Tessl • The package manager for agent skills

SkillPublic

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

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

A highly actionable, executable body with a well-signaled reference file, weakened by padded sections that re-explain known concepts and by the absence of validation checkpoints in batch/download workflows. Trimming Key Concepts and adding verification steps would lift the two 3-score dimensions.

Suggestions

Remove or drastically trim the "Key Concepts" section and the "Common Use Cases" bullet lists, which re-explain concepts Claude already knows and add tokens without instruction.

Add validation to the batch and download workflows (e.g. check the HTTP response status, verify non-empty file content, retry or report failed PDB IDs) so workflow clarity can exceed 3.

Move inline detail such as the raw GraphQL query pattern and install variants into references/api_reference.md to tighten the overview.

Dimension	Reasoning	Score
Conciseness	The capability sections are code-first and efficient, but the "Key Concepts" section explains basics Claude already knows ("Resolution: Measure of detail... lower values = higher detail", "PDB ID: Unique 4-character identifier") and the "Common Use Cases" bullet lists describe rather than instruct. Multiple padded sections, not just minor trim, so below anchor 4.	3 / 5
Actionability	Every capability has copy-paste-ready executable code: TextQuery/AttributeQuery/SequenceQuery/StructSimilarityQuery examples, direct download URLs, GraphQL query, and a batch loop. The code is complete and covers the common cases, matching anchor 5 exactly.	5 / 5
Workflow Clarity	Capabilities are well organized but there is no explicit multi-step sequence with validation checkpoints, and the batch-operations example has no verification beyond a try/except that prints errors. Per the guidelines, batch operations without validation cap workflow clarity at 3.	3 / 5
Progressive Disclosure	Good structure with clearly signaled one-level-deep reference: the body describes what references/api_reference.md contains and when to use it, and the file exists as advertised. Minor gaps — some inline detail (e.g. the GraphQL pattern, install variants) could move to the reference — keep it below anchor 5.	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.

A strong, third-person description with concrete actions and a clearly distinct niche, but it lacks an explicit "Use when..." trigger clause, leaving the "when" only weakly implied and capping completeness. Adding natural synonyms like ".pdb" or "protein structure" would round out trigger coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about protein structures, PDB entries, downloading .pdb/.cif files, or structural data for drug discovery."

Include common synonyms and file extensions users naturally say, such as ".pdb", "mmCIF files", "crystal structure", or "protein coordinates".

Mention batch operations in the description since it is a named core capability of the skill.

Dimension	Reasoning	Score
Specificity	"Search by text/sequence/structure, download coordinates (PDB/mmCIF), retrieve metadata" lists several specific actions with only minor gaps (batch operations and similarity-search detail are not named). Not 5 because coverage is not comprehensive; not 3 because it goes well beyond 1-2 actions.	4 / 5
Completeness	The "what" is clear (search, download, retrieve metadata), but the "when" is only weakly implied by "for structural biology and drug discovery" — a purpose clause, not an explicit "Use when..." trigger. Per the guidelines, a missing explicit trigger clause caps this at 3.	3 / 5
Trigger Term Quality	Natural keywords like "3D protein/nucleic acid structures", "PDB", "structural biology", and "drug discovery" would be said by users, but common variations such as ".pdb files", "protein structure", or "crystal structure" are missing. Anchor 4 (good coverage, a few natural terms missing) is the best fit.	4 / 5
Distinctiveness Conflict Risk	"RCSB PDB" and "3D protein/nucleic acid structures" carve out a clear niche with distinct triggers and minimal conflict risk with other skills. It clearly matches the anchor-5 example pattern of distinct, concrete triggers.	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
Revision: 6a85742

Reviewed: 22 days ago

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.

pdb-database

Table of Contents

Is this your skill?