Skip to content

nature-reviewer-skills v1.0.1

Choose a tag to compare

View all tags
@GeoGeekLab GeoGeekLab released this 29 Jun 13:36
v1.0.1
13233ab

nature-reviewer-skills v1.0.1

Initial public release of GeoGeekLab nature-reviewer-skills, a research-grade suite of Nature-style reviewer skills for claim-dependent scientific peer review across Earth system science, chemistry, engineering, and materials science.

This release organizes seven domain-specific reviewer skills into a coherent skill suite for pre-submission manuscript review, evidence-chain stress testing, reviewer-perspective simulation, and research-quality improvement.

The suite is built around one central idea:

High-level scientific review is not a checklist.
It is a disciplined stress test of claims, evidence chains, uncertainty, novelty, mechanism, validation, and scope.

What is included

This release contains the following skill packages.

Earth system science umbrella

nature-earth-system-reviewer-skills is an umbrella layer for four independent Earth-system reviewer skills:

  • nature-remote-sensing-reviewer
  • nature-atmospheric-science-reviewer
  • nature-hydrology-reviewer
  • nature-climate-ecology-reviewer

The Earth-system umbrella is designed for manuscripts involving Earth observation, atmospheric systems, hydrological processes, climate-ecology interactions, carbon and nutrient cycles, biodiversity, hydroclimatic risk, environmental monitoring, and sustainability-facing environmental inference.

It is not a merged mega-skill. Each Earth-system skill remains scientifically independent, with its own SKILL.md, reviewer-memory patterns, domain gates, scripts, templates, and tests.

Other domain reviewer skills

This release also includes three independent scientific reviewer skills:

  • nature-chemistry-reviewer
  • nature-engineering-reviewer
  • nature-materials-science-reviewer

These skills extend the same reviewer-reasoning framework to chemical science, engineering systems, and materials science while preserving domain-specific standards for evidence, validation, mechanism, reproducibility, and application claims.

Repository structure

nature-reviewer-skills/
├── nature-earth-system-reviewer-skills/
│   └── skills/
│       ├── nature-remote-sensing-reviewer-skill/
│       ├── nature-atmospheric-science-reviewer-skill/
│       ├── nature-hydrology-reviewer-skill/
│       └── nature-climate-ecology-reviewer-skill/
├── nature-chemistry-reviewer-skill/
├── nature-engineering-reviewer-skill/
└── nature-materials-science-reviewer-skill/

Each skill package follows a GitHub-ready structure:

nature-*-reviewer-skill/
├── SKILL.md
├── README.md
├── MANIFEST.json
├── reviewer_db/
├── references/
├── templates/
├── scripts/
├── tests/
├── docs/
├── examples/
├── LICENSE
├── LICENSE-MIT
└── LICENSE-APACHE

Scientific design

The suite is designed around reviewer reasoning distillation, not generic writing assistance.

Instead of redistributing raw reviewer reports, the skills encode abstracted reviewer logic as reusable scientific reasoning patterns:

claim type → evidence risk → stress-test gate → reviewer concern → revision direction

The core review logic emphasizes:

  • claim-dependent review routing
  • evidence-chain stress testing
  • domain-specific reviewer gates
  • validation sufficiency
  • uncertainty propagation
  • mechanism and causality
  • reproducibility and controls
  • benchmark fairness
  • scope discipline
  • generalization boundaries
  • revision-oriented critique

The intended output is a Nature-style pre-review: rigorous, domain-aware, critical, and useful for manuscript revision.

Domain coverage

Remote sensing and Earth observation

For satellite remote sensing, Earth observation products, retrieval models, geospatial machine learning, environmental mapping, spatial validation, product uncertainty, and trend inference.

Key stress tests include product validity, spatial generalization, out-of-domain conditions, leakage, uncertainty propagation, and the distinction between observed signal, retrieved variable, proxy, and scientific interpretation.

Atmospheric science

For atmospheric observation, reanalysis, weather and climate dynamics, aerosol-cloud-radiation interactions, atmospheric chemistry, extreme events, circulation change, and AI weather or climate systems.

Key stress tests include physical consistency, model dependence, forcing and boundary conditions, attribution versus correlation, scale coupling, and dynamical interpretation.

Hydrology and water systems

For catchment hydrology, river discharge, groundwater, soil moisture, floods, droughts, water quality, water resources, hydroclimatic extremes, and water-security implications.

Key stress tests include hydrological variable identity, water balance closure, station-to-basin transferability, concentration versus load, calibration and validation, equifinality, and policy-relevant overclaiming.

Climate, ecology, and sustainability-facing environmental science

For climate impacts, ecological response, biodiversity, ecosystem stability, carbon and nutrient cycles, land-use change, conservation inference, and coupled human-natural systems.

Key stress tests include causal inference, ecological mechanism, spatial confounding, climate-driver separation, temporal lags, resilience claims, carbon-cycle evidence, and sustainability implication strength.

Chemistry

For synthesis, catalysis, analytical chemistry, chemical biology, mechanistic chemistry, computational chemistry, and AI-enabled molecular discovery.

Key stress tests include compound identity, purity, controls, reproducibility, reaction scope, selectivity, catalytic metrics, mechanism, and computational-experimental consistency.

Engineering

For engineering systems, platforms, devices, robotics, biomedical engineering, environmental engineering, algorithms embodied in physical systems, and translational engineering claims.

Key stress tests include requirement-design-validation coherence, prototype versus platform claims, benchmark fairness, operating envelope, failure modes, deployment constraints, and real-world utility.

Materials science

For materials design, synthesis, processing, structure-property relationships, characterization, stability, degradation, performance benchmarking, and application-facing materials claims.

Key stress tests include material identity, structural evidence, synthesis-processing-property linkage, durability, mechanism of performance, benchmark comparability, scalability, and application boundaries.

What this release is for

This release is intended for:

  • researchers preparing high-level journal submissions
  • graduate students learning how top-tier peer review reasons
  • principal investigators conducting internal manuscript pre-review
  • scientific teams building manuscript quality-control workflows
  • AI-assisted research systems requiring domain-aware review logic
  • developers building structured scientific-review agents
  • researchers interested in reviewer reasoning distillation and scientific evaluation systems

The suite is especially useful when a manuscript makes strong claims about mechanism, generalization, novelty, prediction, attribution, application readiness, or sustainability relevance.

What this release is not

This repository is not:

  • an official Nature Portfolio resource
  • a replacement for real peer review
  • a guarantee of journal acceptance
  • a generic writing-polish prompt library
  • a redistributed peer-review corpus
  • a collection of raw reviewer reports
  • a tool for identifying or imitating individual reviewers

It is an independent research and engineering project for strengthening manuscripts before formal peer review.

Provenance and copyright boundary

The reviewer-memory layer is based on abstracted, non-verbatim reasoning patterns.

This release does not redistribute:

  • raw peer-review PDFs
  • long reviewer comments
  • identifiable reviewer language
  • full article text
  • private or non-public review material

Only generalized review logic, domain gates, metadata structures, templates, scripts, and validation utilities are included.

Validation

The package is designed for local validation through included scripts.

Umbrella-level validation:

python nature-earth-system-reviewer-skills/scripts/validate_umbrella.py nature-earth-system-reviewer-skills
python -m compileall -q nature-earth-system-reviewer-skills/scripts
python -m pytest -q nature-earth-system-reviewer-skills/tests

Individual skill validation:

python <skill-folder>/scripts/validate_package.py <skill-folder>
python -m compileall -q <skill-folder>/scripts
python -m pytest -q <skill-folder>/tests

Release status

This is the first consolidated suite release.

It establishes:

  • the top-level nature-reviewer-skills repository
  • the Earth-system umbrella structure
  • seven independent Nature-style reviewer skills
  • package-level validation scripts
  • consistent skill metadata and naming
  • GitHub-ready repository organization
  • a research-oriented public README and release structure

License

This repository is released under the MIT License.

Individual skill packages may include package-level license files and dual-license metadata where applicable.

Disclaimer

This project is independently developed by GeoGeekLab.

It is not affiliated with, endorsed by, or approved by Nature Portfolio, Springer Nature, or any journal publisher.

The skills are intended to support scientific self-review, manuscript improvement, reviewer-perspective simulation, and research-quality control. They should not be treated as editorial decisions, official peer-review outcomes, or publication guarantees.

Assets 2
Loading