ligandmpnn

Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be respected, or to get threaded designed-sequence PDBs out of any MPNN run.

Quality

88%

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

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.

Highly actionable content with a complete executable quick-start, explicit validation, and genuinely non-obvious gotchas. The only costs are version-pinned fix material taking space and everything living inline in one file.

Dimension	Reasoning	Score
Conciseness	Lean and free of explanations of known concepts, but two full sections are consumed by version-sensitive fixes (the numpy >=1.24 sed patch and the py3.11 ProDy source build) that will age and add tokens.	4 / 5
Actionability	The bash block is copy-paste ready with exact clone, patch, checkpoint, and run commands; residue-selection syntax, output file layout, and an error table with exact fixes cover the common cases.	5 / 5
Workflow Clarity	The run block encodes the full ordered sequence (install → clone → patch → fetch checkpoints → run), the ligand_confidence check is an explicit post-run validation with a feedback loop ("fix the input, do not trust the sequences"), and the errors table provides recovery steps.	5 / 5
Progressive Disclosure	Well-organized single file with clear section headers and tables and no nested references, but at roughly 100 lines with all detail (gotchas, error catalog) inlined it exceeds the simple-skill size guide; some of that detail could live in a reference file.	4 / 5
	Total	18 / 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 strong description: concrete, third-person, and explicitly triggered with three distinct use cases. The only weaknesses are incomplete synonym coverage and a minor overlap risk with sibling MPNN skills from the threaded-PDB trigger.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Inverse-fold a backbone with ligand, nucleic-acid, and metal context", "redesign the residues lining a binding pocket", "design metal-coordinating sites", "get threaded designed-sequence PDBs" — covering the tool's capabilities comprehensively in third person.	5 / 5
Completeness	Explicitly answers what ("Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN") and when ("Reach for this skill to redesign the residues lining a binding pocket ... or to design metal-coordinating sites ... or to get threaded designed-sequence PDBs") with concrete triggers.	5 / 5
Trigger Term Quality	Natural domain phrasings like "binding pocket", "bound small molecule or cofactor", "metal-coordinating sites", and "designed-sequence PDBs" are present, but common variations such as "sequence design", "active site", or the .pdb extension are missing.	4 / 5
Distinctiveness Conflict Risk	The ligand/metal inverse-folding niche is unmistakable, but the trigger "threaded designed-sequence PDBs out of any MPNN run" overlaps with what a vanilla proteinmpnn skill would also claim.	4 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/claude-science/ligandmpnn/SKILL.md
Commit: a16301c

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.