CtrlK
BlogDocsLog inGet started
Tessl Logo

bioservices

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.

62

Quality

74%

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 ./backend/cli/skills/biology/bioservices/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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, highly actionable skill body with real executable code for each of the seven capability areas and clean navigation to genuine reference and script files. The main weaknesses are padding that assumes less competence than Claude has (generic error handling, tool-integration lists), missing validation checkpoints in batch/async workflows, and some API detail inlined that belongs in the references.

Suggestions

Cut or shrink the generic try-except 'Error Handling' and 'Integration with Other Tools' sections — Claude already knows basic Python error handling; keep only bioservices-specific error behaviors (e.g., HTTP errors, timeouts).

Add validation checkpoints to the batch and async workflows: verify BLAST job completion before calling getResult, and have batch_id_converter report/inspect unmapped identifiers rather than silently dropping them.

Move the per-service 'Key methods' bullet lists into references/services_reference.md, keeping only a single representative example per capability in SKILL.md.

DimensionReasoningScore

Conciseness

The body is mostly efficient with genuinely useful service-specific detail, but sections like the generic try-except 'Error Handling' block ('Wrap service calls in try-except blocks') and the 'Integration with Other Tools' list explain things Claude already knows and could be trimmed, matching the 'mostly efficient but includes some unnecessary explanation' anchor.

3 / 5

Actionability

Nearly every section contains executable, concrete code with real API calls (u.search('ZAP70_HUMAN', frmt='tab', ...), k.get('hsa04660')) plus runnable script commands, but minor gaps like the undefined 'protein_sequence' variable in the BLAST example and 'u = UniChem()' shadowing the earlier UniProt instance keep it below fully copy-paste ready.

4 / 5

Workflow Clarity

Multi-step workflows are clearly sequenced (the numbered 'Common workflow' for compound cross-referencing, the 'This script demonstrates: 1-5' pipeline listing), but the batch identifier conversion workflow (batch_id_converter.py) and the async BLAST workflow lack validation/verification checkpoints (e.g., confirming job completion or checking mapping results), which the rubric caps at 3.

3 / 5

Progressive Disclosure

Good structure with well-signaled one-level-deep references — each capability section points to a real bundle file ('Reference: references/services_reference.md for complete UniProt API details') and a Resources section indexes all four scripts — but the per-service 'Key methods' lists inline some API detail that duplicates references/services_reference.md, a minor organization gap.

4 / 5

Total

14

/

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 with an explicit 'Use when' trigger clause, concrete named databases, and unusually good de-confliction guidance against gget and biopython. The only weakness is slightly incomplete coverage of the package's action surface (pathways, sequences, interactions) and a few missing natural trigger phrases.

Suggestions

Add one or two more concrete action phrases such as 'pathway analysis' or 'retrieving protein sequences' to broaden trigger coverage.

Include commonly uttered phrases like 'BLAST' or 'map IDs between databases' as natural trigger synonyms for ID mapping.

DimensionReasoningScore

Specificity

The description lists several concrete actions ('querying multiple databases', 'cross-database analysis, ID mapping across services') with named databases (UniProt, KEGG, ChEMBL, Reactome), but coverage of the package's actions is incomplete (no pathway analysis, sequence retrieval, or interaction queries), fitting the 'several specific actions; minor gaps' anchor rather than the comprehensive level 5.

4 / 5

Completeness

It clearly answers both 'what' ('Unified Python interface to 40+ bioinformatics services') and 'when' ('Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow') with concrete trigger phrases, plus explicit scoping via 'Best for cross-database analysis, ID mapping across services'.

5 / 5

Trigger Term Quality

Good natural keyword coverage including 'ID mapping', 'cross-database analysis', 'querying multiple databases', and the specific database names users would mention, but common user phrases like 'pathway analysis', 'protein sequence', or 'BLAST' are missing, placing it just below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (multi-database queries in a single workflow with a consistent API) and explicitly de-conflicts with adjacent skills ('For quick single-database lookups use gget; for sequence/file manipulation use biopython'), minimizing wrong-skill triggering.

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

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
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.