tooluniverse-protein-structural-annotation-pdb

Given a PDB structure, produce a per-residue annotation table: which residues sit at a binding interface (vs a partner chain), which line a ligand pocket, which are buried (core) vs solvent-exposed (surface), and optionally secondary structure. This is the structural track drawn under a DMS heatmap and the structural prior SAE feature drops are read against. Use when you need to anchor a variant-interpretation or DMS analysis to the protein's actual physical context.

Quality

81%

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.

A high-quality, executable scientific skill body with concrete code, a sequenced workflow, an explicit numbering-verification checkpoint, and honest limitations. It is concise and actionable, with only minor verbosity and no bundled reference files to split out.

Suggestions

Move the interpretation table and cross-references into a reference file to improve progressive disclosure and keep SKILL.md a lean overview.

Trim the opening paragraph that restates the description verbatim.

Dimension	Reasoning	Score
Conciseness	Largely lean with executable code blocks and tables that assume domain competence; a few phrases like 'This is the annotation track that anchors...' repeat the description and could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready, fully executable Python calls with realistic arguments, concrete return schemas, and specific downstream snippets (e.g. the by_pos indexing pattern) covering common cases.	5 / 5
Workflow Clarity	Clearly sequenced 5-step workflow with an explicit verification checkpoint (Step 3 landmark assertion), an error-recovery instruction ('Do not silently rebase positions'), and an honest-limitations section covering fragile numbering.	5 / 5
Progressive Disclosure	Well-organized sections with a clean cross-reference table of related tools at one level deep, but all content is inlined in SKILL.md with no separate reference files; minor organization is strong but external split is absent.	4 / 5
	Total	18 / 20 Passed

Description

75%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 anchors a niche scientific workflow (per-residue structural annotation for DMS/variant interpretation) and includes an explicit 'Use when' trigger. It is third-person and concrete, with only minor gaps in trigger synonyms and output specificity.

Suggestions

Add natural synonyms/file extensions (e.g. '.pdb', 'per-residue annotation', 'RSA / solvent exposure') to broaden trigger matching.

Make the output artifact explicit (e.g. 'produces a per-residue annotation table keyed by canonical residue number').

Tighten the 'Use when' clause with one more concrete scenario such as 'Use when labeling a DMS heatmap with structural context'.

Dimension	Reasoning	Score
Specificity	Names the domain (PDB structural annotation) and several concrete actions — interface detection, ligand-pocket lining, buried/exposed classification, optional secondary structure — with minor gaps such as leaving the exact output format implicit.	4 / 5
Completeness	Clearly states what it does (per-residue annotation table) and includes an explicit 'Use when...' trigger clause, but the trigger is somewhat general and could name more specific situations.	4 / 5
Trigger Term Quality	Includes natural user-facing phrases like 'PDB structure', 'binding interface', 'ligand pocket', 'DMS heatmap', and 'variant-interpretation', though it omits common synonyms or file extensions like .pdb or 'per-residue'.	4 / 5
Distinctiveness Conflict Risk	The niche is clearly specific to PDB-based per-residue structural annotation tied to DMS analysis, with low overlap risk against generic structure tools; only minor adjacency to related biophysics skills.	4 / 5
	Total	16 / 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: plugin/skills/tooluniverse-protein-structural-annotation-pdb/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.