Installation
bunx skills add https://github.com/openbio-ai/skills --skill openbio
Authentication
Required: OPENBIO_API_KEY environment variable.
export OPENBIO_API_KEY=your_key_here
Base URL: https://openbio-api.fly.dev/
Quick Start
# List available tools
curl -X GET "https://openbio-api.fly.dev/api/v1/tools" \
-H "X-API-Key: $OPENBIO_API_KEY"
# Get tool schema (always do this first!)
curl -X GET "https://openbio-api.fly.dev/api/v1/tools/{tool_name}" \
-H "X-API-Key: $OPENBIO_API_KEY"
# Invoke tool
curl -X POST "https://openbio-api.fly.dev/api/v1/tools" \
-H "X-API-Key: $OPENBIO_API_KEY" \
-F "tool_name=search_pubmed" \
-F 'params={"query": "CRISPR", "max_results": 5}'
Decision Tree: Which Tools to Use
What do you need?
│
├─ Protein/structure data?
│ └─ Read rules/protein-structure.md
│ → PDB, AlphaFold, UniProt tools
│
├─ Literature search?
│ └─ Read rules/literature.md
│ → PubMed, arXiv, bioRxiv, OpenAlex
│
├─ Genomics/variants?
│ └─ Read rules/genomics.md
│ → Ensembl, GWAS, VEP, GEO
│
├─ Small molecule analysis?
│ └─ Read rules/cheminformatics.md
│ → RDKit, PubChem, ChEMBL
│
├─ Cloning/PCR/assembly?
│ └─ Read rules/molecular-biology.md
│ → Primers, restriction, Gibson, Golden Gate
│
├─ Structure prediction/design?
│ └─ Read rules/structure-prediction.md
│ → Boltz, Chai, ProteinMPNN, LigandMPNN
│
├─ Pathway analysis?
│ └─ Read rules/pathway-analysis.md
│ → KEGG, Reactome, STRING
│
└─ Clinical/drug data?
└─ Read rules/clinical-data.md
→ ClinicalTrials, ClinVar, FDA, Open Targets
Critical Rules
1. Always Check Tool Schema First
# Before invoking ANY tool:
curl -X GET "https://openbio-api.fly.dev/api/v1/tools/{tool_name}" \
-H "X-API-Key: $OPENBIO_API_KEY"
Parameter names vary (e.g., pdb_ids not pdb_id). Check schema to avoid errors.
2. Long-Running Jobs (submit_* tools)
Prediction tools return a job_id. Poll for completion:
# Check status
curl -X GET "https://openbio-api.fly.dev/api/v1/jobs/{job_id}/status" \
-H "X-API-Key: $OPENBIO_API_KEY"
# Get results with download URLs
curl -X GET "https://openbio-api.fly.dev/api/v1/jobs/{job_id}" \
-H "X-API-Key: $OPENBIO_API_KEY"
3. Quality Thresholds
Don't just retrieve data—interpret it:
AlphaFold pLDDT: > 70 = confident, < 50 = disordered
Experimental resolution: < 2.5 Å for binding sites
GWAS p-value: < 5×10⁻⁸ = genome-wide significant
**Tanimoto similarity**: > 0.7 = similar compounds
See individual rule files for detailed thresholds.
Rule Files
Read these for domain-specific knowledge:
| File |
Tools Covered |
| rules/api.md |
Core endpoints, job management |
| rules/protein-structure.md |
PDB, PDBe, AlphaFold, UniProt |
| rules/literature.md |
PubMed, arXiv, bioRxiv, OpenAlex |
| rules/genomics.md |
Ensembl, ENA, Gene, GWAS, GEO |
| rules/cheminformatics.md |
RDKit, PubChem, ChEMBL |
| rules/molecular-biology.md |
Primers, PCR, restriction, assembly |
| rules/structure-prediction.md |
Boltz, Chai, ProteinMPNN, etc. |
| rules/pathway-analysis.md |
KEGG, Reactome, STRING |
| rules/clinical-data.md |
ClinicalTrials, ClinVar, FDA |
Tool Categories Summary
| Category |
Count |
Examples |
| Protein structure |
23 |
fetch_pdb_metadata, get_alphafold_prediction |
| Literature |
14 |
search_pubmed, arxiv_search, biorxiv_search_keywords |
| Genomics |
27 |
lookup_gene, vep_predict, search_gwas_associations_by_trait |
| Cheminformatics |
20+ |
calculate_molecular_properties, chembl_similarity_search |
| Molecular biology |
15 |
design_primers, restriction_digest, assemble_gibson |
| Structure prediction |
15+ |
submit_boltz_prediction, submit_proteinmpnn_prediction |
| Pathway analysis |
24 |
analyze_gene_list, get_string_network |
| Clinical data |
22 |
search_clinical_trials, search_clinvar |
Common Mistakes
- Not checking schemas → Parameter errors
- Ignoring quality metrics → Using unreliable data
- Wrong tool for task → Check decision trees in rule files
- Not polling jobs → Missing prediction results
Tip: When in doubt, search for tools: GET /api/v1/tools/search?q=your_query
1---2name: openbio3description: OpenBio API for biological data access and computational biology tools. Use when: (1) Querying biological databases (PDB, UniProt, ChEMBL, etc.), (2) Searching scientific literature (PubMed, bioRxiv, arXiv), (3) Running structure prediction (Boltz, Chai, ProteinMPNN), (4) Performing pathway/enrichment analysis, (5) Designing molecular biology experiments (primers, cloning), (6) Analyzing variants and clinical data.4---56## Installation78```bash9bunx skills add https://github.com/openbio-ai/skills --skill openbio10```1112## Authentication1314**Required**: `OPENBIO_API_KEY` environment variable.1516```bash17export OPENBIO_API_KEY=your_key_here18```1920**Base URL**: `https://openbio-api.fly.dev/`2122## Quick Start2324```bash25# List available tools26curl -X GET "https://openbio-api.fly.dev/api/v1/tools" \27 -H "X-API-Key: $OPENBIO_API_KEY"2829# Get tool schema (always do this first!)30curl -X GET "https://openbio-api.fly.dev/api/v1/tools/{tool_name}" \31 -H "X-API-Key: $OPENBIO_API_KEY"3233# Invoke tool34curl -X POST "https://openbio-api.fly.dev/api/v1/tools" \35 -H "X-API-Key: $OPENBIO_API_KEY" \36 -F "tool_name=search_pubmed" \37 -F 'params={"query": "CRISPR", "max_results": 5}'38```3940## Decision Tree: Which Tools to Use4142```43What do you need?44│45├─ Protein/structure data?46│ └─ Read rules/protein-structure.md47│ → PDB, AlphaFold, UniProt tools48│49├─ Literature search?50│ └─ Read rules/literature.md51│ → PubMed, arXiv, bioRxiv, OpenAlex52│53├─ Genomics/variants?54│ └─ Read rules/genomics.md55│ → Ensembl, GWAS, VEP, GEO56│57├─ Small molecule analysis?58│ └─ Read rules/cheminformatics.md59│ → RDKit, PubChem, ChEMBL60│61├─ Cloning/PCR/assembly?62│ └─ Read rules/molecular-biology.md63│ → Primers, restriction, Gibson, Golden Gate64│65├─ Structure prediction/design?66│ └─ Read rules/structure-prediction.md67│ → Boltz, Chai, ProteinMPNN, LigandMPNN68│69├─ Pathway analysis?70│ └─ Read rules/pathway-analysis.md71│ → KEGG, Reactome, STRING72│73└─ Clinical/drug data?74 └─ Read rules/clinical-data.md75 → ClinicalTrials, ClinVar, FDA, Open Targets76```7778## Critical Rules7980### 1. Always Check Tool Schema First81```bash82# Before invoking ANY tool:83curl -X GET "https://openbio-api.fly.dev/api/v1/tools/{tool_name}" \84 -H "X-API-Key: $OPENBIO_API_KEY"85```86Parameter names vary (e.g., `pdb_ids` not `pdb_id`). Check schema to avoid errors.8788### 2. Long-Running Jobs (submit_* tools)89Prediction tools return a `job_id`. Poll for completion:90```bash91# Check status92curl -X GET "https://openbio-api.fly.dev/api/v1/jobs/{job_id}/status" \93 -H "X-API-Key: $OPENBIO_API_KEY"9495# Get results with download URLs96curl -X GET "https://openbio-api.fly.dev/api/v1/jobs/{job_id}" \97 -H "X-API-Key: $OPENBIO_API_KEY"98```99100### 3. Quality Thresholds101Don't just retrieve data—interpret it:102103**AlphaFold pLDDT**: > 70 = confident, < 50 = disordered104**Experimental resolution**: < 2.5 Å for binding sites105**GWAS p-value**: < 5×10⁻⁸ = genome-wide significant106**Tanimoto similarity**: > 0.7 = similar compounds107108See individual rule files for detailed thresholds.109110## Rule Files111112Read these for domain-specific knowledge:113114| File | Tools Covered |115|------|---------------|116| [rules/api.md](rules/api.md) | Core endpoints, job management |117| [rules/protein-structure.md](rules/protein-structure.md) | PDB, PDBe, AlphaFold, UniProt |118| [rules/literature.md](rules/literature.md) | PubMed, arXiv, bioRxiv, OpenAlex |119| [rules/genomics.md](rules/genomics.md) | Ensembl, ENA, Gene, GWAS, GEO |120| [rules/cheminformatics.md](rules/cheminformatics.md) | RDKit, PubChem, ChEMBL |121| [rules/molecular-biology.md](rules/molecular-biology.md) | Primers, PCR, restriction, assembly |122| [rules/structure-prediction.md](rules/structure-prediction.md) | Boltz, Chai, ProteinMPNN, etc. |123| [rules/pathway-analysis.md](rules/pathway-analysis.md) | KEGG, Reactome, STRING |124| [rules/clinical-data.md](rules/clinical-data.md) | ClinicalTrials, ClinVar, FDA |125126## Tool Categories Summary127128| Category | Count | Examples |129|----------|-------|----------|130| Protein structure | 23 | fetch_pdb_metadata, get_alphafold_prediction |131| Literature | 14 | search_pubmed, arxiv_search, biorxiv_search_keywords |132| Genomics | 27 | lookup_gene, vep_predict, search_gwas_associations_by_trait |133| Cheminformatics | 20+ | calculate_molecular_properties, chembl_similarity_search |134| Molecular biology | 15 | design_primers, restriction_digest, assemble_gibson |135| Structure prediction | 15+ | submit_boltz_prediction, submit_proteinmpnn_prediction |136| Pathway analysis | 24 | analyze_gene_list, get_string_network |137| Clinical data | 22 | search_clinical_trials, search_clinvar |138139## Common Mistakes1401411. **Not checking schemas** → Parameter errors1422. **Ignoring quality metrics** → Using unreliable data1433. **Wrong tool for task** → Check decision trees in rule files1444. **Not polling jobs** → Missing prediction results145146---147148**Tip**: When in doubt, search for tools: `GET /api/v1/tools/search?q=your_query`
kbarbel640-del