GeoGeekLab/nature-reviewer-skills / nature-earth-system-reviewer-skills/skills/nature-atmospheric-science-reviewer-skill
nature-atmospheric-science-reviewer
VerifiedNature-style atmospheric science manuscript reviewer skill for testing observation, reanalysis, model, aerosol-cloud-radiation, extreme-event, circulation-mechanism and attribution claims against their physical evidence chain.
| File | Kind | Size |
|---|---|---|
| LICENSE | other | 1.1 KB |
| MANIFEST.json | config | 368 B |
| README.md | markdown | 7.5 KB |
| SKILL.md | skill md | 10.4 KB |
| checksums.sha256 | other | 1.7 KB |
| docs/SECURITY.md | markdown | 114 B |
| examples/evaluation_prediction.json | config | 260 B |
| references/claim_evidence_protocol.md | markdown | 550 B |
| references/domain_gate.md | markdown | 155 B |
| references/evaluation_contract.md | markdown | 306 B |
| requirements-dev.txt | markdown | 30 B |
| reviewer_db/patterns.csv | other | 17.4 KB |
| reviewer_db/patterns.jsonl | other | 55.9 KB |
| reviewer_db/summary.json | config | 919 B |
| scripts/extract_text_with_anchors.py | script | 1.2 KB |
| scripts/render_review_docx.py | script | 971 B |
| scripts/reviewer_db.py | script | 1.6 KB |
| scripts/validate_package.py | script | 928 B |
| templates/review_report.md | markdown | 953 B |
| tests/test_package.py | script | 640 B |
references/claim_evidence_protocol.md
View on GitHub# Claim–evidence protocol
For every major concern, record: the manuscript claim, direct evidence, inference step, hidden assumptions, plausible alternatives, uncertainty, scope boundary, and the smallest revision that could resolve or calibrate the claim. Do not request an experiment merely because it is interesting. Explain which decision-relevant uncertainty the requested action resolves.
Never invent lines, figures, references, data, or experimental details. When an input cannot be inspected, state that limitation and reduce confidence.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |