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

88%

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

77%

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

A highly actionable, clearly sequenced workflow with strong validation checkpoints, but it is somewhat verbose and inlines detailed reference content that the named (but missing) bundle files are meant to hold, weakening progressive disclosure.

Suggestions

Consolidate the repeated NVIDIA_API_KEY notes and NIM runtime timings into a single 'NVIDIA NIM Runtime Notes' section to reduce redundancy across Phase 0 and the runtime notes.

Move the inline tool-call parameter listings and fallback chains into the referenced TOOLS_REFERENCE.md/WORKFLOW_DETAILS.md bundle files so SKILL.md stays a lean overview, and ensure those referenced files actually exist.

Trim any restated guidance (e.g., GenMol/MolMIM usage appears in both Phase 4 and the runtime notes) to keep each instruction appearing once.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with dense tool calls, thresholds, and fallback chains that assume Claude's competence, but ~298 lines with repeated NVIDIA_API_KEY notes and restated GenMol/MolMIM runtime info that could be tightened.	2 / 3
Actionability	Provides executable Python/REST snippets, exact parameter names, similarity thresholds, composite score weights, and evidence tiers that are copy-paste ready, matching the 'fully executable' anchor.	3 / 3
Workflow Clarity	Clear 8-phase sequence with a Phase 0 verification step, explicit fallback chains, decision points, and validation checkpoints (pLDDT guidance, filter-funnel pass/fail counts, dock-reference-first validation).	3 / 3
Progressive Disclosure	Has a well-signaled one-level-deep reference list at the end, but the referenced bundle files (WORKFLOW_DETAILS.md, TOOLS_REFERENCE.md, etc.) are not actually present, and substantial tool-reference/fallback detail that belongs in TOOLS_REFERENCE.md is kept inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, well-scoped description that concretely names capabilities, uses natural trigger phrases, and explicitly states when to use it. It avoids vague fluff and is clearly distinguishable from adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (druggability assessment, known-ligand mining, similarity expansion, ADMET filtering, synthesis feasibility, structure-based and ligand-based screening), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does and includes an explicit 'Use for...' clause naming trigger scenarios, satisfying both the 'what' and 'when' requirements.	3 / 3
Trigger Term Quality	Natural domain phrases a user would actually say ('hit identification', 'virtual screening', 'target-to-compounds workflows', 'lead-finding before commit-to-medchem') give good coverage of real trigger terms.	3 / 3
Distinctiveness Conflict Risk	The small-molecule binder discovery niche with named tool/data sources is clearly distinct and unlikely to trigger for unrelated chemistry skills.	3 / 3
	Total	12 / 12 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: 089eb8e

Reviewed: about 9 hours 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.