CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-protein-structure-retrieval

Protein structure retrieval from RCSB PDB, PDBe, and AlphaFold with disambiguation, quality assessment (resolution, R-factor, pLDDT), and metadata. Distinguishes high-quality experimental (X-ray under 2 Angstrom) vs predicted vs medium-quality structures. Use for fetching protein structures, structure-quality comparison, and selecting structures for drug design or modeling.

69

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is a well-structured, mostly executable retrieval workflow with clear sequencing, fallback chains, and useful domain-quality heuristics. Main weaknesses are minor redundancy (Tool Reference restating Phase 2 calls) and validation that is more implicit than stepwise in the later phases.

Suggestions

Remove or condense the trailing Tool Reference section, since every tool it lists already appears with usage context in the Phase 2 code block.

Add an explicit within-workflow validation checkpoint in Phase 2 (e.g., confirm PDB ID resolved and quality scores returned before composing the Phase 3 report) to tighten the feedback loop.

Tighten placeholder variables in code examples (define `uniprot_id`/`name` near their first use or pair them with a concrete value) so examples are closer to copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence—domain reasoning gives useful judgment thresholds (pLDDT/resolution cutoffs) rather than explaining basics—but the trailing Tool Reference section duplicates tool calls already shown in Phase 2 and could be trimmed.

4 / 5

Actionability

Provides concrete, real-signature tool calls (e.g., tu.tools.alphafold_get_prediction(uniprot_id=...), PDBeValidation_get_quality_scores), fallback-chain and error-handling tables; mostly executable with minor gaps from placeholder variables.

4 / 5

Workflow Clarity

Clear Phase 0→1→2→3 sequence with explicit gating criteria in Phase 0, an Identity Checklist checkpoint in Phase 1, and feedback loops via fallback chains and the error-handling table, though within-phase validation in Phase 2/3 is more implicit than stepwise.

4 / 5

Progressive Disclosure

Well-organized into clear sections (Domain Reasoning, Workflow, Phases, Quality Assessment, Error Handling, Tool Reference) with no nested references and easy navigation; slightly above the simple-skill threshold so a couple of dense blocks (full Tool Reference, quality tables) could arguably be split out.

4 / 5

Total

16

/

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.

The description is specific, complete, and distinct: it states concrete capabilities, an explicit 'Use for' trigger clause, and a well-bounded niche around protein-structure retrieval and quality assessment. Its only minor gap is a few missing natural synonyms/file extensions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—retrieval, disambiguation, quality assessment (resolution/R-factor/pLDDT), metadata, and tier distinction (X-ray <2 A vs predicted vs medium)—giving comprehensive coverage of capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (retrieval with disambiguation, quality assessment, metadata, tier distinguishing) and 'when' ('Use for fetching... comparison... selecting structures for drug design or modeling') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural domain terms ('fetching protein structures', 'drug design', 'structure-quality comparison', RCSB/PDBe/AlphaFold), but missing a few common synonyms and file extensions users might say (e.g., '.pdb', '3D structure', 'homology modeling').

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche—protein structure retrieval from named databases (RCSB PDB, PDBe, AlphaFold) with quality-tier reasoning—with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.