CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is tooluniverse-protein-structural-annotation-pdb 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, actionable skill body with executable examples and an explicit validation checkpoint guarding the fragile numbering-join step. It is concise for its domain and easy to navigate as a single self-contained file.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence without explaining basic concepts; domain-specific cautions (silent numbering offsets, RSA>1.0) earn their place, with only minor passages that could be tightened.

4 / 5

Actionability

Provides copy-paste-ready Python calls with concrete parameters (pdb_id, chains, ligand_resnames, cutoffs) plus return-shape descriptions, covering the common cases from PDB lookup through annotation to downstream use.

5 / 5

Workflow Clarity

Five clearly sequenced steps with an explicit validation checkpoint in Step 3 (landmark assert, offset recording, 'Do not silently rebase positions') that functions as an error-recovery feedback loop.

5 / 5

Progressive Disclosure

Well-organized into clearly signaled sections (When to use, Required inputs, Workflow, Interpretation table, Honest limitations, Cross-references) with easy navigation; no bundle files exist, so content stays appropriately inline with only minor split opportunities.

4 / 5

Total

18

/

20

Passed

Description

87%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 clearly states both capability and trigger context for a specialized structural-bioinformatics task. The only blemish is second-person voice in the 'Use when' clause, which costs it one specificity point.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (interface vs partner chain, ligand pocket, buried vs solvent-exposed, optional secondary structure) that would warrant a 5, but the second-person 'Use when you need to anchor' triggers the voice penalty reducing specificity by one point.

4 / 5

Completeness

Explicitly answers both what ('produce a per-residue annotation table: ...') and when ('Use when you need to anchor a variant-interpretation or DMS analysis...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong domain-natural terms ('PDB structure', 'binding interface', 'ligand pocket', 'buried vs solvent-exposed', 'DMS heatmap', 'variant-interpretation') cover what users say, with only minor synonyms (e.g. ASA/RSA/solvent accessibility) absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (per-residue PDB structural annotation anchored to DMS/variant interpretation) with distinct triggers and minimal overlap with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.