CtrlK
BlogDocsLog inGet started
Tessl Logo

flux-analyzer

Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.

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/flux-analyzer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 body is a concise, highly actionable workflow with complete, runnable code and useful conventions/failure-mode tables. Its gaps are the lack of explicit validation checkpoints around the batch deletion analyses and the absence of any external reference structure despite a substantial body.

Suggestions

Add explicit validation/feedback steps for the batch operations — e.g. after single_gene_deletion, check that growth_fraction values are finite and that essential_gene count is plausible before proceeding.

Split the conventions and output-file tables into a separate reference file (e.g. references/conventions.md) and link to it from the workflow, so SKILL.md stays a lean overview.

Include a short 'validate outputs' checklist tying each step to its expected output file so missing or all-zero results are caught early.

DimensionReasoningScore

Conciseness

Lean and efficient — each step leads with executable code and minimal prose, assuming Claude's competence; only a few short framing sentences ('turns numbers into biology') and they earn their place.

3 / 3

Actionability

Fully executable COBRApy code in every step with specific thresholds (5% WT lethality, n=1000 sampling), named output files, and copy-paste-ready blocks.

3 / 3

Workflow Clarity

A clear 7-step sequence with failure-mode troubleshooting is present, but there are no explicit validation checkpoints or feedback loops (validate→fix→retry) for batch operations like the gene/reaction deletion sweeps, capping clarity at 2.

2 / 3

Progressive Disclosure

No bundle files exist, so the single SKILL.md is a monolith with all code, conventions, and troubleshooting inline; sections are well organized but content that could be split out (e.g. a reference table) is not separated.

2 / 3

Total

10

/

12

Passed

Description

67%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 and clearly distinct, naming six concrete analyses tied to a well-defined metabolic-modelling niche. Its main weakness is the absence of an explicit 'Use when...' activation clause and the technical-heavy trigger terms that a non-specialist user would be less likely to voice.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when analysing FBA flux distributions, identifying essential genes, or characterising metabolic phenotypes from a COBRApy model.'

Add a few more natural-language trigger terms users might say (e.g. 'metabolic model', 'flux balance analysis', 'FBA') alongside the technical vocabulary to broaden activation.

Keep the existing concrete action list but lead with the highest-intent trigger so the 'when' is obvious at a glance.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and ... figures' — rather than vague language.

3 / 3

Completeness

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

2 / 3

Trigger Term Quality

Includes relevant domain terms ('gene essentiality', 'phase plane', 'flux sampling', 'secretion', 'yield') but they are heavily technical and omit common lay phrasings a user might naturally say, missing common variations.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (FBA/COBRA flux analysis) with domain-specific triggers that are unlikely to collide with other skills.

3 / 3

Total

10

/

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.