gsmm-validator

Validate a COBRApy genome-scale metabolic model for mass/charge balance, stoichiometric consistency, biomass producibility, dead-end metabolites, thermodynamic loops, and GPR rule formatting. Outputs a structured validation report with errors and warnings.

Quality

78%

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 ./external/agents/Biology-Agent/skills/gsmm-validator/SKILL.md

Quality

Content

82%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 complete executable code and a clearly sequenced, checkpointed validation workflow. It is mostly concise and well-structured, with only minor over-explanation prose and no remediation feedback loop.

Suggestions

Trim the explanatory prose leads before Steps 2, 4, and 6 that restate known concepts (e.g. what dead-ends or energy-generating cycles are) to improve token efficiency.

Add a brief remediation feedback loop after the final report (e.g. 'If status is FAIL, address ERRORs by category then re-run from Step 1 until PASS') to strengthen workflow clarity.

Consider moving the per-check code blocks into a reference script under scripts/ and keeping SKILL.md as an overview, to improve progressive disclosure for this 200+ line skill.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code dominating, but a few prose sentences explain concepts Claude already knows (e.g. 'Unbalanced reactions are among the most common modelling errors', 'Energy-generating cycles violate thermodynamics and inflate apparent fluxes') and could be trimmed.	4 / 5
Actionability	Every step provides complete, copy-paste-ready Python using real COBRApy APIs (check_mass_balance, optimize, find_blocked_reactions, loopless_solution), with the common cases fully covered and a concrete report-writing step.	5 / 5
Workflow Clarity	An explicit 8-step sequence with per-step PASS/FAIL/ERROR print checkpoints and a final summary report; this is a read-only validation (not destructive/batch), so the destructive-cap does not apply, but there is no validate→fix→retry remediation loop, leaving a minor gap.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent), and the single self-contained file is well-organized with clear section headers (Overview, Workflow, Key Conventions, Interpretation Guide); the detailed per-check code could arguably be split into reference files but is reasonable inline, leaving only a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

75%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, comprehensive, and clearly distinct, but it omits any explicit 'Use when...' trigger guidance, which limits its completeness score. Adding a concrete usage-trigger clause would raise the overall quality.

Suggestions

Add an explicit 'Use when ...' clause naming natural trigger situations (e.g. 'Use when validating a COBRApy genome-scale metabolic model before flux analysis, or when debugging implausible FBA fluxes').

Include a couple of common synonyms users say, such as 'FBA feasibility' or 'GSM model', to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete validation actions — 'mass/charge balance, stoichiometric consistency, biomass producibility, dead-end metabolites, thermodynamic loops, and GPR rule formatting' — plus 'structured validation report with errors and warnings', giving comprehensive coverage.	5 / 5
Completeness	The 'what' is explicit and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric says caps completeness at 3.	3 / 5
Trigger Term Quality	Strong domain keywords a user would naturally say ('COBRApy', 'genome-scale metabolic model', 'mass/charge balance', 'dead-end metabolites', 'thermodynamic loops', 'GPR'), but missing a few common synonyms/variations like 'FBA' or 'GSM model'.	4 / 5
Distinctiveness Conflict Risk	Targets a very specific niche — COBRApy genome-scale metabolic model validation — with distinct, domain-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: aiming-lab/AutoResearchClaw
Path: external/agents/Biology-Agent/skills/gsmm-validator/SKILL.md
Commit: be4ba47

Reviewed: 5 days 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.