mfa-pipeline-orchestrator

Orchestrate the full metabolic flux analysis pipeline from model loading to phenotype prediction and publication figures. Triggers when the user provides an organism name, BIGG model ID, or custom reaction list and wants end-to-end metabolic modelling run automatically.

Quality

81%

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

Quality

Content

75%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 content is a tight, well-structured orchestrator skill: clear sequencing, explicit per-step I/O contracts, and resume semantics. Main gap is the absence of an explicit FAIL-handling/feedback loop, which is the kind of validation checkpoint the rubric rewards.

Suggestions

Add an explicit branch for handling a FAIL status (e.g. 'If a step reports FAIL: read the error, attempt one retry within the budget, then halt and report') to strengthen the validation feedback loop.

Briefly state the expected invocation interface for each sub-agent (name + message format) so the orchestration is fully copy-paste actionable rather than implied.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — it lists steps, inputs/outputs, and conventions without explaining what FBA or COBRApy is. The progress-file template blocks are slightly heavier than strictly necessary, but every line carries operational information.	4 / 5
Actionability	Each step specifies concrete inputs to provide, the progress file to wait for, and the values to read back, plus exact file paths. It stops short of copy-paste executable commands because it delegates computation to sub-agents, but the orchestration guidance is concrete and actionable.	4 / 5
Workflow Clarity	Steps 0–4 are clearly sequenced with per-step progress-file checkpoints and a retry budget, and the convention "check progress file status before re-invoking" gives a resume loop. It lacks an explicit validation/feedback loop for FAIL status (what to do when a step reports FAIL), which keeps it just below 5.	4 / 5
Progressive Disclosure	Well-organized with clear sections (Overview, Workflow, Progress File Specification, Key Conventions) and one-level-deep progress files as the coordination substrate. No bundle files exist so there are no nested references to verify; structure is appropriately flat for an orchestrator skill.	4 / 5
	Total	16 / 20 Passed

Description

87%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 well-crafted: it states both a concrete capability and an explicit trigger condition in third person, with natural domain keywords. Minor improvements would add the sub-analyses (FBA/essentiality/yield) and a few more synonyms to the trigger clause.

Suggestions

Mention the key sub-analyses (FBA/pFBA, gene essentiality, yield optimization) in the description so the capability list is more comprehensive.

Add 'COBRApy' or 'genome-scale model' to the trigger phrase since these are natural terms users say for this domain.

Dimension	Reasoning	Score
Specificity	Lists concrete, specific actions — "model loading," "phenotype prediction," "publication figures," and an end-to-end pipeline run — but does not enumerate the sub-stages (FBA, essentiality, yield) in the description itself, leaving minor gaps.	4 / 5
Completeness	Clearly answers what ("Orchestrate the full metabolic flux analysis pipeline from model loading to phenotype prediction and publication figures") and when ("Triggers when the user provides an organism name, BIGG model ID, or custom reaction list and wants end-to-end metabolic modelling"), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms users would say ("metabolic flux analysis," "BIGG model ID," "organism name") with synonyms, but misses a few common variants users might voice (e.g. "COBRApy" is not in the description, "genome-scale model").	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — end-to-end MFA pipeline orchestration with BIGG IDs and custom reaction lists — with triggers unlikely to fire for unrelated skills, so conflict risk is minimal.	5 / 5
	Total	18 / 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/mfa-pipeline-orchestrator/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.