CtrlK
BlogDocsLog inGet started
Tessl Logo

gsmm-builder

Build or load a genome-scale metabolic model (GSMM) using COBRApy. Covers loading from BIGG, constructing minimal models from scratch, setting medium constraints, and exporting validated .json model files.

62

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 ./external/agents/Biology-Agent/skills/gsmm-builder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable code and a clear four-step workflow, but it carries some unnecessary conceptual explanation, lacks an explicit validation checkpoint before export, and leaves a provided reference file unlinked.

Suggestions

Add an explicit validation step before export — e.g. run model.optimize() and confirm solution.status == 'optimal' before saving — turning it into a validate -> fix -> retry loop.

Link references/cobra_reference.md from the body (e.g. under a 'Reference' section) so the bundle is actually navigable, and consider moving the conventions table and BIGG download snippets there.

Trim the Overview paragraph that explains what a stoichiometric matrix and linear program are, since Claude already knows these concepts.

DimensionReasoningScore

Conciseness

Mostly efficient with good code, but the Overview explains concepts Claude already knows ('GSMMs encode every known metabolic reaction as a stoichiometric matrix') and could be tightened.

2 / 3

Actionability

Provides fully executable, copy-paste-ready COBRApy code with real model IDs and a concrete conventions table — no pseudocode.

3 / 3

Workflow Clarity

The four steps are clearly sequenced, but for a batch/export operation there is no explicit validate-then-proceed checkpoint in the workflow; validation appears only reactively in 'Common Failure Modes', capping clarity at 2.

2 / 3

Progressive Disclosure

Sections are well-organized, but the existing references/cobra_reference.md bundle is never linked or signaled in the body, and content that could be split (conventions table, BIGG downloads) stays inline.

2 / 3

Total

9

/

12

Passed

Description

82%Weight 40%Scale 1-3

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, domain-distinctive, and rich in natural trigger terms, but it omits any explicit 'when to use' guidance, which caps completeness. Adding a 'Use when...' clause would raise it to full marks.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when building or loading genome-scale metabolic models, running FBA, or when the user mentions COBRApy, BIGG, or stoichiometric models.'

Mirror a couple of the trigger-keywords from metadata (e.g. 'flux analysis', 'medium constraints') in the description so the 'when' is reinforced.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Build or load', 'loading from BIGG', 'constructing minimal models from scratch', 'setting medium constraints', 'exporting validated .json model files' — in third person, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric 'when' is only implied — capping completeness at 2.

2 / 3

Trigger Term Quality

Uses canonical domain vocabulary a metabolic-modeling user would actually say — 'GSMM', 'COBRApy', 'BIGG', 'genome-scale metabolic model' — giving good natural-term coverage.

3 / 3

Distinctiveness Conflict Risk

A narrowly specialized niche (genome-scale metabolic models via COBRApy) with distinct triggers that is unlikely to conflict with other skills.

3 / 3

Total

11

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
aiming-lab/AutoResearchClaw
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.