Agent router

Skill Alim430/bioresearch-agent/skills/core/agent-router

Executable biomedical workflows for AI assistants — literature analysis, biomarker discovery, and Mendelian randomization through reproducible agent skills.

Install

npx -y skills add Alim430/bioresearch-agent --skill agent-router

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Classify a free-text research intent into the right BioResearch Agent workflow (literature / biomarker / causal / case-study / doctor) using a deterministic, rule-based router. Use when an AI client receives an open-ended biomedical research request and must pick which workflow or skill to invoke — NOT to generate or evaluate hypotheses. No LLM, no network.

SKILL.md

2.3 KB, as published. Nobody here has run it

BioResearch Agent — Agent Router Skill

Capability

A rule-based intent classifier that translates a free-text research request into one of the framework's workflows/skills:

Route	Workflow / skill
`literature`	Literature review + co-occurrence graph (`bioresearch-literature-analysis`)
`biomarker`	Biomarker discovery — DEG + enrichment (`bioresearch-biomarker-discovery`)
`causal`	Mendelian randomization (`bioresearch-causal-inference`)
`case-study`	Disease case study / validation run (`bioresearch-disease-case-study`)
`doctor`	Environment & reproducibility check (`bioresearch-environment-check`)

It is intent translation, not reasoning: it maps a request to an existing workflow and emits the matching CLI command. It does not generate, rank, or evaluate hypotheses, and uses no model and no network — the same input always yields the same route (deterministic).

Run

bioresearch route "find biomarkers for Parkinson's disease using GSE7621"
bioresearch route "test the causal effect of BMI on type 2 diabetes with Mendelian randomization"

Output is JSON: {route, confidence, matched_keywords, scores, rationale, suggestion} plus a suggested CLI command. confidence is the share of all matched keywords belonging to the winning route; an unmatched intent returns route: "unknown" with a suggestion list of available routes.

When to invoke

An agent should call this router first when it gets an ambiguous or free-form biomedical request, to decide which specialized skill/workflow to dispatch to. It is the entry funnel of the skill system — not a replacement for the analysis skills themselves.

Note

Honest scope: keyword-substring matching only. It will not understand paraphrases that contain none of the known keywords (it then returns unknown rather than guessing). Extend bioresearch/router.py:ROUTE_KEYWORDS to cover new phrasing.