cobrapy

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

Quality

66%

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 ./backend/cli/skills/biology/cobrapy/SKILL.md

Quality

Content

63%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 thorough, highly actionable reference for COBRApy with well-organized capability sections and real bundle files, weakened by duplication between the inline workflows and references/workflows.md, some re-explanation of library basics, and a few code snippets with small errors.

Suggestions

Replace the inline 'Common Workflows' section with pointers to references/workflows.md (keeping one short quick-start workflow) to remove duplication and shrink the body.

Fix the Workflow 2 snippet: 'neutral_genes' references an undefined 'solution' variable — compute a baseline first via 'model.slim_optimize()'.

Move the 'Key Concepts' explanations (DictList behavior, GPR boolean logic) into the API quick reference, keeping only non-obvious gotchas like the model.medium full-dict reassignment inline.

Dimension	Reasoning	Score
Conciseness	The ~470-line body is mostly executable code with lean comments, but the five 'Common Workflows' largely repeat patterns already shown in 'Core Capabilities', and the 'Key Concepts' section explains library basics (DictList access, AND/OR GPR logic) Claude can derive. It fits the 3 anchor ('mostly efficient but could be tightened') better than 4, where only minor trimming would be needed.	3 / 5
Actionability	Nearly every section is copy-paste-ready Python with real function signatures (load_model, flux_variability_analysis, single_gene_deletion, sample). Not 5: Workflow 2 filters with 'results[results["growth"] < 0.01]' and references an undefined 'solution' variable, and 'load_model("universal")' is not a bundled cobra model — small but real executability gaps.	4 / 5
Workflow Clarity	The five workflows are clearly sequenced (load → baseline → analysis → classification), and validation checkpoints appear as best practices ('Check solution status after optimization', 'Validate flux samples'). Not 5 because validation is stated as general advice rather than inline checkpoints within each workflow (e.g., no explicit status check after optimize() inside the workflows).	4 / 5
Progressive Disclosure	Two real one-level-deep reference files (references/workflows.md, references/api_quick_reference.md) are clearly signaled at the end, but the body inlines ~80 lines of 'Common Workflows' that overlap the workflows reference, plus a full model-building tutorial. Content that should live in the references is duplicated inline, matching the 3 anchor ('content that should be separate is inline').	3 / 5
	Total	14 / 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.

A dense, domain-fluent description with strong trigger keywords and near-zero conflict risk, undermined by the absence of an explicit 'Use when' clause and unexpanded FBA/FVA abbreviations.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with genome-scale metabolic models, running flux balance analysis, or performing gene knockout studies.'

Spell out FBA/FVA once ('flux balance analysis (FBA), flux variability analysis (FVA)') so users who say the full phrase still match.

Mention one or two natural synonyms such as 'metabolic network' or '.xml/.sbml model files' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'FBA, FVA, gene knockouts, flux sampling, SBML models' — in terse domain shorthand. Not the 5 anchor because coverage is compressed and omits capabilities the body documents (model building, gapfilling, production envelopes, media design); not 3 because more than 1-2 actions are named.	4 / 5
Completeness	The 'what' is clear (multiple concrete capabilities), but there is no 'Use when...' clause or equivalent explicit trigger guidance — 'for systems biology and metabolic engineering analysis' only weakly implies when. Per the judging guideline, a missing explicit 'when' caps this dimension at 3.	3 / 5
Trigger Term Quality	Good natural keyword coverage: 'metabolic modeling', 'COBRA', 'gene knockouts', 'flux sampling', 'SBML models', 'systems biology', 'metabolic engineering'. Not 5 because abbreviations FBA/FVA are not spelled out ('flux balance analysis') and no synonyms/extensions a user might say are included.	4 / 5
Distinctiveness Conflict Risk	'COBRA', 'FVA', 'flux sampling', 'SBML models', 'metabolic engineering' occupy a clear niche with distinct triggers; minimal overlap with any other plausible skill. It clearly matches the 5 anchor, not 4 which reserves for overlap with closely related skills.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: backend/cli/skills/biology/cobrapy/SKILL.md
Commit: 4082a2e

Reviewed: 1 day 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.