CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is tooluniverse-binder-discovery in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 phased workflow with strong validation checkpoints and fallback chains. Its main gap is progressive disclosure: the five referenced reference files do not exist in the bundle, so the promised detail layer is unverifiable.

Suggestions

Create the referenced bundle files (WORKFLOW_DETAILS.md, TOOLS_REFERENCE.md, REPORT_TEMPLATE.md, EXAMPLES.md, CHECKLIST.md) or remove the links, since none exist in the references/ directory.

Consolidate the repeated 'requires NVIDIA_API_KEY' notes into one Runtime Notes section instead of restating them inline in Phase 0, Phase 1, and Phase 4.

Move the bulk of per-tool parameter reference inline in the phase sections into TOOLS_REFERENCE.md, keeping SKILL.md as a lean overview that points out.

DimensionReasoningScore

Conciseness

Mostly efficient with direct tool calls and minimal padding, though the NVIDIA_API_KEY notes are repeated across phases and the Key Principles list partly restates later sections.

4 / 5

Actionability

Fully executable — named tool calls with real parameters, copy-paste code blocks, and concrete thresholds (IC50/Ki/Kd < 10 uM, similarity 70-85%, QED > 0.3) covering common cases.

5 / 5

Workflow Clarity

Clear phased sequence (0–7) with explicit validation checkpoints — Phase 0 tool verification, reference-inhibitor docking to validate pocket geometry — plus decision points, fallback chains, and an evidence-tier checklist.

5 / 5

Progressive Disclosure

Good overview with well-signaled one-level-deep references (WORKFLOW_DETAILS, TOOLS_REFERENCE, REPORT_TEMPLATE, EXAMPLES, CHECKLIST), but those referenced files are not present in the bundle and some inline tool reference content could reside in TOOLS_REFERENCE.md.

4 / 5

Total

18

/

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, third-person description that pairs a comprehensive capability list with concrete 'Use for...' trigger guidance. It is specific, well-triggered, and clearly scoped with little conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'druggability assessment, known-ligand mining (ChEMBL, BindingDB), similarity expansion, ADMET filtering, and synthesis feasibility' — giving comprehensive coverage of the workflow.

5 / 5

Completeness

Explicitly answers both what (the screening pipeline) and when via the concrete 'Use for hit identification, virtual screening, target-to-compounds workflows, and lead-finding before commit-to-medchem' trigger clause.

5 / 5

Trigger Term Quality

Strong natural trigger phrases ('hit identification', 'virtual screening', 'lead-finding', 'target-to-compounds workflows') users would actually say, though a few common synonyms could broaden coverage.

4 / 5

Distinctiveness Conflict Risk

Clear niche — small-molecule binder discovery for protein targets — with distinct triggers and minimal overlap risk against unrelated skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 5 missing

Warning

Total

15

/

16

Passed

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

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.