsline 110
[Credential-related source omitted] - Access to secretsline 112
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Network accessline 158
while True: try: return _API_CLIENT.fetch(full_url, max_retries=0) - Network accessline 159
try: return _API_CLIENT.fetch(full_url, max_retries=0) except http_client.HttpError as e: - Network accessline 160
return _API_CLIENT.fetch(full_url, max_retries=0) - Access to secretsline 186
[Credential-related source omitted] - Access to secretsline 199
[Credential-related source omitted] - Access to secretsline 213
[Credential-related source omitted] - Network accessline 215
try: if url.startswith(PDF_BASE_URL): resp = _PDF_CLIENT.fetch(full_url, max_retries=max_retries) - Network accessline 216
if url.startswith(PDF_BASE_URL): resp = _PDF_CLIENT.fetch(full_url, max_retries=max_retries) elif url.startswith(BASE_URL): - Network accessline 217
resp = _PDF_CLIENT.fetch(full_url, max_retries=max_retries) - Network accessline 230
" because it uses a plan-gated filter such as from_created_date." " Retrying or adding a free API key will not help; drop that part" " of the query or see https://openalex.org/pricing.", - Network accessline 231
" Retrying or adding a free API key will not help; drop that part" " of the query or see https://openalex.org/pricing.", PLAN_UPGRADE_ERROR, - Network accessline 232
" of the query or see https://openalex.org/pricing.", - Access to secretsline 235
[Credential-related source omitted] - Network accessline 293
[Credential-related source omitted] - Access to secretsline 293
[Credential-related source omitted] - Network accessline 295
# Construct search URL (e.g., https://api.openalex.org/works) - Access to secretsline 301
[Credential-related source omitted] - Network accessline 325
Accepted formats: - Short IDs: W2741809807, A5023888391 - Full OpenAlex URLs: https://openalex.org/W2741809807 - Network accessline 326
- Short IDs: W2741809807, A5023888391 - Full OpenAlex URLs: https://openalex.org/W2741809807 - DOIs: https://doi.org/10.xxx - Network accessline 327
- Full OpenAlex URLs: https://openalex.org/W2741809807 - Network accessline 328
- DOIs: https://doi.org/10.xxx - Network accessline 330
return bool( _OPENALEX_SHORT_ID_RE.match(entity_id) or entity_id.startswith("https://openalex.org/") - Network accessline 331
_OPENALEX_SHORT_ID_RE.match(entity_id) or entity_id.startswith("https://openalex.org/") or entity_id.startswith("https://doi.org/") - Network accessline 332
or entity_id.startswith("https://openalex.org/") - Network accessline 333
or entity_id.startswith("https://doi.org/") - Access to secretsline 342
[Credential-related source omitted] - Network accessline 352
# Construct entity-specific URL (e.g., https://api.openalex.org/works/W123) - Access to secretsline 360
[Credential-related source omitted] - Access to secretsline 415
[Credential-related source omitted] - Access to secretsline 426
[Credential-related source omitted] - Access to secretsline 434
[Credential-related source omitted] - Access to secretsline 472
[Credential-related source omitted] - Access to secretsline 479
[Credential-related source omitted] - Access to secretsline 507
[Credential-related source omitted] - Access to secretsline 513
[Credential-related source omitted] - Access to secretsline 525
[Credential-related source omitted] - Access to secretsline 561
[Credential-related source omitted] - Access to secretsline 569
[Credential-related source omitted] - Access to secretsline 575
[Credential-related source omitted] - Access to secretsline 590
[Credential-related source omitted] - Access to secretsline 603
[Credential-related source omitted] - Access to secretsline 606
[Credential-related source omitted] - Access to secretsline 622
[Credential-related source omitted] - Access to secretsline 629
[Credential-related source omitted] - Access to secretsline 634
[Credential-related source omitted]
skills/ncbi_sequence_fetch/SKILL.md
- Network accessline 17
2. **User Notification**: If .licenses/ncbi_sequence_fetch_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ncbi.nlm.nih.gov/ and - Network accessline 18
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ncbi.nlm.nih.gov/ and https://www.ncbi.nlm.nih.gov/home/about/policies/, then (2) create the file - Network accessline 19
the user to check the terms at https://www.ncbi.nlm.nih.gov/ and - Network accessline 20
https://www.ncbi.nlm.nih.gov/home/about/policies/, then (2) create the file - Access to secretsline 24
[Credential-related source omitted] - Network accessline 25
requests/second. The skill works without it, but a key is recommended if the user plans many queries or encounters a 429 error. You can register for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** - Network accessline 26
user plans many queries or encounters a 429 error. You can register for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** use the safe credentials protocol in the `credentials` skill to check for - Network accessline 27
key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** - Access to secretsline 36
[Credential-related source omitted] - Network accessline 221
- **NCBI E-utilities docs**: https://www.ncbi.nlm.nih.gov/books/NBK25499/ - Network accessline 222
- **Entrez search syntax**: https://www.ncbi.nlm.nih.gov/books/NBK49540/
skills/ncbi_sequence_fetch/references/citation.bib
- Network accessline 1
@ARTICLE{Sayers2025, ABSTRACT = {The National Center for Biotechnology Information (NCBI) provides online information resources for biology, including the GenBank® nucleic acid sequence repository and the PubMed® repository of citations a - Network accessline 2
ABSTRACT = {The National Center for Biotechnology Information (NCBI) provides online information resources for biology, including the GenBank® nucleic acid sequence repository and the PubMed® repository of citations and abstracts published - Network accessline 3
AUTHOR = {Sayers, Eric W and Beck, Jeffrey and Bolton, Evan E and Brister, J Rodney and Chan, Jessica and Connor, Ryan and Feldgarden, Michael and Fine, Anna M and Funk, Kathryn and Hoffman, Jinna and Kannan, Sivakumar and Kelly, Christophe - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkae979}, - Network accessline 5
DATE = {2025-01}, DOI = {10.1093/nar/gkae979}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D20/60586411/gkae979.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkae979}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D20/60586411/gkae979.pdf}, ISSN = {1362-4962}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D20/60586411/gkae979.pdf},
skills/ncbi_sequence_fetch/scripts/ncbi_fetch.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Access to secretsline 21
[Credential-related source omitted] - Network accessline 116
EUTILS_BASE = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils' - Access to secretsline 125
[Credential-related source omitted] - Access to secretsline 126
[Credential-related source omitted] - Access to secretsline 144
[Credential-related source omitted] - Access to secretsline 145
[Credential-related source omitted] - Access to secretsline 146
[Credential-related source omitted] - Network accessline 153
try: res = get_api_client().fetch(full_url) - Network accessline 154
res = get_api_client().fetch(full_url) - Access to secretsline 1083
[Credential-related source omitted]
skills/openfda_database/SKILL.md
- Network accessline 17
2. **User Notification**: If .licenses/openfda_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://open.fda.gov/apis/ and - Network accessline 18
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://open.fda.gov/apis/ and https://open.fda.gov/license, then (2) create the file recording the - Network accessline 19
the user to check the terms at https://open.fda.gov/apis/ and - Network accessline 20
https://open.fda.gov/license, then (2) create the file recording the - Access to secretsline 24
[Credential-related source omitted] - Network accessline 25
from 1,000 to 120,000. The skill works without it, but an agent can easily exhaust the keyless limit in a single session. You can register for a free key at https://open.fda.gov/apis/authentication/. You **MUST** use the safe - Network accessline 26
exhaust the keyless limit in a single session. You can register for a free key at https://open.fda.gov/apis/authentication/. You **MUST** use the safe credentials protocol in the `credentials` skill to check for and request - Network accessline 27
key at https://open.fda.gov/apis/authentication/. You **MUST** use the safe - Access to secretsline 47
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Network accessline 132
- `--max_pages`: Maximum pages to fetch (default 10).
skills/openfda_database/references/api_endpoints.md
skills/openfda_database/references/citation.bib
- Network accessline 2
ABSTRACT = {Objective The objective of openFDA is to facilitate access and use of big important Food and Drug Administration public datasets by developers, researchers, and the public through harmonization of data across disparate FDA datas - Network accessline 3
AUTHOR = {Kass-Hout, Taha A and Xu, Zhiheng and Mohebbi, Matthew and Nelsen, Hans and Baker, Adam and Levine, Jonathan and Johanson, Elaine and Bright, Roselie A}, URL = {https://doi.org/10.1093/jamia/ocv153}, DATE = {2016-05}, - Network accessline 4
URL = {https://doi.org/10.1093/jamia/ocv153}, - Network accessline 5
DATE = {2016-05}, DOI = {10.1093/jamia/ocv153}, EPRINT = {https://academic.oup.com/jamia/article-pdf/23/3/596/34147863/ocv153.pdf}, - Network accessline 6
DOI = {10.1093/jamia/ocv153}, EPRINT = {https://academic.oup.com/jamia/article-pdf/23/3/596/34147863/ocv153.pdf}, ISSN = {1067-5027}, - Network accessline 7
EPRINT = {https://academic.oup.com/jamia/article-pdf/23/3/596/34147863/ocv153.pdf},
skills/openfda_database/scripts/openfda_query.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 42
BASE_URL = "https://api.fda.gov" - Access to secretsline 81
[Credential-related source omitted] - Access to secretsline 82
[Credential-related source omitted] - Network accessline 84
print( "WARNING: No API key provided. This API has much lower rate limits" " without a key. Get one at https://open.fda.gov/apis/authentication/" - Network accessline 85
"WARNING: No API key provided. This API has much lower rate limits" " without a key. Get one at https://open.fda.gov/apis/authentication/" " and pass via --api_key or the FDA_API_KEY environment variable.", - Network accessline 86
" without a key. Get one at https://open.fda.gov/apis/authentication/" - Access to secretsline 87
[Credential-related source omitted] - Network accessline 98
data["_license_notice"] = ( "Data provided by openFDA. Please review the licensing terms at" " https://open.fda.gov/license/" - Network accessline 99
"Data provided by openFDA. Please review the licensing terms at" " https://open.fda.gov/license/" ) - Network accessline 100
" https://open.fda.gov/license/" - Access to secretsline 147
[Credential-related source omitted] - Access to secretsline 159
[Credential-related source omitted] - Access to secretsline 167
[Credential-related source omitted] - Access to secretsline 169
[Credential-related source omitted] - Network accessline 186
try: resp = CLIENT.fetch(url, headers={"Accept": "application/json"}) - Network accessline 187
resp = CLIENT.fetch(url, headers={"Accept": "application/json"}) - Network accessline 201
" limit. Without an API key the limit is 240 requests/min and" " 1,000/day. With a free API key the daily limit increases to" " 120,000. Register at: https://open.fda.gov/apis/authentication/" - Network accessline 202
" 1,000/day. With a free API key the daily limit increases to" " 120,000. Register at: https://open.fda.gov/apis/authentication/" ), - Network accessline 203
" 120,000. Register at: https://open.fda.gov/apis/authentication/" - Access to secretsline 232
[Credential-related source omitted] - Access to secretsline 238
[Credential-related source omitted] - Access to secretsline 247
[Credential-related source omitted] - Access to secretsline 277
[Credential-related source omitted] - Access to secretsline 285
[Credential-related source omitted] - Access to secretsline 320
[Credential-related source omitted] - Access to secretsline 346
[Credential-related source omitted] - Access to secretsline 390
[Credential-related source omitted] - Access to secretsline 439
[Credential-related source omitted] - Access to secretsline 442
[Credential-related source omitted] - Network accessline 483
type=int, default=10, help="Max pages to fetch (default 10)", - Network accessline 484
default=10, help="Max pages to fetch (default 10)", ) - Network accessline 485
help="Max pages to fetch (default 10)", - Access to secretsline 501
[Credential-related source omitted]
skills/opentargets_database/SKILL.md
- Network accessline 23
not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://platform-docs.opentargets.org/licence, then (2) create the file - Network accessline 24
notify the user to check the terms at https://platform-docs.opentargets.org/licence, then (2) create the file recording the notification text and timestamp. - Network accessline 25
https://platform-docs.opentargets.org/licence, then (2) create the file - Network accessline 40
Always use the provided Python script `scripts/query_opentargets.py` to quickly query the database. It handles API communication, retries, formatting, and automatically truncates overly large responses. NEVER write your own curl or - Network accessline 41
query the database. It handles API communication, retries, formatting, and automatically truncates overly large responses. NEVER write your own curl or similar requests. - Network accessline 42
automatically truncates overly large responses. NEVER write your own curl or
skills/opentargets_database/references/citation.bib
- Network accessline 1
@ARTICLE{Buniello2025, ABSTRACT = {The Open Targets Platform (https://platform.opentargets.org) is a unique, open-source, publicly-available knowledge base providing data and tooling for systematic drug target identification, annotation, - Network accessline 2
ABSTRACT = {The Open Targets Platform (https://platform.opentargets.org) is a unique, open-source, publicly-available knowledge base providing data and tooling for systematic drug target identification, annotation, and prioritisation. Since - Network accessline 3
AUTHOR = {Buniello, Annalisa and Suveges, Daniel and Cruz-Castillo, Carlos and Llinares, Manuel Bernal and Cornu, Helena and Lopez, Irene and Tsukanov, Kirill and Roldán-Romero, Juan María and Mehta, Chintan and Fumis, Luca and McNeill, Gra - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkae1128}, - Network accessline 5
DATE = {2025-01}, DOI = {10.1093/nar/gkae1128}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D1467/60967175/gkae1128.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkae1128}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D1467/60967175/gkae1128.pdf}, ISSN = {1362-4962}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D1467/60967175/gkae1128.pdf},
skills/opentargets_database/scripts/query_opentargets.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 37
BASE_URL = "https://api.platform.opentargets.org/api/v4/graphql"
skills/pdb_database/SKILL.md
- Network accessline 18
2. **User Notification**: If .licenses/pdb_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.rcsb.org/pages/usage-policy, then - Network accessline 19
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.rcsb.org/pages/usage-policy, then (2) create the file recording the notification text and timestamp. - Network accessline 20
the user to check the terms at https://www.rcsb.org/pages/usage-policy, then - Network accessline 119
See https://search.rcsb.org/#search-services for more details.
skills/pdb_database/references/citation.bib
- Network accessline 1
@ARTICLE{Berman2000, ABSTRACT = {The Protein Data Bank (PDB; http://www.rcsb.org/pdb/ ) is the single worldwide archive of structural data of biological macromolecules. This paper describes the goals of the PDB, the systems in place for d - Network accessline 2
ABSTRACT = {The Protein Data Bank (PDB; http://www.rcsb.org/pdb/ ) is the single worldwide archive of structural data of biological macromolecules. This paper describes the goals of the PDB, the systems in place for data deposition and acce - Network accessline 3
AUTHOR = {Berman, Helen M. and Westbrook, John and Feng, Zukang and Gilliland, Gary and Bhat, T. N. and Weissig, Helge and Shindyalov, Ilya N. and Bourne, Philip E.}, URL = {https://doi.org/10.1093/nar/28.1.235}, DATE = {2000-01}, - Network accessline 4
URL = {https://doi.org/10.1093/nar/28.1.235}, - Network accessline 5
DATE = {2000-01}, DOI = {10.1093/nar/28.1.235}, EPRINT = {https://academic.oup.com/nar/article-pdf/28/1/235/9895144/280235.pdf}, - Network accessline 6
DOI = {10.1093/nar/28.1.235}, EPRINT = {https://academic.oup.com/nar/article-pdf/28/1/235/9895144/280235.pdf}, ISSN = {0305-1048}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/28/1/235/9895144/280235.pdf},
skills/pdb_database/scripts/download_coordinate_files.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 31
CLIENT = http_client.HttpClient("https://files-beta.rcsb.org", qps=5.0) - Network accessline 49
"**Check with the user**, then consider downloading a copy of all" f" {args.format} files using the recommended bulk script at " "https://cdn.rcsb.org/wwpdb/docs/BetaArchiveBatchDownloader.py.", - Network accessline 50
f" {args.format} files using the recommended bulk script at " "https://cdn.rcsb.org/wwpdb/docs/BetaArchiveBatchDownloader.py.", file=sys.stderr, - Network accessline 51
"https://cdn.rcsb.org/wwpdb/docs/BetaArchiveBatchDownloader.py.",
skills/pdb_database/scripts/fetch_pdb_metadata.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 30
CLIENT = http_client.HttpClient("https://data.rcsb.org", qps=2.0) - Network accessline 39
encoded_query = urllib.parse.quote(args.query.strip()) url = f"https://data.rcsb.org/graphql?query={encoded_query}" - Network accessline 40
url = f"https://data.rcsb.org/graphql?query={encoded_query}"
skills/pdb_database/scripts/fetch_schema.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 29
SEARCH_CLIENT = http_client.HttpClient("https://search.rcsb.org", qps=2.0) - Network accessline 30
DATA_CLIENT = http_client.HttpClient("https://data.rcsb.org", qps=2.0) - Network accessline 33
API_URLS = { "search_structure": "https://search.rcsb.org/rcsbsearch/v2/metadata/schema", - Network accessline 34
"search_structure": "https://search.rcsb.org/rcsbsearch/v2/metadata/schema", - Network accessline 35
"search_chemical": ( "https://search.rcsb.org/rcsbsearch/v2/metadata/chemical/schema" ), - Network accessline 36
"https://search.rcsb.org/rcsbsearch/v2/metadata/chemical/schema" - Network accessline 37
), "data_entry": "https://data.rcsb.org/rest/v1/schema/entry", "data_polymer_entity": ( - Network accessline 38
"data_entry": "https://data.rcsb.org/rest/v1/schema/entry", - Network accessline 39
"data_polymer_entity": ( "https://data.rcsb.org/rest/v1/schema/polymer_entity" ), - Network accessline 40
"https://data.rcsb.org/rest/v1/schema/polymer_entity" - Network accessline 41
), "data_polymer_entity_instance": ( "https://data.rcsb.org/rest/v1/schema/polymer_entity_instance" - Network accessline 42
"data_polymer_entity_instance": ( "https://data.rcsb.org/rest/v1/schema/polymer_entity_instance" ), - Network accessline 43
"https://data.rcsb.org/rest/v1/schema/polymer_entity_instance" - Network accessline 44
), "data_assembly": "https://data.rcsb.org/rest/v1/schema/assembly", "data_non_polymer_entity": ( - Network accessline 45
"data_assembly": "https://data.rcsb.org/rest/v1/schema/assembly", - Network accessline 46
"data_non_polymer_entity": ( "https://data.rcsb.org/rest/v1/schema/nonpolymer_entity" ), - Network accessline 47
"https://data.rcsb.org/rest/v1/schema/nonpolymer_entity" - Network accessline 48
), "data_non_polymer_entity_instance": ( "https://data.rcsb.org/rest/v1/schema/nonpolymer_entity_instance" - Network accessline 49
"data_non_polymer_entity_instance": ( "https://data.rcsb.org/rest/v1/schema/nonpolymer_entity_instance" ), - Network accessline 50
"https://data.rcsb.org/rest/v1/schema/nonpolymer_entity_instance" - Network accessline 51
), "data_branched_entity_instance": ( "https://data.rcsb.org/rest/v1/schema/branched_entity_instance" - Network accessline 52
"data_branched_entity_instance": ( "https://data.rcsb.org/rest/v1/schema/branched_entity_instance" ), - Network accessline 53
"https://data.rcsb.org/rest/v1/schema/branched_entity_instance" - Network accessline 54
), "data_branched_entity": ( "https://data.rcsb.org/rest/v1/schema/branched_entity" - Network accessline 55
"data_branched_entity": ( "https://data.rcsb.org/rest/v1/schema/branched_entity" ), - Network accessline 56
"https://data.rcsb.org/rest/v1/schema/branched_entity" - Network accessline 57
), "data_chemical_component": "https://data.rcsb.org/rest/v1/schema/chem_comp", } - Network accessline 58
"data_chemical_component": "https://data.rcsb.org/rest/v1/schema/chem_comp",
skills/pdb_database/scripts/search_pdb.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 35
CLIENT = http_client.HttpClient("https://search.rcsb.org", qps=2.0) - Network accessline 89
json_payload = json.dumps(payload, separators=(",", ":")) encoded_query = urllib.parse.quote(json_payload) url = f"https://search.rcsb.org/rcsbsearch/v2/query?json={encoded_query}" - Network accessline 91
url = f"https://search.rcsb.org/rcsbsearch/v2/query?json={encoded_query}"
skills/predictingthepast/SKILL.md
- Network accessline 27
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://github.com/google-deepmind/predictingthepast/blob/main/README.md#license--disclaimer, - Network accessline 28
the user to check the terms at https://github.com/google-deepmind/predictingthepast/blob/main/README.md#license--disclaimer, and include the appropriate citation and the full dataset acknowledgement, - Network accessline 29
https://github.com/google-deepmind/predictingthepast/blob/main/README.md#license--disclaimer, - Network accessline 186
# Pick an unused port and start the server as a persistent process HTML_FILE=/tmp/dashboard.html # ← set to the actual HTML file path PORT=$(export PATH="$HOME/.local/bin:$PATH" && uv run python -c "import socket; s=socket.socket(); s.bin - Network accessline 187
HTML_FILE=/tmp/dashboard.html # ← set to the actual HTML file path PORT=$(export PATH="$HOME/.local/bin:$PATH" && uv run python -c "import socket; s=socket.socket(); s.bind(('',0)); print(s.getsockname()[1]); s.close()") FILENAME=$(basena - Network accessline 188
PORT=$(export PATH="$HOME/.local/bin:$PATH" && uv run python -c "import socket; s=socket.socket(); s.bind(('',0)); print(s.getsockname()[1]); s.close()") - Network accessline 189
FILENAME=$(basename "$HTML_FILE") echo "View URL: http://localhost:${PORT}/${FILENAME}" export PATH="$HOME/.local/bin:$PATH" && uv run python -m http.server "$PORT" --bind 0.0.0.0 --directory "$(dirname "$HTML_FILE")" - Network accessline 190
echo "View URL: http://localhost:${PORT}/${FILENAME}" - Network accessline 197
# Pick an unused port and start the server as a persistent process $HTML_FILE = "C:\tmp\dashboard.html" # ← set to the actual HTML file path $PORT = & "$HOME\.local\bin\uv" run python -c "import socket; s=socket.socket(); s.bind(('',0)); - Network accessline 198
$HTML_FILE = "C:\tmp\dashboard.html" # ← set to the actual HTML file path $PORT = & "$HOME\.local\bin\uv" run python -c "import socket; s=socket.socket(); s.bind(('',0)); print(s.getsockname()[1]); s.close()" $FILENAME = Split-Path $HTML_ - Network accessline 199
$PORT = & "$HOME\.local\bin\uv" run python -c "import socket; s=socket.socket(); s.bind(('',0)); print(s.getsockname()[1]); s.close()" - Network accessline 200
$FILENAME = Split-Path $HTML_FILE -Leaf $DIRNAME = Split-Path $HTML_FILE -Parent Write-Host "View URL: http://localhost:${PORT}/${FILENAME}" - Network accessline 201
$DIRNAME = Split-Path $HTML_FILE -Parent Write-Host "View URL: http://localhost:${PORT}/${FILENAME}" & "$HOME\.local\bin\uv" run python -m http.server $PORT --bind 0.0.0.0 --directory $DIRNAME - Network accessline 202
Write-Host "View URL: http://localhost:${PORT}/${FILENAME}" - Network accessline 206
Then provide `http://localhost:<port>/<filename>` (or - Network accessline 207
`http://127.0.0.1:<port>/<filename>`) as the primary clickable link in your - Network accessline 254
Present results for **every** task requested by the user. Always generate the HTML dashboard, serve it via the background HTTP server described above, and provide the `http://` URL as a clickable link. Format years as BCE/CE. - Network accessline 256
provide the `http://` URL as a clickable link. Format years as BCE/CE. - Network accessline 296
For more information, see: [predictingthepast.com](https://predictingthepast.com) - Network accessline 297
[predictingthepast.com](https://predictingthepast.com) - Network accessline 322
Searchable Greek Inscriptions database made available under "Fair Use" license by the Packard Humanities Institute, generously supported by David Packard: [inscriptions.packhum.org](https://inscriptions.packhum.org). - Network accessline 324
[inscriptions.packhum.org](https://inscriptions.packhum.org). - Network accessline 328
* **Epigraphic Database Roma (EDR)**: Made available pursuant to a Creative Commons Attribution 4.0 International License (CC-BY) on [Zenodo](https://zenodo.org/records/3575495). EDR is also available at - Network accessline 329
Commons Attribution 4.0 International License (CC-BY) on [Zenodo](https://zenodo.org/records/3575495). EDR is also available at [edr-edr.it](http://www.edr-edr.it/). - Network accessline 330
[Zenodo](https://zenodo.org/records/3575495). EDR is also available at - Network accessline 331
[edr-edr.it](http://www.edr-edr.it/). - Network accessline 332
* **Epigraphic Database Heidelberg (EDH)**: Made available pursuant to a Creative Commons Attribution-ShareAlike 4.0 International License (CC-BY-SA) on [Zenodo](https://zenodo.org/records/3575155). EDH is also available at - Network accessline 333
Creative Commons Attribution-ShareAlike 4.0 International License (CC-BY-SA) on [Zenodo](https://zenodo.org/records/3575155). EDH is also available at [edh.ub.uni-heidelberg.de](https://edh.ub.uni-heidelberg.de/). - Network accessline 334
on [Zenodo](https://zenodo.org/records/3575155). EDH is also available at - Network accessline 335
[edh.ub.uni-heidelberg.de](https://edh.ub.uni-heidelberg.de/). - Network accessline 336
* **ETL repository for Epigraphic Database Clauss Slaby (EDCS\_ETL)**: Made available pursuant to a Creative Commons Attribution 4.0 International License (CC-BY) on [Zenodo](https://zenodo.org/records/7072337). EDCS\_ETL - Network accessline 337
available pursuant to a Creative Commons Attribution 4.0 International License (CC-BY) on [Zenodo](https://zenodo.org/records/7072337). EDCS\_ETL is also available at [manfredclauss.de](http://www.manfredclauss.de/) and - Network accessline 338
License (CC-BY) on [Zenodo](https://zenodo.org/records/7072337). EDCS\_ETL - Network accessline 339
is also available at [manfredclauss.de](http://www.manfredclauss.de/) and - Network accessline 340
[github.com/sdam-au/EDCS\_ETL](https://github.com/sdam-au/EDCS_ETL).
skills/predictingthepast/scripts/preprocess.py
skills/predictingthepast/scripts/run_inference.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 95
GCS_BASE: str = 'https://storage.googleapis.com/ithaca-resources/models' - Access to secretsline 328
[Credential-related source omitted] - Network accessline 340
probe_req = urllib.request.Request(url, headers={'Range': 'bytes=0-0'}) - Network accessline 341
with urllib.request.urlopen( - Network accessline 364
while start < total_size: end = min(start + _DOWNLOAD_CHUNK_SIZE - 1, total_size - 1) req = urllib.request.Request( - Network accessline 365
end = min(start + _DOWNLOAD_CHUNK_SIZE - 1, total_size - 1) req = urllib.request.Request( url, headers={'Range': f'bytes={start}-{end}'} - Network accessline 366
req = urllib.request.Request( - Network accessline 367
url, headers={'Range': f'bytes={start}-{end}'} ) with urllib.request.urlopen( - Network accessline 368
) with urllib.request.urlopen( req, timeout=_DOWNLOAD_TIMEOUT_SECONDS, context=ssl_ctx - Network accessline 369
with urllib.request.urlopen( - Network accessline 376
start += len(data) else: with urllib.request.urlopen( - Network accessline 377
else: with urllib.request.urlopen( url, timeout=_DOWNLOAD_TIMEOUT_SECONDS, context=ssl_ctx - Network accessline 378
with urllib.request.urlopen(
skills/predictingthepast/scripts/visualize_results.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 434
<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Predicting The Past — Results Dashboard</title> <link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 435
<title>Predicting The Past — Results Dashboard</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 436
<link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 437
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 438
<link href="https://fonts.googleapis.com/css2?family=Roboto+Mono:wght@400&family=Roboto:wght@300;400;700&display=swap" rel="stylesheet"> - Network accessline 439
<script src="https://www.gstatic.com/charts/loader.js"></script> - Network accessline 508
Restoring and attributing ancient texts using deep neural networks. <em>Nature</em> 603, 280–283 (2022). <a href="https://doi.org/10.1038/s41586-022-04448-z" target="_blank" rel="noopener">https://doi.org/10.1038/s41586-022-04448-z</a - Network accessline 509
<em>Nature</em> 603, 280–283 (2022). <a href="https://doi.org/10.1038/s41586-022-04448-z" target="_blank" rel="noopener">https://doi.org/10.1038/s41586-022-04448-z</a> </p> - Network accessline 510
<a href="https://doi.org/10.1038/s41586-022-04448-z" target="_blank" rel="noopener">https://doi.org/10.1038/s41586-022-04448-z</a> - Network accessline 515
Contextualizing ancient texts with generative neural networks. <em>Nature</em> 645, 141–147 (2025). <a href="https://doi.org/10.1038/s41586-025-09292-5" target="_blank" rel="noopener">https://doi.org/10.1038/s41586-025-09292-5</a> - Network accessline 516
<em>Nature</em> 645, 141–147 (2025). <a href="https://doi.org/10.1038/s41586-025-09292-5" target="_blank" rel="noopener">https://doi.org/10.1038/s41586-025-09292-5</a> </p> - Network accessline 517
<a href="https://doi.org/10.1038/s41586-025-09292-5" target="_blank" rel="noopener">https://doi.org/10.1038/s41586-025-09292-5</a> - Network accessline 518
</p> <p style="font-size:13px;color:#6c757d;">For more information, visit <a href="https://predictingthepast.com" target="_blank" rel="noopener">predictingthepast.com</a>. - Network accessline 519
<p style="font-size:13px;color:#6c757d;">For more information, visit <a href="https://predictingthepast.com" target="_blank" rel="noopener">predictingthepast.com</a>. </p> - Network accessline 520
<a href="https://predictingthepast.com" target="_blank" rel="noopener">predictingthepast.com</a>. - Network accessline 540
version of the Searchable Greek Inscriptions database made available under “Fair Use” license by the Packard Humanities Institute, generously supported by David Packard: <a href="https://inscriptions.packhum.org" target="_blank" - Network accessline 541
“Fair Use” license by the Packard Humanities Institute, generously supported by David Packard: <a href="https://inscriptions.packhum.org" target="_blank" rel="noopener">inscriptions.packhum.org</a>. </p> - Network accessline 542
by David Packard: <a href="https://inscriptions.packhum.org" target="_blank" rel="noopener">inscriptions.packhum.org</a>. - Network accessline 548
<strong>Epigraphic Database Roma (EDR)</strong>: Made available pursuant to a Creative Commons Attribution 4.0 International License (CC-BY) on <a href="https://zenodo.org/records/3575495" target="_blank" rel="noopener">Zenodo</a>. - Network accessline 549
Creative Commons Attribution 4.0 International License (CC-BY) on <a href="https://zenodo.org/records/3575495" target="_blank" rel="noopener">Zenodo</a>. EDR is also available at <a href="http://edr-edr.it" target="_blank" rel="noopener">ed - Network accessline 550
<a href="https://zenodo.org/records/3575495" target="_blank" rel="noopener">Zenodo</a>. - Network accessline 551
EDR is also available at <a href="http://edr-edr.it" target="_blank" rel="noopener">edr-edr.it</a>. - Network accessline 554
<strong>Epigraphic Database Heidelberg (EDH)</strong>: Made available pursuant to a Creative Commons Attribution-ShareAlike 4.0 International License (CC-BY-SA) on <a href="https://zenodo.org/records/3575155" target="_blank" rel="noopener"> - Network accessline 555
Creative Commons Attribution-ShareAlike 4.0 International License (CC-BY-SA) on <a href="https://zenodo.org/records/3575155" target="_blank" rel="noopener">Zenodo</a>. EDH is also available at <a href="https://edh.ub.uni-heidelberg.de/" tar - Network accessline 556
<a href="https://zenodo.org/records/3575155" target="_blank" rel="noopener">Zenodo</a>. - Network accessline 557
EDH is also available at <a href="https://edh.ub.uni-heidelberg.de/" target="_blank" rel="noopener">edh.ub.uni-heidelberg.de</a>. - Network accessline 560
<strong>ETL repository for Epigraphic Database Clauss Slaby (EDCS_ETL)</strong>: Made available pursuant to a Creative Commons Attribution 4.0 International License (CC-BY) on <a href="https://zenodo.org/records/7072337" target="_blank" rel - Network accessline 561
Made available pursuant to a Creative Commons Attribution 4.0 International License (CC-BY) on <a href="https://zenodo.org/records/7072337" target="_blank" rel="noopener">Zenodo</a>. EDCS_ETL is also available at <a href="http://www.manfred - Network accessline 562
<a href="https://zenodo.org/records/7072337" target="_blank" rel="noopener">Zenodo</a>. - Network accessline 563
EDCS_ETL is also available at <a href="http://www.manfredclauss.de/" target="_blank" rel="noopener">manfredclauss.de</a> and - Network accessline 564
<a href="https://github.com/sdam-au/EDCS_ETL" target="_blank" rel="noopener">github.com/sdam-au/EDCS_ETL</a>.
skills/protein_sequence_msa/SKILL.md
- Network accessline 18
not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/jdispatcher/msa/clustalo and - Network accessline 19
notify the user to check the terms at https://www.ebi.ac.uk/jdispatcher/msa/clustalo and https://www.ebi.ac.uk/about/terms-of-use/, then (2) create the file - Network accessline 20
https://www.ebi.ac.uk/jdispatcher/msa/clustalo and - Network accessline 21
https://www.ebi.ac.uk/about/terms-of-use/, then (2) create the file - Network accessline 32
- **Use the Wrapper**: ALWAYS execute the alignment using `scripts/msa_align.py` rather than writing your own curl or custom Python - Network accessline 33
`scripts/msa_align.py` rather than writing your own curl or custom Python - Network accessline 122
- Multiple Sequence Alignment: https://www.ebi.ac.uk/jdispatcher/msa/clustalo
skills/protein_sequence_msa/references/citation.bib
- Network accessline 2
ABSTRACT = {Multiple sequence alignments are fundamental to many sequence analysis methods. Most alignments are computed using the progressive alignment heuristic. These methods are starting to become a bottleneck in some analysis pipelines - Network accessline 3
AUTHOR = {Sievers, Fabian and Wilm, Andreas and Dineen, David and Gibson, Toby J. and Karplus, Kevin and Li, Weizhong and Lopez, Rodrigo and McWilliam, Hamish and Remmert, Michael and Söding, Johannes and Thompson, Julie D. and Higgins, Des - Network accessline 4
URL = {https://doi.org/10.1038/msb.2011.75}, - Network accessline 15
@ARTICLE{Goujon2010, ABSTRACT = {The EMBL-EBI provides access to various mainstream sequence analysis applications. These include sequence similarity search services such as BLAST, FASTA, InterProScan and multiple sequence alignment tools - Network accessline 16
ABSTRACT = {The EMBL-EBI provides access to various mainstream sequence analysis applications. These include sequence similarity search services such as BLAST, FASTA, InterProScan and multiple sequence alignment tools such as ClustalW, T-Co - Network accessline 17
AUTHOR = {Goujon, Mickael and McWilliam, Hamish and Li, Weizhong and Valentin, Franck and Squizzato, Silvano and Paern, Juri and Lopez, Rodrigo}, URL = {https://doi.org/10.1093/nar/gkq313}, DATE = {2010-07}, - Network accessline 18
URL = {https://doi.org/10.1093/nar/gkq313}, - Network accessline 19
DATE = {2010-07}, DOI = {10.1093/nar/gkq313}, EPRINT = {https://academic.oup.com/nar/article-pdf/38/suppl_2/W695/3832907/gkq313.pdf}, - Network accessline 20
DOI = {10.1093/nar/gkq313}, EPRINT = {https://academic.oup.com/nar/article-pdf/38/suppl_2/W695/3832907/gkq313.pdf}, ISSN = {0305-1048}, - Network accessline 21
EPRINT = {https://academic.oup.com/nar/article-pdf/38/suppl_2/W695/3832907/gkq313.pdf}, - Network accessline 30
@ARTICLE{Madeira2024, ABSTRACT = {The EMBL-EBI Job Dispatcher sequence analysis tools framework (https://www.ebi.ac.uk/jdispatcher) enables the scientific community to perform a diverse range of sequence analyses using popular bioinformat - Network accessline 31
ABSTRACT = {The EMBL-EBI Job Dispatcher sequence analysis tools framework (https://www.ebi.ac.uk/jdispatcher) enables the scientific community to perform a diverse range of sequence analyses using popular bioinformatics applications. Free a - Network accessline 32
AUTHOR = {Madeira, Fábio and Madhusoodanan, Nandana and Lee, Joonheung and Eusebi, Alberto and Niewielska, Ania and Tivey, Adrian R N and Lopez, Rodrigo and Butcher, Sarah}, URL = {https://doi.org/10.1093/nar/gkae241}, DATE = {2024-07}, - Network accessline 33
URL = {https://doi.org/10.1093/nar/gkae241}, - Network accessline 34
DATE = {2024-07}, DOI = {10.1093/nar/gkae241}, EPRINT = {https://academic.oup.com/nar/article-pdf/52/W1/W521/58436149/gkae241.pdf}, - Network accessline 35
DOI = {10.1093/nar/gkae241}, EPRINT = {https://academic.oup.com/nar/article-pdf/52/W1/W521/58436149/gkae241.pdf}, ISSN = {0305-1048}, - Network accessline 36
EPRINT = {https://academic.oup.com/nar/article-pdf/52/W1/W521/58436149/gkae241.pdf},
skills/protein_sequence_msa/scripts/msa_align.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 39
_CLIENT = http_client.HttpClient( "https://www.ebi.ac.uk/Tools/services/rest/clustalo/", qps=1 - Network accessline 40
"https://www.ebi.ac.uk/Tools/services/rest/clustalo/", qps=1 - Access to secretsline 101
[Credential-related source omitted] - Access to secretsline 150
[Credential-related source omitted]
skills/protein_sequence_similarity_search/SKILL.md
- Network accessline 17
.licenses/protein_sequence_similarity_search_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/jdispatcher/sss/ncbiblast and - Network accessline 18
exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/jdispatcher/sss/ncbiblast and https://colabfold.com, then (2) create the file recording the notification - Network accessline 19
to check the terms at https://www.ebi.ac.uk/jdispatcher/sss/ncbiblast and - Network accessline 20
https://colabfold.com, then (2) create the file recording the notification
skills/protein_sequence_similarity_search/references/citation.bib
- Network accessline 1
@ARTICLE{Steinegger2017, AUTHOR = {Steinegger, Martin and Söding, Johannes}, URL = {https://doi.org/10.1038/nbt.3988}, - Network accessline 2
AUTHOR = {Steinegger, Martin and Söding, Johannes}, URL = {https://doi.org/10.1038/nbt.3988}, DATE = {2017-11-01}, - Network accessline 3
URL = {https://doi.org/10.1038/nbt.3988}, - Network accessline 25
@ARTICLE{Madeira2022, ABSTRACT = {The EMBL-EBI search and sequence analysis tools frameworks provide integrated access to EMBL-EBI’s data resources and core bioinformatics analytical tools. EBI Search (https://www.ebi.ac.uk/ebisearch) pro - Network accessline 26
ABSTRACT = {The EMBL-EBI search and sequence analysis tools frameworks provide integrated access to EMBL-EBI’s data resources and core bioinformatics analytical tools. EBI Search (https://www.ebi.ac.uk/ebisearch) provides a full-text search - Network accessline 27
AUTHOR = {Madeira, Fábio and Pearce, Matt and Tivey, Adrian R N and Basutkar, Prasad and Lee, Joon and Edbali, Ossama and Madhusoodanan, Nandana and Kolesnikov, Anton and Lopez, Rodrigo}, URL = {https://doi.org/10.1093/nar/gkac240}, DAT - Network accessline 28
URL = {https://doi.org/10.1093/nar/gkac240}, - Network accessline 29
DATE = {2022-07}, DOI = {10.1093/nar/gkac240}, EPRINT = {https://academic.oup.com/nar/article-pdf/50/W1/W276/44376102/gkac240.pdf}, - Network accessline 30
DOI = {10.1093/nar/gkac240}, EPRINT = {https://academic.oup.com/nar/article-pdf/50/W1/W276/44376102/gkac240.pdf}, ISSN = {0305-1048}, - Network accessline 31
EPRINT = {https://academic.oup.com/nar/article-pdf/50/W1/W276/44376102/gkac240.pdf},
skills/protein_sequence_similarity_search/scripts/mmseqs2_search.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 42
MAX_ALIGNMENT_HITS = 300 POLLING_TIMEOUT = 15 * 60 # 15 minutes. COLABFOLD_HOST = "https://api.colabfold.com" - Network accessline 43
POLLING_TIMEOUT = 15 * 60 # 15 minutes. COLABFOLD_HOST = "https://api.colabfold.com" FASTA_COLUMNS = [ - Network accessline 44
COLABFOLD_HOST = "https://api.colabfold.com" - Network accessline 216
# States below are taken from the original ColabFold code: # https://github.com/sokrypton/ColabFold/blob/main/colabfold/colabfold.py:201 - Network accessline 217
# https://github.com/sokrypton/ColabFold/blob/main/colabfold/colabfold.py:201
skills/protein_sequence_similarity_search/scripts/uniprot_blast.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 68
DEFAULT_EVALUE = 1000 POLLING_TIMEOUT = 15 * 60 # 15 minutes. BASE_URL = "https://www.ebi.ac.uk/Tools/services/rest/ncbiblast" - Network accessline 69
POLLING_TIMEOUT = 15 * 60 # 15 minutes. BASE_URL = "https://www.ebi.ac.uk/Tools/services/rest/ncbiblast" CLIENT = http_client.HttpClient(BASE_URL, qps=2) - Network accessline 70
BASE_URL = "https://www.ebi.ac.uk/Tools/services/rest/ncbiblast" - Access to secretsline 143
[Credential-related source omitted] - Access to secretsline 269
[Credential-related source omitted]
skills/pubchem_database/SKILL.md
- Network accessline 16
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://pubchem.ncbi.nlm.nih.gov/docs/citation-guidelines and - Network accessline 17
the user to check the terms at https://pubchem.ncbi.nlm.nih.gov/docs/citation-guidelines and https://pubchem.ncbi.nlm.nih.gov/docs/pug-rest, then (2) create the file - Network accessline 18
https://pubchem.ncbi.nlm.nih.gov/docs/citation-guidelines and - Network accessline 19
https://pubchem.ncbi.nlm.nih.gov/docs/pug-rest, then (2) create the file
skills/pubchem_database/references/citation.bib
- Network accessline 1
@ARTICLE{Kim2025, ABSTRACT = {PubChem (https://pubchem.ncbi.nlm.nih.gov) is a large and highly-integrated public chemical database resource at NIH. In the past two years, significant updates were made to PubChem. With additions from over - Network accessline 2
ABSTRACT = {PubChem (https://pubchem.ncbi.nlm.nih.gov) is a large and highly-integrated public chemical database resource at NIH. In the past two years, significant updates were made to PubChem. With additions from over 130 new sources, Pub - Network accessline 3
AUTHOR = {Kim, Sunghwan and Chen, Jie and Cheng, Tiejun and Gindulyte, Asta and He, Jia and He, Siqian and Li, Qingliang and Shoemaker, Benjamin A and Thiessen, Paul A and Yu, Bo and Zaslavsky, Leonid and Zhang, Jian and Bolton, Evan E}, - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkae1059}, - Network accessline 5
DATE = {2025-01}, DOI = {10.1093/nar/gkae1059}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D1516/60743708/gkae1059.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkae1059}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D1516/60743708/gkae1059.pdf}, ISSN = {1362-4962}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D1516/60743708/gkae1059.pdf},
skills/pubchem_database/references/endpoints.md
- Network accessline 8
**Base URL:** `https://pubchem.ncbi.nlm.nih.gov/rest/pug` - Network accessline 46
* **Properties by CID (JSON)**: `https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/2244/property/MolecularWeight,MolecularFormula/JSON` - Network accessline 47
* **Mass Range Search (JSON)**: `https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/molecular_weight/range/400.0/400.05/cids/JSON` - Network accessline 48
* **Patents by SID (JSON)**: `https://pubchem.ncbi.nlm.nih.gov/rest/pug/substance/sid/137349406/xrefs/PatentID/JSON` - Network accessline 57
**Base URL:** `https://pubchem.ncbi.nlm.nih.gov/rest/pug_view` - Network accessline 59
The standard structure for retrieving specific sections: `https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/<cid>/JSON?heading=<Section+Heading>` - Network accessline 60
`https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/<cid>/JSON?heading=<Section+Heading>`
skills/pubchem_database/scripts/pubchem_api.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 37
PUBCHEM_BASE_URL = "https://pubchem.ncbi.nlm.nih.gov/rest" - Network accessline 43
try: resp = _CLIENT.fetch(url, method=method, data=data) - Network accessline 44
resp = _CLIENT.fetch(url, method=method, data=data)
skills/pubmed_database/SKILL.md
- Network accessline 18
2. **User Notification**: If .licenses/pubmed_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://pubmed.ncbi.nlm.nih.gov/disclaimer/ - Network accessline 19
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://pubmed.ncbi.nlm.nih.gov/disclaimer/ and https://www.ncbi.nlm.nih.gov/home/about/policies/ and to always check - Network accessline 20
the user to check the terms at https://pubmed.ncbi.nlm.nih.gov/disclaimer/ - Network accessline 21
and https://www.ncbi.nlm.nih.gov/home/about/policies/ and to always check - Access to secretsline 26
[Credential-related source omitted] - Network accessline 27
to 10 requests/second. The skill works without it, but a key is recommended if the user plans many queries or encounters a 429 error. You can register for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You - Network accessline 28
if the user plans many queries or encounters a 429 error. You can register for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You **MUST** use the safe credentials protocol in the `credentials` skill to - Network accessline 29
for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You - Access to secretsline 46
[Credential-related source omitted]
skills/pubmed_database/references/advanced-linking.md
- Network accessline 42
This list covers the most common `pubmed → X` links. For the full list of all ELink linknames across all NCBI databases, see the [NCBI Entrez Links catalog](https://eutils.ncbi.nlm.nih.gov/entrez/query/static/entrezlinks.html). - Network accessline 44
[NCBI Entrez Links catalog](https://eutils.ncbi.nlm.nih.gov/entrez/query/static/entrezlinks.html).
skills/pubmed_database/references/citation.bib
- Network accessline 1
@ARTICLE{Sayers2025, ABSTRACT = {The National Center for Biotechnology Information (NCBI) provides online information resources for biology, including the GenBank® nucleic acid sequence repository and the PubMed® repository of citations a - Network accessline 2
ABSTRACT = {The National Center for Biotechnology Information (NCBI) provides online information resources for biology, including the GenBank® nucleic acid sequence repository and the PubMed® repository of citations and abstracts published - Network accessline 3
AUTHOR = {Sayers, Eric W and Beck, Jeffrey and Bolton, Evan E and Brister, J Rodney and Chan, Jessica and Connor, Ryan and Feldgarden, Michael and Fine, Anna M and Funk, Kathryn and Hoffman, Jinna and Kannan, Sivakumar and Kelly, Christophe - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkae979}, - Network accessline 5
DATE = {2025-01}, DOI = {10.1093/nar/gkae979}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D20/60586411/gkae979.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkae979}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D20/60586411/gkae979.pdf}, ISSN = {1362-4962}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D20/60586411/gkae979.pdf},
skills/pubmed_database/references/cross-database-linking.md
skills/pubmed_database/references/search-and-discovery.md
skills/pubmed_database/scripts/pubmed_api.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 45
EUTILS_BASE = "https://eutils.ncbi.nlm.nih.gov" - Network accessline 46
PMC_BIOC_BASE = ( "https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json" ) - Network accessline 47
"https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json" - Access to secretsline 58
[Credential-related source omitted] - Access to secretsline 67
[Credential-related source omitted] - Access to secretsline 79
[Credential-related source omitted] - Access to secretsline 80
[Credential-related source omitted] - Access to secretsline 81
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Access to secretsline 87
[Credential-related source omitted] - Network accessline 127
try: data_bytes = urllib.parse.urlencode(params).encode("utf-8") resp = get_eutils_client().fetch(url, method="POST", data=data_bytes) - Network accessline 128
data_bytes = urllib.parse.urlencode(params).encode("utf-8") resp = get_eutils_client().fetch(url, method="POST", data=data_bytes) return resp.text - Network accessline 129
resp = get_eutils_client().fetch(url, method="POST", data=data_bytes) - Access to secretsline 636
[Credential-related source omitted]
skills/pymol/SKILL.md
- Network accessline 18
2. **User Notification**: If .licenses/pymol_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the license at https://www.pymol.org/, then (2) create the file - Network accessline 19
in the workspace root directory then (1) prominently notify the user to check the license at https://www.pymol.org/, then (2) create the file recording the notification text and timestamp. - Network accessline 20
check the license at https://www.pymol.org/, then (2) create the file - Access to secretsline 94
[Credential-related source omitted]
skills/pymol/references/PYMOL_REFERENCE.md
- Network accessline 138
container will time out. 2. **Selection case sensitivity** — `"chain a"` is NOT the same as `"chain A"`. 3. **`cmd.fetch()` will fail** — there is no network inside the container. Use - Network accessline 139
2. **Selection case sensitivity** — `"chain a"` is NOT the same as `"chain A"`. 3. **`cmd.fetch()` will fail** — there is no network inside the container. Use `cmd.load()` with pre-downloaded files. - Network accessline 140
3. **`cmd.fetch()` will fail** — there is no network inside the container. Use
skills/quickgo_database/SKILL.md
- Network accessline 28
2. **User Notification**: If .licenses/quickgo_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/QuickGO/ and - Network accessline 29
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/QuickGO/ and https://www.ebi.ac.uk/QuickGO/api/index.html, then (2) create the file - Network accessline 30
the user to check the terms at https://www.ebi.ac.uk/QuickGO/ and - Network accessline 31
https://www.ebi.ac.uk/QuickGO/api/index.html, then (2) create the file
skills/quickgo_database/references/citation.bib
- Network accessline 1
@ARTICLE{Binns2009, ABSTRACT = {Summary: QuickGO is a web-based tool that allows easy browsing of the Gene Ontology (GO) and all associated electronic and manual GO annotations provided by the GO Consortium annotation groups QuickGO has b - Network accessline 2
ABSTRACT = {Summary: QuickGO is a web-based tool that allows easy browsing of the Gene Ontology (GO) and all associated electronic and manual GO annotations provided by the GO Consortium annotation groups QuickGO has been a popular GO brows - Network accessline 3
AUTHOR = {Binns, David and Dimmer, Emily and Huntley, Rachael and Barrell, Daniel and O'Donovan, Claire and Apweiler, Rolf}, URL = {https://doi.org/10.1093/bioinformatics/btp536}, DATE = {2009-11}, - Network accessline 4
URL = {https://doi.org/10.1093/bioinformatics/btp536}, - Network accessline 5
DATE = {2009-11}, DOI = {10.1093/bioinformatics/btp536}, EPRINT = {https://academic.oup.com/bioinformatics/article-pdf/25/22/3045/48997998/bioinformatics_25_22_3045.pdf}, - Network accessline 6
DOI = {10.1093/bioinformatics/btp536}, EPRINT = {https://academic.oup.com/bioinformatics/article-pdf/25/22/3045/48997998/bioinformatics_25_22_3045.pdf}, ISSN = {1367-4803}, - Network accessline 7
EPRINT = {https://academic.oup.com/bioinformatics/article-pdf/25/22/3045/48997998/bioinformatics_25_22_3045.pdf},
skills/quickgo_database/scripts/quickgo_tool.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 36
BASE_URL = "https://www.ebi.ac.uk/QuickGO/services"
skills/reactome_database/SKILL.md
- Network accessline 18
2. **User Notification**: If .licenses/reactome_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://reactome.org/license and - Network accessline 19
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://reactome.org/license and https://reactome.org/cite, then (2) create the file recording the - Network accessline 20
the user to check the terms at https://reactome.org/license and - Network accessline 21
https://reactome.org/cite, then (2) create the file recording the - Network accessline 26
Reactome is a free, open-source, curated pathway database. This skill wraps both the **Analysis Service** (`https://reactome.org/AnalysisService/`) and the - Network accessline 27
the **Analysis Service** (`https://reactome.org/AnalysisService/`) and the - Network accessline 28
**Content Service** (`https://reactome.org/ContentService/`) providing pathway
skills/reactome_database/references/api_reference.md
- Network accessline 3
Base URL: `https://reactome.org/AnalysisService`
skills/reactome_database/references/citation.bib
- Network accessline 1
@ARTICLE{Ragueneau2026, ABSTRACT = {The Reactome Knowledgebase (https://reactome.org) is a freely accessible, expert-curated, open-source, and open-data resource that describes human biology in molecular detail. It spans normal physiology - Network accessline 2
ABSTRACT = {The Reactome Knowledgebase (https://reactome.org) is a freely accessible, expert-curated, open-source, and open-data resource that describes human biology in molecular detail. It spans normal physiology as well as disease mechan - Network accessline 3
AUTHOR = {Ragueneau, Eliot and Gong, Chuqiao and Sinquin, Pierre and Sevilla, Cristoffer and Beavers, Deidre and Grentner, Alexander and Griss, Johannes and Hogue, Gregory F J and Li, Nancy T and Matthews, Lisa and May, Bruce and Milacic, M - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkaf1223}, - Network accessline 5
DATE = {2026-01}, DOI = {10.1093/nar/gkaf1223}, EPRINT = {https://academic.oup.com/nar/article-pdf/54/D1/D673/65369785/gkaf1223.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkaf1223}, EPRINT = {https://academic.oup.com/nar/article-pdf/54/D1/D673/65369785/gkaf1223.pdf}, ISSN = {1362-4962}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/54/D1/D673/65369785/gkaf1223.pdf},
skills/reactome_database/scripts/reactome_analysis.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 17
Provides subcommands covering all endpoints of the Reactome Analysis Service (https://reactome.org/AnalysisService/) and key Content Service endpoints - Network accessline 18
(https://reactome.org/AnalysisService/) and key Content Service endpoints - Network accessline 19
(https://reactome.org/ContentService/). Supports pathway enrichment analysis, - Network accessline 41
ANALYSIS_BASE_URL = "https://reactome.org/AnalysisService" - Network accessline 42
CONTENT_BASE_URL = "https://reactome.org/ContentService" - Network accessline 43
_CLIENT = http_client.HttpClient("https://reactome.org/", qps=1)
skills/string_database/SKILL.md
- Network accessline 19
2. **User Notification**: If .licenses/string_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://string-db.org/cgi/access, then (2) - Network accessline 20
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://string-db.org/cgi/access, then (2) create the file recording the notification text and timestamp. - Network accessline 21
the user to check the terms at https://string-db.org/cgi/access, then (2)
skills/string_database/references/valuesranks.md
- Access to secretsline 13
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 43
[Credential-related source omitted] - Access to secretsline 44
[Credential-related source omitted]
skills/string_database/scripts/string_cli.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 37
CALLER_IDENTITY = 'google-science-skills' URL_TEMPLATE = ( 'https://version-{api_version}-0.string-db.org/api/{format_type}/{endpoint}' - Network accessline 38
URL_TEMPLATE = ( 'https://version-{api_version}-0.string-db.org/api/{format_type}/{endpoint}' ) - Network accessline 39
'https://version-{api_version}-0.string-db.org/api/{format_type}/{endpoint}' - Access to secretsline 205
[Credential-related source omitted] - Access to secretsline 216
[Credential-related source omitted] - Network accessline 226
global _CLIENT base_url = f'https://version-{args.api_version}-0.string-db.org/' - Network accessline 227
base_url = f'https://version-{args.api_version}-0.string-db.org/' - Access to secretsline 297
[Credential-related source omitted] - Access to secretsline 303
[Credential-related source omitted] - Access to secretsline 340
[Credential-related source omitted]
skills/ucsc_conservation_and_tfbs/SKILL.md
- Network accessline 27
does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://genome.ucsc.edu/conditions.html and - Network accessline 28
notify the user to check the terms at https://genome.ucsc.edu/conditions.html and https://genome.ucsc.edu/goldenPath/help/api.html, then (2) create the file - Network accessline 29
https://genome.ucsc.edu/conditions.html and - Network accessline 30
https://genome.ucsc.edu/goldenPath/help/api.html, then (2) create the file
skills/ucsc_conservation_and_tfbs/scripts/get_conservation.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 31
UCSC_API_URL = "https://api.genome.ucsc.edu/getData/track" - Network accessline 32
CLIENT = http_client.HttpClient("https://api.genome.ucsc.edu/", qps=0.05)
skills/ucsc_conservation_and_tfbs/scripts/get_tfbs.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 31
UCSC_API_URL = "https://api.genome.ucsc.edu/getData/track" - Network accessline 33
api_client = http_client.HttpClient("https://api.genome.ucsc.edu/", qps=0.05)
skills/ucsc_conservation_and_tfbs/scripts/list_tracks.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 31
UCSC_API_URL = "https://api.genome.ucsc.edu/list/tracks" - Network accessline 33
api_client = http_client.HttpClient("https://api.genome.ucsc.edu/", qps=0.05)
skills/unibind_database/SKILL.md
- Network accessline 22
2. **User Notification**: If .licenses/unibind_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://unibind.uio.no/ and - Network accessline 23
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://unibind.uio.no/ and https://unibind.uio.no/api/overview, then (2) create the file recording the - Network accessline 24
the user to check the terms at https://unibind.uio.no/ and - Network accessline 25
https://unibind.uio.no/api/overview, then (2) create the file recording the
skills/unibind_database/scripts/unibind_api.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 37
CLIENT = http_client.HttpClient(f"https://unibind.uio.no/", qps=20.0) - Network accessline 231
# URL format: https://unibind.uio.no/api/v1/{endpoint}/ID/
skills/uniprot_database/SKILL.md
- Network accessline 17
2. **User Notification**: If .licenses/uniprot_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.uniprot.org/help/license and - Network accessline 18
already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.uniprot.org/help/license and https://www.uniprot.org/help/api_queries, then (2) create the file recording - Network accessline 19
the user to check the terms at https://www.uniprot.org/help/license and - Network accessline 20
https://www.uniprot.org/help/api_queries, then (2) create the file recording - Network accessline 32
- **Use the Wrapper**: Always use the provided Python scripts (e.g., `scripts/uniprot_tools.py`) rather than constructing custom curl requests. - Network accessline 33
`scripts/uniprot_tools.py`) rather than constructing custom curl requests. - Network accessline 140
PREFIX up: <http://purl.uniprot.org/core/> - Network accessline 141
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> - Network accessline 154
PREFIX up: <http://purl.uniprot.org/core/> - Network accessline 155
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> - Network accessline 157
SELECT ?uniparc ?val WHERE { GRAPH <http://sparql.uniprot.org/uniparc> { - Network accessline 158
GRAPH <http://sparql.uniprot.org/uniparc> { - Network accessline 174
PREFIX up: <http://purl.uniprot.org/core/> - Network accessline 175
PREFIX taxon: <http://purl.uniprot.org/taxonomy/> - Network accessline 235
uv run scripts/uniprot_tools.py sparql 'PREFIX up: <http://purl.uniprot.org/core/> SELECT ?protein WHERE { ?protein a up:Protein ; up:reviewed true . } LIMIT 5' - Network accessline 285
- [Search Query Fields Documentation](references/search_query_fields.md) - [ID Mapping Documentation](references/id_mapping_documentation.md) - [UniProt Evidence Docs](https://www.uniprot.org/help/evidences) - Network accessline 286
- [ID Mapping Documentation](references/id_mapping_documentation.md) - [UniProt Evidence Docs](https://www.uniprot.org/help/evidences) - **Underlying API Endpoints** (Used by `scripts/uniprot_tools.py`): - Network accessline 287
- [UniProt Evidence Docs](https://www.uniprot.org/help/evidences)
skills/uniprot_database/references/citation.bib
- Network accessline 1
@ARTICLE{Consortium2025, ABSTRACT = {The aim of the UniProt Knowledgebase (UniProtKB; https://www.uniprot.org/) is to provide users with a comprehensive, high-quality and freely accessible set of protein sequences annotated with functiona - Network accessline 2
ABSTRACT = {The aim of the UniProt Knowledgebase (UniProtKB; https://www.uniprot.org/) is to provide users with a comprehensive, high-quality and freely accessible set of protein sequences annotated with functional information. In this publ - Network accessline 3
AUTHOR = {{The UniProt Consortium}}, URL = {https://doi.org/10.1093/nar/gkae1010}, DATE = {2025-01}, - Network accessline 4
URL = {https://doi.org/10.1093/nar/gkae1010}, - Network accessline 5
DATE = {2025-01}, DOI = {10.1093/nar/gkae1010}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D609/60719276/gkae1010.pdf}, - Network accessline 6
DOI = {10.1093/nar/gkae1010}, EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D609/60719276/gkae1010.pdf}, ISSN = {1362-4962}, - Network accessline 7
EPRINT = {https://academic.oup.com/nar/article-pdf/53/D1/D609/60719276/gkae1010.pdf},
skills/uniprot_database/references/id_mapping_databases.md
- Network accessline 6
**Source:** `https://rest.uniprot.org/configure/idmapping/fields`
skills/uniprot_database/references/sparql_examples.md
- Network accessline 10
PREFIX up: <http://purl.uniprot.org/core/> - Network accessline 11
PREFIX taxon: <http://purl.uniprot.org/taxonomy/> - Network accessline 12
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> - Network accessline 13
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> - Network accessline 14
PREFIX skos: <http://www.w3.org/2004/02/skos/core#> - Network accessline 42
up:reviewed true ; rdfs:seeAlso ?pdbLink . ?pdbLink up:database <http://purl.uniprot.org/database/PDB> . - Network accessline 43
rdfs:seeAlso ?pdbLink . ?pdbLink up:database <http://purl.uniprot.org/database/PDB> . } - Network accessline 44
?pdbLink up:database <http://purl.uniprot.org/database/PDB> . - Network accessline 55
up:reviewed true ; up:recommendedName/up:fullName ?name ; up:classifiedWith <http://purl.uniprot.org/keywords/238> . # DNA-binding - Network accessline 56
up:recommendedName/up:fullName ?name ; up:classifiedWith <http://purl.uniprot.org/keywords/238> . # DNA-binding } - Network accessline 57
up:classifiedWith <http://purl.uniprot.org/keywords/238> . # DNA-binding - Network accessline 65
PREFIX up: <http://purl.uniprot.org/core/> - Network accessline 66
PREFIX taxon: <http://purl.uniprot.org/taxonomy/> - Network accessline 77
PREFIX up: <http://purl.uniprot.org/core/> - Network accessline 89
PREFIX up: <http://purl.uniprot.org/core/> - Network accessline 90
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> - Network accessline 94
up:reviewed true ; rdfs:seeAlso ?pdbLink . ?pdbLink up:database <http://purl.uniprot.org/database/PDB> . - Network accessline 95
rdfs:seeAlso ?pdbLink . ?pdbLink up:database <http://purl.uniprot.org/database/PDB> . } - Network accessline 96
?pdbLink up:database <http://purl.uniprot.org/database/PDB> . - Network accessline 112
SERVICE <https://query.wikidata.org/sparql> {
skills/uniprot_database/scripts/uniprot_tools.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 42
BASE_URL = "https://rest.uniprot.org" - Network accessline 43
SPARQL_URL = "https://sparql.uniprot.org/sparql" - Network accessline 76
if as_json: headers |= {"Accept": "application/json"} response = CLIENT.fetch(url, headers=headers, method=method, data=data) - Network accessline 77
headers |= {"Accept": "application/json"} response = CLIENT.fetch(url, headers=headers, method=method, data=data) decoded_data = _get_decompressed_data(response) - Network accessline 78
response = CLIENT.fetch(url, headers=headers, method=method, data=data) - Network accessline 124
while next_url: full_url = _add_params_to_url(next_url, current_params) resp = CLIENT.fetch(full_url) - Network accessline 125
full_url = _add_params_to_url(next_url, current_params) resp = CLIENT.fetch(full_url) if total_results is None: - Network accessline 126
resp = CLIENT.fetch(full_url) - Network accessline 220
url = f"{BASE_URL}/{dataset}/search" params = {"query": query, "size": 1, "format": "json"} resp = CLIENT.fetch(_add_params_to_url(url, params)) - Network accessline 221
params = {"query": query, "size": 1, "format": "json"} resp = CLIENT.fetch(_add_params_to_url(url, params)) return int(_get_header(resp, "X-Total-Results") or 0) - Network accessline 222
resp = CLIENT.fetch(_add_params_to_url(url, params))
skills/uv/SKILL.md
skills/workflow_skill_creator/references/cli_script_template.py
- Executable scriptline 1
Executable file - Network accessline 5
# You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 6
# # http://www.apache.org/licenses/LICENSE-2.0 # - Network accessline 7
# http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 49
BASE_URL = 'https://api.example.com/v1'
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 3 facts
- Contacts purl.obolibrary.org, which SKILL.md, the README and the plugin manifest do not mentionembl_ebi_ols/scripts/ols_utils.py:79High confidence
- Contacts factorbook.api.wenglab.org, which SKILL.md, the README and the plugin manifest do not mentionencode_ccres_database/scripts/screen_api.py:35High confidence
- Contacts screen-v2.wenglab.org, which SKILL.md, the README and the plugin manifest do not mentionencode_ccres_database/scripts/screen_api.py:40High confidence
Signal confidence: 497 facts
- Network access in prose of the SKILL.mdalphafold_database_fetch_and_analyze/SKILL.md:18Low confidence
- Network access in prose of the SKILL.mdalphafold_database_fetch_and_analyze/SKILL.md:19Low confidence
- Network access in prose of the SKILL.mdalphafold_database_fetch_and_analyze/SKILL.md:20Low confidence
- Network access in prose of the SKILL.mdalphafold_database_fetch_and_analyze/SKILL.md:32Low confidence
- Network access in prose of the SKILL.mdalphafold_database_fetch_and_analyze/SKILL.md:33Low confidence
- Network access in prose of the SKILL.mdalphafold_database_fetch_and_analyze/SKILL.md:34Low confidence
- Executable script in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/analyze_pae.py:1Low confidence
- Network access in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/analyze_pae.py:5Low confidence
- Network access in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/analyze_pae.py:6Low confidence
- Network access in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/analyze_pae.py:7Low confidence
- Executable script in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/analyze_plddt.py:1Low confidence
- Network access in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/analyze_plddt.py:5Low confidence
- Network access in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/analyze_plddt.py:6Low confidence
- Network access in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/analyze_plddt.py:7Low confidence
- Executable script in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/fetch_structure.py:1Low confidence
- Network access in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/fetch_structure.py:5Low confidence
- Network access in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/fetch_structure.py:6Low confidence
- Network access in a comment of a file that runsalphafold_database_fetch_and_analyze/scripts/fetch_structure.py:7Low confidence
- Network access in code of a file that runsalphafold_database_fetch_and_analyze/scripts/fetch_structure.py:30High confidence
- Network access in code of a file that runsalphafold_database_fetch_and_analyze/scripts/fetch_structure.py:35High confidence
- Network access in code of a file that runsalphafold_database_fetch_and_analyze/scripts/fetch_structure.py:36High confidence
- Network access in prose of the SKILL.mdalphagenome_atlas_website_links/SKILL.md:17Low confidence
- Network access in prose of the SKILL.mdalphagenome_atlas_website_links/SKILL.md:18Low confidence
- Network access in prose of the SKILL.mdalphagenome_atlas_website_links/SKILL.md:20Low confidence
- Network access in prose of the SKILL.mdalphagenome_atlas_website_links/SKILL.md:23Low confidence
- Network access in prose of the SKILL.mdalphagenome_atlas_website_links/SKILL.md:24Low confidence
- Network access in prose of the SKILL.mdalphagenome_atlas_website_links/SKILL.md:25Low confidence
- Network access in prose of the SKILL.mdalphagenome_atlas_website_links/SKILL.md:196Low confidence
- Network access in prose of the SKILL.mdalphagenome_atlas_website_links/SKILL.md:197Low confidence
- Executable script in a comment of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:1Low confidence
- Network access in a comment of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:5Low confidence
- Network access in a comment of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:6Low confidence
- Network access in a comment of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:7Low confidence
- Network access in prose of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:17Low confidence
- Network access in prose of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:19Low confidence
- Network access in code of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:44High confidence
- Access to secrets in prose of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:402Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuealphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:403Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuealphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:405Low confidence
- Access to secrets in code of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:406High confidence
- Access to secrets in code of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:408High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuealphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:412Low confidence
- Network access in code of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:413High confidence
- Network access in code of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:414High confidence
- Network access in code of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:415High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuealphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:420Low confidence
- Network access in code of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:423High confidence
- Network access in code of a file that runsalphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:424High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuealphagenome_atlas_website_links/scripts/alphagenome_atlas_links.py:431Low confidence
- Network access in prose of the SKILL.mdalphagenome_single_variant_analysis/SKILL.md:21Low confidence
and 447 more
Only the first 500 facts are listed.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/alphafold_database_fetch_and_analyze/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/alphafold_database_fetch_and_analyze/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/alphafold_database_fetch_and_analyze/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/alphafold_database_fetch_and_analyze/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/alphafold_database_fetch_and_analyze/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/alphafold_database_fetch_and_analyze/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/google-deepmind-science-skills/)