pdb-database

Access RCSB PDB for 3D protein/nucleic acid structures. Search by text/sequence/structure, download coordinates (PDB/mmCIF), retrieve metadata, for structural biology and drug discovery.

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/pdb-database/SKILL.md

Quality

Content

68%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 highly actionable with comprehensive executable examples and a well-signaled reference file, but it is padded with obvious use-case lists and concept explanations, and batch operations lack explicit validation checkpoints. Trimming explanatory filler and adding verification steps would lift conciseness and workflow clarity.

Suggestions

Remove or condense the 'Common Use Cases' bullet lists and the 'Key Concepts' section, which restate knowledge Claude already has, to improve conciseness.

Add an explicit validation/verification checkpoint to the batch-operations workflow (e.g., verify each fetched entry has expected fields before proceeding) to lift workflow clarity above 3.

Move the bulk of inline API examples (GraphQL, attribute search variants) into references/api_reference.md, keeping only a quick-start example in SKILL.md, to strengthen progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with abundant useful code, but padded by the 'Common Use Cases' bullet lists of obvious tasks and a 'Key Concepts' section explaining terms (Resolution, Entity, Biological Assembly) that Claude already knows.	3 / 5
Actionability	Fully executable, copy-paste-ready examples cover the common cases — text/attribute/sequence/structure search, fetch, GraphQL, download, BioPython parsing, and batch retrieval — each as complete runnable code.	5 / 5
Workflow Clarity	Content is organized by capability rather than a sequenced workflow, and the batch-operations section has try/except error handling but no validation/verification checkpoint, capping workflow clarity at 3 per the batch-operations guideline.	3 / 5
Progressive Disclosure	A real one-level-deep references/api_reference.md is clearly signaled with a description of its contents, but substantial API examples are inlined in SKILL.md that could live in the reference, leaving minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

70%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 and distinctive, clearly scoping the RCSB PDB domain with concrete capabilities, but it omits an explicit 'Use when...' trigger clause, leaving the 'when' only weakly implied. Adding concrete trigger phrases and file extensions would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when searching for protein or nucleic acid 3D structures, downloading .pdb/.cif coordinate files, or retrieving structural metadata.'

Include file extensions and synonyms ('.pdb', '.cif', 'macromolecular structures', 'crystal structures') to strengthen trigger-term coverage.

Tighten 'retrieve metadata' to specific metadata types (experimental method, resolution, deposition info) to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Search by text/sequence/structure', 'download coordinates (PDB/mmCIF)', 'retrieve metadata') with comprehensive coverage, though 'metadata' is somewhat generic, leaving minor gaps versus a full 5.	4 / 5
Completeness	Has a clear 'what' (access RCSB PDB, search/download/retrieve) but lacks an explicit 'Use when...' trigger clause; 'for structural biology and drug discovery' only weakly implies when, so completeness is capped at 3 per the guideline.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('protein/nucleic acid structures', 'PDB/mmCIF', 'structural biology', 'drug discovery') but misses common synonyms and file extensions like '.pdb', '.cif', 'macromolecular structures'.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — RCSB PDB 3D macromolecular structures — with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/pdb-database/SKILL.md
Commit: 5f2a37b

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.