Name: tooluniverse-peptide-target-deorphanization
Rating: 68 (1 reviews)
Author: mims-harvard

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

82%

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

The canonical home for this skill is tooluniverse-peptide-target-deorphanization in mims-harvard/ToolUniverse

Quality

Content

76%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 highly actionable skill body with executable CLI examples, a clear phased workflow, and well-signaled references to bundle files. It is somewhat verbose with repeated rationale across sections, and one referenced path (evals/evals.json) does not exist in the bundle.

Suggestions

Tighten redundancy: the 'LOOK UP, DON'T GUESS' points, the 'Extra signals' bullets, and the phase table restate the same anti-guessing/tool-list material — consolidate to improve conciseness.

Add an explicit failure-recovery / retry checkpoint for batch FASTA mode in the workflow, since batch operations warrant a feedback loop per the rubric.

Create the referenced evals/evals.json (or remove the reference) so all cited bundle paths resolve and progressive-disclosure navigation is complete.

Dimension	Reasoning	Score
Conciseness	The body is dense and frequently repeats the same anti-guessing rationale and tool lists across the overview, pipeline table, and signal bullets; while accurate and non-pedantic, several sections could be tightened (e.g. the 'LOOK UP, DON'T GUESS' points and 'Extra signals' bullets re-explain concepts already covered by the table).	3 / 5
Actionability	Provides fully executable, copy-paste-ready CLI invocations for both scripts with all flags, modes, and a concrete validated control command, plus specific tool-call sequences in the phase table and references to exact parameter names in phases.md.	5 / 5
Workflow Clarity	A clear six-phase sequence with a phase table, explicit script automation of phases 1–4, evidence tiers, and validation checkpoints (Phase 0 verify, key-gated dry-run); minor gaps in explicit retry/failure recovery loops for the batch FASTA path.	4 / 5
Progressive Disclosure	Good one-level-deep structure: an overview SKILL.md pointing to scripts/ and references/phases.md with clear signaling; however evals/evals.json is referenced but the evals/ directory is absent, a minor navigation gap.	4 / 5
	Total	16 / 20 Passed

Description

88%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 highly specific, complete, and distinctive description that explicitly states both the capability and concrete 'Use when...' triggers, with named tools and target classes. Slightly dense and technical, which marginally limits the naturalness of trigger phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — motif scan, BLAST homology, target-family enumeration, phenotype anchoring, cross-species reconciliation, and co-folding — naming specific tools (PROSITE/ELM, OpenTargets, Boltz2) for comprehensive coverage of the deorphanization workflow.	5 / 5
Completeness	Explicitly answers both 'what' (find real protein target(s) of a peptide via a multi-route keyless pipeline plus optional co-folding) and 'when' (an explicit 'Use when...' clause with three concrete trigger scenarios).	5 / 5
Trigger Term Quality	Contains strong natural trigger phrasing ('peptide has a phenotype but does not bind its hypothesized target', 'binds a target in one species or assay but not another', 'orphan peptide') but leans slightly technical; a few common synonyms a bench scientist might say are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — peptide target deorphanization / off-target identification — with specific triggers (mismatched species binding, non-binding hypothesized target, orphan screening) 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: plugins/tooluniverse/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.