Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mims-harvard/tooluniverse-gpcr-structural-pharmacology
GPCR receptor pharmacology — agonist/antagonist/inverse-agonist/biased-agonist classification, GPCRdb structural data, receptor-ligand binding analysis, antibody-target interface (SAbDab).
Passed 8 of 14 test cases with the skill, and 7 of 14 without it.
and 8 more in the full report
6 fixed7 passed either way6 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need to query all human chemokine receptors in GPCRdb. Rather than looking up a numerical family slug ID, what human-readable parameter in GPCRdb_list_proteins allows filtering directly by class name?
| Checked | Without skill | With skill |
|---|---|---|
| The protein_class parameter is named for filtering by human-readable receptor class names. | Missed | Passed |
| chemokine receptors is specified as the parameter value for querying this class. | Missed | Passed |
The instructions your model reads when the skill loads.
GPCR pharmacology: agonist vs antagonist vs inverse agonist vs biased agonist — each has different clinical implications. Biased agonism (preferential G-protein vs β-arrestin signaling) can separate efficacy from side effects; for example, G-protein-biased opioid agonists aim to retain analgesia while reducing β-arrestin-mediated respiratory depression. Always classify retrieved ligands by their pharmacological type, not just their chemical structure. Receptor state (active vs inactive crystal structure) determines which ligands and mutations are interpretable — an inactive-state structure is appropriate for antagonist binding analysis, active-state for agonist-bound complexes. Generic GPCR numbering (Ballesteros-Weinstein) enables cross-receptor mutation comparison; always report positions in this system alongside sequence positions.
LOOK UP DON'T GUESS: never assume GPCRdb entry names (e.g., adrb2_human) or PDB IDs — always use GPCRdb_list_proteins to find the correct entry name and GPCRdb_get_structures to confirm available structures.
Research skill integrating GPCRdb (GPCR receptor biology), SAbDab (antibody structures), and PDBePISA (protein interface analysis) to support structural pharmacology, antibody engineering, and GPCR-targeted drug discovery.
KEY PRINCIPLES:
Apply when user asks:
| Tool | Key Parameters | Notes |
|---|---|---|
GPCRdb_get_protein | protein | GPCRdb entry name (e.g., adrb2_human), NOT gene symbol or UniProt accession |
GPCRdb_list_proteins | family (optional), protein_class (optional) | Lists all GPCRs; filter by family slug (e.g., "adrenoceptors") OR by human-readable class name via protein_class (e.g., "chemokine receptors", "opioid receptors") |
GPCRdb_get_structures | protein (optional), state (optional) | state: "active", "inactive", "intermediate" |
GPCRdb_get_ligands | protein | Returns agonists, antagonists, biased ligands with affinities |
GPCRdb_get_mutations | protein | Returns mutation effects on receptor function and ligand binding |
test cases passed, vs 7 / 14 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.