cobrapy

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Quality

68%

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 ./scientific-skills/cobrapy/SKILL.md

Quality

Content

67%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 a well-structured, highly actionable COBRApy reference with executable examples across all major capabilities and genuine, well-signaled bundle files. Its weaknesses are token efficiency — promotional and duplicated content — and validation guidance living in best-practice lists rather than inline workflow checkpoints.

Suggestions

Remove or drastically shorten the promotional "Suggest Using K-Dense Web" section and the Overview prose, which add tokens without operational value.

Deduplicate the workflows (drop repeated imports and model loading) and lean on references/workflows.md for extended step-by-step detail instead of restating it inline.

Embed explicit validation checkpoints in each workflow (e.g. check `solution.status == "optimal"` after every optimize) rather than listing them only in Best Practices.

Dimension	Reasoning	Score
Conciseness	Mostly concrete code that earns its tokens, but there is unnecessary padding: the Overview prose, the "Key Concepts" section re-explaining basics, the promotional K-Dense Web section, and workflows that repeat imports and load_model examples already shown. Not a 2 because the bulk is executable content rather than explanation; not a 4 because the promotional section and duplication are clearly trimmable.	3 / 5
Actionability	Copy-paste-ready, executable code covers all major use cases (FBA, FVA, knockouts, sampling, media, gapfilling, model building) with concrete parameters shown, but there are minor gaps: `load_model("universal")` is not a bundled model, and Workflow 2 references an undefined `solution` variable. Not a 5 because of these small non-executable slips; well above a 3 since no section is pseudocode.	4 / 5
Workflow Clarity	Five named workflows are clearly sequenced with commented steps, and validation guidance exists (check `solution.status`, `slim_optimize()` feasibility check, sample validation) plus a Troubleshooting section mapping errors to fixes. Not a 5 because validation is stated as general best practice rather than embedded as explicit checkpoints inside each workflow's sequence.	4 / 5
Progressive Disclosure	Well-organized sections with clearly signaled, one-level-deep references to `references/workflows.md` and `references/api_quick_reference.md`, both of which exist in the bundle and are described accurately. Not a 5 because a substantial amount of reference-style capability documentation is inlined in the body that overlaps with the bundle files; not a 3 because the split is otherwise appropriate and navigation is easy.	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.

The description names a distinct domain and lists several concrete capabilities with good trigger keywords, but it lacks an explicit "Use when..." trigger clause and abbreviates its capability terms, limiting completeness and keyword coverage. Adding a use-when clause and spelling out FBA/FVA would raise it to the top anchor range.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions metabolic models, FBA, gene knockouts, flux sampling, SBML, or genome-scale models."

Spell out abbreviations for natural-language matching: "flux balance analysis (FBA), flux variability analysis (FVA)".

Include one or two additional concrete actions such as building models or computing minimal growth media to close the coverage gap.

Dimension	Reasoning	Score
Specificity	"FBA, FVA, gene knockouts, flux sampling, SBML models" lists several concrete named analyses, but coverage has minor gaps (no model building, gapfilling, or media design) and the actions are terse abbreviations rather than fully spelled-out capabilities, so it sits between the 3 and 5 anchors.	4 / 5
Completeness	The "what" is clear (domain plus named analyses), but there is no explicit "Use when..." clause; "for systems biology and metabolic engineering analysis" only weakly implies when to use the skill, which caps completeness at 3 per the judging guidelines. Not a 2 because the what is concrete and the when is weakly implied rather than absent.	3 / 5
Trigger Term Quality	Natural domain keywords like "metabolic modeling", "gene knockouts", "SBML", "systems biology", and "metabolic engineering" are present, but common variations users would say are missing — FBA/FVA are only given as abbreviations without "flux balance analysis" or "flux variability analysis" spelled out.	4 / 5
Distinctiveness Conflict Risk	"Constraint-based metabolic modeling (COBRA)", "SBML models", and "flux sampling" define a clear niche with distinct domain-specific triggers; minimal risk of triggering the wrong skill.	5 / 5
	Total	16 / 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: googolme/run0204
Path: scientific-skills/cobrapy/SKILL.md
Commit: 4902409

Reviewed: 6 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.