tooluniverse-binder-discovery

Discover novel small-molecule binders for protein targets using structure-based and ligand-based screening. Covers druggability assessment, known-ligand mining (ChEMBL, BindingDB), similarity expansion, ADMET filtering, and synthesis feasibility. Use for hit identification, virtual screening, target-to-compounds workflows, and lead-finding before commit-to-medchem.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%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, actionable multi-phase screening workflow with executable tool calls, validation checkpoints, and fallback chains. The main weakness is progressive disclosure: every referenced bundle file is missing, so the carefully signaled detail documents do not actually exist alongside the skill.

Suggestions

Create the referenced bundle files (WORKFLOW_DETAILS.md, TOOLS_REFERENCE.md, REPORT_TEMPLATE.md, EXAMPLES.md, CHECKLIST.md) or remove the broken links, since progressive disclosure currently points to nonexistent material.

Move the bulk of the inline per-phase tool catalogs and fallback chains into TOOLS_REFERENCE.md, keeping SKILL.md as a tighter overview that links out.

Consolidate the repeated inline NVIDIA_API_KEY disclaimers into a single 'NVIDIA NIM Runtime Notes' note to trim redundancy.

Dimension	Reasoning	Score
Conciseness	Mostly lean — direct tool calls, code blocks, and compact fallback-chain tables with no concept padding — but the repeated inline NVIDIA_API_KEY notes and pLDDT guidance could be trimmed slightly.	4 / 5
Actionability	Highly executable guidance: specific tool calls with parameters (e.g., NvidiaNIM_genmol(smiles=...)), copy-paste Python for PubChem/ChEMBL, and concrete scoring rubrics; a few calls omit full argument lists, leaving minor gaps.	4 / 5
Workflow Clarity	Clear eight-phase sequence with explicit decision points (druggability warning, dock-a-reference-first validation checkpoint) and a filter funnel; validation exists so the batch-operation cap does not apply, though not every phase has an explicit retry loop.	4 / 5
Progressive Disclosure	Section structure and a dedicated Reference Files section with clearly signaled one-level-deep links are good, but all five referenced files (WORKFLOW_DETAILS.md, TOOLS_REFERENCE.md, REPORT_TEMPLATE.md, EXAMPLES.md, CHECKLIST.md) and the references/assets directories are missing, so the offloaded detail content is effectively absent and navigation is broken.	3 / 5
	Total	15 / 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 concretely states capabilities and provides explicit 'Use for...' trigger guidance with natural medchem terminology. Minor synonym coverage gaps in trigger terms keep it just short of perfect.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'druggability assessment, known-ligand mining (ChEMBL, BindingDB), similarity expansion, ADMET filtering, and synthesis feasibility' — with named data sources, giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' ('Discover novel small-molecule binders... Covers...') and 'when' ('Use for hit identification, virtual screening... before commit-to-medchem') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural medchem triggers like 'hit identification, virtual screening, target-to-compounds workflows, and lead-finding before commit-to-medchem' are good, but a few common synonyms (drug discovery, hit-to-lead, lead optimization) are absent.	4 / 5
Distinctiveness Conflict Risk	The 'small-molecule binders for protein targets' niche plus named screening phases and databases is a clear, distinct scope with minimal overlap risk versus sibling skills like tooluniverse-data-wrangling.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-binder-discovery/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.