tooluniverse-peptide-target-deorphanization

Find the real protein target(s) of a peptide from its sequence — peptide target deorphanization / off-target identification, for ANY target class (GPCR, ion channel, protease, cytokine/growth-factor receptor, enzyme, integrin), not only GPCRs. Use when a peptide has a phenotype but does not bind its hypothesized target, when a peptide binds a target in one species or assay but not another, or to screen candidate targets for an orphan peptide. A target-class router steers a multi-route keyless pipeline (PROSITE/ELM motif, BLAST homology, HGNC/InterPro/GPCRdb/GtoPdb target-family enumeration, OpenTargets phenotype anchor, EnsemblCompara/Alliance cross-species reconciliation) plus optional NVIDIA-NIM co-folding (Boltz2, AlphaFold2-Multimer, OpenFold3) for structural confirmation.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill body with executable scripts, a clear phased workflow, and good progressive disclosure into references/phases.md. Minor gains available from de-duplicating repeated warnings and ensuring every referenced path exists.

Suggestions

De-duplicate the 'name-level guess -> GLP1R' warning and the exendin-4 control result, which each appear multiple times, to tighten conciseness.

Add an explicit per-record validation/retry checkpoint for batch (`--fasta`) mode so the batch workflow matches the verification rigor of the single-peptide path.

Either add the referenced `evals/evals.json` to the bundle or remove the reference, so every signaled navigation target resolves.

Dimension	Reasoning	Score
Conciseness	Mostly lean and dense with executable value per line, but the 'name-level guess -> GLP1R' warning is restated three times and the exendin-4 control result is described twice (script section and validation section), which could be trimmed.	4 / 5
Actionability	Provides fully executable, copy-paste-ready command lines for both scripts with every flag documented (including modes, repeatable args, and fallback behavior), plus a concrete worked validation example.	5 / 5
Workflow Clarity	The six-phase pipeline table, numbered core-reasoning steps, and explicit Phase-0 verification plus co-fold dry-run gating give a clear sequence with most checkpoints present; however batch mode (`--fasta`) lacks an explicit per-record validation/retry step, leaving a minor checkpoint gap.	4 / 5
Progressive Disclosure	Good structure with the body as overview and `references/phases.md` clearly signaled as one-level-deep several times, but the body also references `evals/evals.json` which is not present in the bundle, slightly weakening navigation reliability.	4 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both the capability and the triggering scenarios, with a distinctive niche and minimal conflict risk. Minor tightening of the tool-list jargon would improve trigger-term naturalness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Find the real protein target(s)', 'off-target identification', 'screen candidate targets for an orphan peptide') and names many specific tools (PROSITE/ELM, BLAST, HGNC/InterPro/GPCRdb/GtoPdb, OpenTargets, EnsemblCompara/Alliance, Boltz2/AlphaFold2-Multimer/OpenFold3), giving comprehensive coverage of the capability.	5 / 5
Completeness	Clearly and explicitly answers both what (deorphanize/off-target-identify a peptide's real target via a keyless multi-route pipeline) and when ('Use when a peptide has a phenotype but does not bind its hypothesized target...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases ('a peptide has a phenotype but does not bind its hypothesized target', 'binds a target in one species or assay but not another', 'screen candidate targets for an orphan peptide'), but the dense tool enumeration and acronyms dilute the natural-language trigger coverage somewhat.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (peptide target deorphanization) with distinctive triggers ('orphan peptide', 'phenotype but does not bind hypothesized target', 'binds in one species but not another') that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-peptide-target-deorphanization/SKILL.md
Commit: 1b02920

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.