CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-electron-microscopy

Search and analyze electron microscopy data — cryo-EM density maps (EMDB), fitted atomic models (PDB), raw micrograph datasets (EMPIAR), and cryo-electron tomography volumes (CryoET Data Portal). Use for finding 3D structural data on a protein/complex, comparing experimental EM resolution to AlphaFold confidence, and accessing raw EM data for re-processing.

68

Quality

81%

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-electron-microscopy in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 phased workflow with concrete tool signatures and useful domain thresholds. Its main weaknesses are repeated/educational content that inflates length and a monolithic single-file layout that underuses progressive disclosure for a skill of this size.

Suggestions

Remove the restated-description opening paragraph and the 'EM resolution determines what you see' background aside; consolidate the duplicated resolution ranges into one canonical table referenced from both Phase 1 and Phase 6.

Move the per-phase tool input/output specifications and the IDR 'Related Resource' section into separate reference files (e.g. references/tools.md, references/idr.md) and link to them one level deep from the body.

Add one copy-paste tu.run_tool(...) example per phase (not just IDR) so the actionability reaches fully executable coverage across all seven phases.

DimensionReasoningScore

Conciseness

Mostly efficient and domain-specific, but contains removable padding: the opening paragraph restates the description, 'EM resolution determines what you see' explains background Claude already knows, and resolution ranges appear twice (Phase 1 interpretation table and the Phase 6 decision matrix).

3 / 5

Actionability

Each tool is listed with concrete input/output signatures and one full invocation example (tu.run_tool('IDR_search_studies', {...})); numeric thresholds (>0.7 cross-correlation, pLDDT<70, FSC 0.143) make guidance executable, though most phases describe I/O rather than showing copy-paste calls.

4 / 5

Workflow Clarity

A clearly sequenced 7-phase pipeline (Phase 0–7) with a diagram, per-phase numbered steps, a decision matrix, a quality-assessment checklist, and an Edge Cases & Fallbacks section; no error-recovery feedback loop is present, but the operations are read-only so the destructive/batch validation cap does not apply.

4 / 5

Progressive Disclosure

Well-organized with clear headers, tables, and a workflow diagram, but it is a single ~295-line monolithic file with no bundle/reference files; per-tool I/O specs and the IDR 'Related Resource' section are API-reference-style content that could be split into one-level-deep reference files.

3 / 5

Total

14

/

20

Passed

Description

100%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 names concrete actions, concrete trigger phrases, and a distinct EM-data niche with low conflict risk. Both the 'what' and 'when' are explicitly and concretely answered.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Search and analyze', 'finding 3D structural data', 'comparing experimental EM resolution to AlphaFold confidence', 'accessing raw EM data for re-processing') across four named databases, giving comprehensive coverage rather than vague domain naming.

5 / 5

Completeness

Explicitly answers 'what' (search/analyze EM data across EMDB, PDB, EMPIAR, CryoET) and 'when' via a concrete 'Use for ...' clause with specific trigger phrases (finding 3D structural data, comparing EM resolution to AlphaFold, accessing raw EM data).

5 / 5

Trigger Term Quality

Covers the natural terms structural-biology users would say — 'cryo-EM density maps', 'EMDB', 'raw micrograph datasets', 'EMPIAR', 'cryo-electron tomography', 'CryoET Data Portal', 'AlphaFold', 're-processing' — including database synonyms/extensions equivalents.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear EM-data niche scoped to specific databases; the body explicitly fences off X-ray/NMR (use PDB directly) and structure prediction (use tooluniverse-protein-structure), minimizing wrong-skill triggering.

5 / 5

Total

20

/

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.