CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

biopython-structure

Use Bio.PDB to parse and analyze protein structures (PDB/mmCIF) for structural bioinformatics tasks; use when you need structure parsing, geometry calculations, or structural comparison/superposition.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/biopython-structure/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 core technical content (example script and Implementation Details) is concrete and executable, but roughly a third of the body is generic template padding that adds no Bio.PDB-specific value. The orphaned references/structure.md file means progressive disclosure is broken: detail exists in the bundle with no navigation to it.

Suggestions

Delete the generic boilerplate sections ('When Not to Use', 'Required Inputs', 'Recommended Workflow', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling', 'Quick Validation') and keep only guidance specific to Bio.PDB structure work.

Reference references/structure.md explicitly from the body (e.g., a '## Advanced usage' section linking to it) and move the duplicated Implementation Details material there.

Add a short concrete validation step to the workflow (e.g., verifying the parsed structure has the expected chain/residue counts before writing output) instead of the abstract 'final validation pass' wording.

DimensionReasoningScore

Conciseness

Six boilerplate sections ('When Not to Use', 'Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling', 'Quick Validation') contain generic template filler Claude already knows (e.g., 'Do not use this skill when a simpler direct answer is more appropriate', 'No local script validation step is required'), and 'Key Features' restates 'When to Use'.

2 / 5

Actionability

The example is a complete, executable script (config-file convention, parser selection, NeighborSearch, JSON output) with concrete API pointers (calc_angle, calc_dihedral, Superimposer), but superposition and structure extraction/saving are only named, not shown.

4 / 5

Workflow Clarity

'Recommended Workflow' lists a sequence but its checkpoints are abstract ('Run a final validation pass for completeness, consistency, and safety') rather than concrete commands, and 'Quick Validation' explicitly waives any concrete validation step.

3 / 5

Progressive Disclosure

The body is well-sectioned, but the bundled references/structure.md (a 13KB Bio.PDB detail guide) is never referenced anywhere in the body, and 'Implementation Details' duplicates material that belongs in that reference — between anchor 2 (references buried) and anchor 3 (references not clearly signaled).

3 / 5

Total

12

/

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: it names the tool, domain, file formats, and several concrete operations, and gives an explicit 'use when' trigger clause. Minor gaps in action coverage and natural-term synonyms keep it just short of perfect.

DimensionReasoningScore

Specificity

Names several concrete actions ('parse and analyze protein structures (PDB/mmCIF)', 'structure parsing, geometry calculations, or structural comparison/superposition'), but coverage has minor gaps — neighbor search, extraction/saving, and DSSP integration from the body are not mentioned.

4 / 5

Completeness

Explicitly answers both what ('Use Bio.PDB to parse and analyze protein structures (PDB/mmCIF) for structural bioinformatics tasks') and when ('use when you need structure parsing, geometry calculations, or structural comparison/superposition') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('protein structures', 'PDB/mmCIF', 'superposition', 'geometry calculations', 'structural bioinformatics'), but common user phrasings like '.pdb', 'RMSD', 'dihedral', 'distances', and 'contacts' are missing.

4 / 5

Distinctiveness Conflict Risk

'Bio.PDB', 'PDB/mmCIF', and 'structural bioinformatics' define a clear niche with distinct triggers; minimal conflict risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Data Analysis/biopython-structure/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.