GeoGeekLab/nature-reviewer-skills / nature-earth-system-reviewer-skills/skills/polar-earth-system-review-orchestrator
polar-earth-system-review-orchestrator
VerifiedCross-disciplinary polar Earth-system manuscript review orchestrator for Arctic, Antarctic and Southern Ocean research. Routes claims to existing domain reviewer skills and applies polar-specific evidence gates for sparse observations, cryosphere variables, product dependence, conservation budgets, coupled attribution, paleoclimate archives and regional research responsibility.
gates/permafrost_ecology_biogeochemistry.md
View on GitHub# Permafrost Ecology Biogeochemistry
Permafrost state, process benchmarking, carbon pathways, ecological transfer, function, methane and shifting baselines.
## Internal questions
- **Ground-temperature trend is generalized to degradation:** A temperature increase at boreholes is described as widespread thaw, ground-ice loss, or landscape collapse without corresponding state observations. Resolution: Report depth-specific temperatures and add active-layer, deformation, or ground-ice evidence before claiming degradation.
- **Model permafrost process is not benchmarked:** A land model produces permafrost extent or carbon feedback without testing snow insulation, soil physics, organic layers, hydrology, and excess ice. Resolution: Benchmark process diagnostics against observations and perturb structural choices, not only bulk extent.
- **Carbon release is inferred from thaw extent:** Projected thaw area or active-layer deepening is translated directly into carbon or methane emissions. Resolution: Use process-resolving carbon evidence, separate potential stock from realized flux, and report pathway uncertainty.
- **Microbiome model extrapolates beyond sampled systems:** A predictive ecological model trained on accessible glacier-fed streams is applied globally without covering climate, geology, hydrology, and biogeographic domains. Resolution: Map environmental coverage, use leave-region-out validation, quantify extrapolation, and limit global claims to supported domains.
- **Community composition is equated with ecosystem function:** Taxonomic or gene-marker shifts are interpreted as changes in productivity, export, greenhouse-gas cycling, or resilience without functional measurement. Resolution: Add rate or functional assays, triangulate with biogeochemistry, and calibrate functional language.
- **Freshwater methane filter lacks system boundary:** Oxidation or filtering efficiency is interpreted as a fixed ecosystem property without testing residence time, stratification, oxygen, transport, and seasonality. Resolution: Define the control volume and period, quantify gross production, oxidation, storage, and evasion, and test warming-induced transport changes.
- **Ice-loss effect confounded by co-varying drivers:** Ecological change attributed to sea-ice or glacier loss is not separated from temperature, nutrients, light, freshwater, turbidity, habitat, and circulation. Resolution: Use experiments, natural gradients, mediation, or process models to discriminate drivers and report unresolved confounding.
- **Ecological baseline is shifting or incomplete:** A short modern baseline is treated as undisturbed or representative despite rapid warming, harvest, pollution, or earlier cryosphere change. Resolution: Justify the baseline with historical, paleo, or long-term data and show sensitivity to alternative reference periods.
Use only when relevant to a central claim. Do not expose this gate name or pattern IDs in the final referee report.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |