CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pdb-database

Use when you want to search for or download experimentally-determined 3D structures for biomolecules (proteins, nucleic acids, bound ligands). Supports searching by sequence similarity, structure similarity, chemical and other attributes. Also use to get metadata about biomolecular structure experiments.

Quality

87%

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

82%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-crafted, highly actionable skill body: all five workflows give executable commands with realistic examples, core rules are stated tersely, and domain gotchas (label vs auth, resolution_combined, full-text as last resort) are genuinely non-obvious. Remaining weaknesses are minor: some implicit validation checkpoints, a small flag-spelling inconsistency, and an unreferenced citation.bib bundle file.

DimensionReasoningScore

Conciseness

The body is dense and almost entirely actionable — rules are terse and examples are complete commands — but a few spots could be trimmed, e.g. entity/chain/assembly concept explanations Claude partially already knows and an inconsistent flag spelling ('--count_only' in the workflow text vs '--count-only' in an example), fitting the 4 anchor of efficient with minor over-explanation.

4 / 5

Actionability

Every workflow is backed by fully executable, copy-paste-ready commands with concrete examples covering the common cases: schema fetch, attribute/group search, sequence/structure/motif/chemical similarity, full text, coordinate file download, and GraphQL metadata queries — matching the 5 anchor.

5 / 5

Workflow Clarity

Both multi-step workflows are clearly numbered with specific commands, and verification affordances exist (grep the schema to confirm attribute choice, '--count_only' to check match counts before retrieval), but checkpoints are partly implicit and the batch download workflow lacks an explicit post-download verification step — the 4 anchor's 'minor validation gaps'.

4 / 5

Progressive Disclosure

Good structure: one section per workflow, and all four bundle scripts (scripts/fetch_schema.py, search_pdb.py, fetch_pdb_metadata.py, download_coordinate_files.py) are referenced with runnable usage, matching the actual bundle layout. Minor gap: references/citation.bib exists in the bundle but is never referenced or signaled from the body.

4 / 5

Total

17

/

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 description that explicitly covers what the skill does and when to use it, with concrete capabilities and a well-defined niche. Main gaps are the missing 'PDB'/'Protein Data Bank' keywords and file extensions, and second-person phrasing in the trigger clause.

DimensionReasoningScore

Specificity

Lists multiple concrete actions covering the skill's full surface ('search for or download experimentally-determined 3D structures', 'searching by sequence similarity, structure similarity, chemical and other attributes', 'get metadata about biomolecular structure experiments'), which matches the 5 anchor, but the trigger clause 'Use when you want to' is second person, so the third-person guideline penalty reduces it by 1.

4 / 5

Completeness

Explicitly answers both what ('search ... by sequence similarity, structure similarity, chemical and other attributes', 'get metadata about biomolecular structure experiments') and when ('Use when you want to search for or download ...', 'Also use to get metadata ...') with two explicit trigger clauses, matching the 5 anchor.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('3D structures', 'proteins', 'nucleic acids', 'bound ligands', 'sequence similarity', 'structure similarity', 'metadata') but the canonical terms users would most naturally say — 'PDB', 'Protein Data Bank', and file extensions like .pdb/.cif/.mmCIF — are absent, keeping it below the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche of experimentally-determined biomolecular 3D structures with distinct triggers (sequence/structure similarity, chemical attributes, structure experiment metadata) that would not plausibly fire for unrelated skills; 'experimentally-determined' even distinguishes it from structure-prediction tools.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

google-deepmind/science-skills

Path

skills/pdb_database/SKILL.md

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.