Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

arbor-optimization

Étoiles1

Forks0

Mis à jour1 juillet 2026 à 23:33

Run evaluator-driven hypothesis trees for improving research artifacts, prompts, analyses, and designs. Use when a task needs branch-and-prune exploration, rubric scoring, iterative refinement, or explicit comparison of competing scientific/workflow alternatives.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

BaranziniLab

BaranziniLab/biorouter-skills

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	arbor-optimization
description	Run evaluator-driven hypothesis trees for improving research artifacts, prompts, analyses, and designs. Use when a task needs branch-and-prune exploration, rubric scoring, iterative refinement, or explicit comparison of competing scientific/workflow alternatives.
user-invocable	true
license	Apache-2.0

Arbor Optimization

Source adaptation: BioRouter-original synthesis inspired by Scientific Agent Skills tree-optimization patterns, rewritten under Apache-2.0. This is a native BioRouter iterative-improvement workflow.

When to Use

Use this skill when a single-shot answer is not enough and the user wants structured exploration: competing hypotheses, analysis plans, designs, prompts, figures, abstracts, protocols, or implementation options.

Define the Tree

Before branching, define:

Objective and non-negotiable constraints.
Evaluation rubric with 3-7 criteria.
Evidence sources or tests available.
Maximum branch count and stopping rule.
What counts as a failed branch.

Branching Pattern

Create 3-5 materially different candidate branches.
For each branch, state the core idea, assumptions, expected upside, and failure mode.
Score branches against the rubric.
Prune weak branches with a short reason.
Refine the strongest branch once, incorporating the best elements from competitors.
Produce a final recommendation with the rejected alternatives preserved in a compact comparison.

BioRouter Routes

Use empirical-benchmark-harness when the branch can be tested against known-answer empirical cases.
Use replication-package-audit when the winning branch creates a runnable analysis.
Use claim-evidence-integrity for manuscript or report branches.
Use scientific-visual-communication for figure/poster/slide alternatives.
Use domain skills or BRXT extensions before scoring branches that depend on platform data.

Quality Gates

Do not call a branch "best" unless:

The rubric is visible.
Evidence or test results are tied to each score.
Tradeoffs are explicit.
The final answer names what would change the recommendation.
The user can rerun or audit the decision.

Response Shape

Return:

Objective.
Rubric.
Branch table.
Pruned branches.
Refined winner.
Verification still needed.

Plus depuis ce dépôt

même dépôt

computational-fluid-dynamics

BaranziniLab/biorouter-skills

Plan and review computational fluid dynamics workflows with meshes, boundary conditions, turbulence models, OpenFOAM/FluidSim-style solvers, validation cases, convergence checks, and reproducible simulation artifacts. Use when users mention CFD, fluid dynamics, Navier-Stokes, meshing, turbulence, OpenFOAM, or flow simulation.

2026-07-011

autoskill-workflow-discovery

BaranziniLab/biorouter-skills

Detect repeated user workflows and draft native BioRouter skills, hooks, or checklist updates from observed work patterns. Use when users ask to turn repeated work, screen-history patterns, project routines, or recurring guardrails into reusable BioRouter skills.

2026-07-011

bids-neuroimaging

BaranziniLab/biorouter-skills

Plan and audit BIDS neuroimaging datasets, derivatives, validation, metadata, and reproducible preprocessing. Use when users mention BIDS, fMRI, MRI, EEG/MEG/iEEG, DICOM conversion, dataset_description.json, participants.tsv, or neuroimaging derivatives.

2026-07-011

clinical-ai-modeling

BaranziniLab/biorouter-skills

Plan and review clinical AI modeling workflows with EHR cohorts, PyHealth-style tasks, validation, bias checks, calibration, safety boundaries, and no-PHI handling. Use when users ask about clinical prediction models, risk scores, treatment-response ML, medical reports, or clinical model evaluation.

2026-07-011

general-time-series-forecasting

BaranziniLab/biorouter-skills

Plan and review general time-series forecasting with classical models, ML, foundation models, backtesting, leakage checks, and uncertainty. Use for non-omics forecasting, sensor streams, operations, finance, clinical vitals, demand, or irregular temporal data.

2026-07-011

hugging-science-resource-discovery

BaranziniLab/biorouter-skills

Find and evaluate Hugging Face scientific models, datasets, Spaces, and papers with license, provenance, benchmark, and fit checks. Use when users ask for scientific ML resources, model cards, datasets, embeddings, checkpoints, or reproducible AI assets from Hugging Face.

2026-07-011

name	arbor-optimization
description	Run evaluator-driven hypothesis trees for improving research artifacts, prompts, analyses, and designs. Use when a task needs branch-and-prune exploration, rubric scoring, iterative refinement, or explicit comparison of competing scientific/workflow alternatives.
user-invocable	true
license	Apache-2.0

Arbor Optimization

Source adaptation: BioRouter-original synthesis inspired by Scientific Agent Skills tree-optimization patterns, rewritten under Apache-2.0. This is a native BioRouter iterative-improvement workflow.

When to Use

Define the Tree

Before branching, define:

Objective and non-negotiable constraints.
Evaluation rubric with 3-7 criteria.
Evidence sources or tests available.
Maximum branch count and stopping rule.
What counts as a failed branch.

Branching Pattern

Create 3-5 materially different candidate branches.
For each branch, state the core idea, assumptions, expected upside, and failure mode.
Score branches against the rubric.
Prune weak branches with a short reason.
Refine the strongest branch once, incorporating the best elements from competitors.
Produce a final recommendation with the rejected alternatives preserved in a compact comparison.

BioRouter Routes

Use empirical-benchmark-harness when the branch can be tested against known-answer empirical cases.
Use replication-package-audit when the winning branch creates a runnable analysis.
Use claim-evidence-integrity for manuscript or report branches.
Use scientific-visual-communication for figure/poster/slide alternatives.
Use domain skills or BRXT extensions before scoring branches that depend on platform data.

Quality Gates

Do not call a branch "best" unless:

The rubric is visible.
Evidence or test results are tied to each score.
Tradeoffs are explicit.
The final answer names what would change the recommendation.
The user can rerun or audit the decision.

Response Shape

Return:

Objective.
Rubric.
Branch table.
Pruned branches.
Refined winner.
Verification still needed.