Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

autoskill-workflow-discovery

Étoiles1

Forks0

Mis à jour1 juillet 2026 à 23:33

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.

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

Autres occupations informatiquesProfessions informatiques et mathématiques·SOC 15-1299

SKILL.md

readonly

name	autoskill-workflow-discovery
description	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.
user-invocable	true
license	Apache-2.0

Autoskill Workflow Discovery

Source adaptation: BioRouter-original synthesis inspired by Scientific Agent Skills workflow-discovery patterns, rewritten under Apache-2.0. Do not copy upstream text; use this as a native BioRouter skill-design and governance workflow.

When to Use

Use this skill when the user wants to convert repeated work into a reusable BioRouter skill, project hook, checklist, or template. This is for pattern mining and skill drafting, not for silently installing automation.

Intake

Collect:

The repeated workflow or recent examples to inspect.
Trigger conditions: files, phrases, repo paths, apps, data types, or task stages.
Desired output: new skill, update to an existing skill, hook proposal, checklist, template, or registry plan.
Safety boundaries: what must never be automated, what requires confirmation, and what can be auto-applied.
Ownership and destination repo.

Discovery Pass

Identify repeated decision points, not just repeated commands.
Separate stable domain knowledge from project-specific preference.
Record the inputs the model needs before acting.
Record the output shape the user repeatedly wants.
Identify checks that can be enforced as BioRouter hooks and checks that should remain advisory.
Keep external credentials, private datasets, and PHI out of the skill body.

BioRouter Output Choices

Use a top-level SKILL.md when the pattern is reusable across projects.
Use a project hook in .biorouter/hooks.yaml when a guardrail should warn or block.
Use develop-biorouter-extension when repeated work needs tools, APIs, credentials, or local compute.
Use scientific-research, replication-package-audit, or a domain BioSkill as the parent route when the workflow is scientific.

Skill Draft Checklist

Every proposed skill must include:

name, description, license: Apache-2.0, and appropriate user-invocable.
A precise "When to Use" section.
Intake questions.
Routing rules to existing BioRouter skills/extensions.
Verification gates.
A response shape.
Provenance and license notes.

Review Gates

Before recommending installation:

Show exactly what pattern was observed and what evidence supports it.
Explain why an existing BioRouter skill is not enough.
Mark private/project-specific details for removal.
Prefer a small first version that can be tested on one real task.
Ask before creating hooks that warn/block user actions.

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

arbor-optimization

BaranziniLab/biorouter-skills

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.

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	autoskill-workflow-discovery
description	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.
user-invocable	true
license	Apache-2.0

Autoskill Workflow Discovery

When to Use

Intake

Collect:

The repeated workflow or recent examples to inspect.
Trigger conditions: files, phrases, repo paths, apps, data types, or task stages.
Desired output: new skill, update to an existing skill, hook proposal, checklist, template, or registry plan.
Safety boundaries: what must never be automated, what requires confirmation, and what can be auto-applied.
Ownership and destination repo.

Discovery Pass

Identify repeated decision points, not just repeated commands.
Separate stable domain knowledge from project-specific preference.
Record the inputs the model needs before acting.
Record the output shape the user repeatedly wants.
Identify checks that can be enforced as BioRouter hooks and checks that should remain advisory.
Keep external credentials, private datasets, and PHI out of the skill body.

BioRouter Output Choices

Use a top-level SKILL.md when the pattern is reusable across projects.
Use a project hook in .biorouter/hooks.yaml when a guardrail should warn or block.
Use develop-biorouter-extension when repeated work needs tools, APIs, credentials, or local compute.
Use scientific-research, replication-package-audit, or a domain BioSkill as the parent route when the workflow is scientific.

Skill Draft Checklist

Every proposed skill must include:

name, description, license: Apache-2.0, and appropriate user-invocable.
A precise "When to Use" section.
Intake questions.
Routing rules to existing BioRouter skills/extensions.
Verification gates.
A response shape.
Provenance and license notes.

Review Gates

Before recommending installation:

Show exactly what pattern was observed and what evidence supports it.
Explain why an existing BioRouter skill is not enough.
Mark private/project-specific details for removal.
Prefer a small first version that can be tested on one real task.
Ask before creating hooks that warn/block user actions.