fcr-figures-and-tables — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited fcr-figures-and-tables (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Exhibits are where an agronomy reviewer checks whether the result is real and general. At FCR every exhibit must be self-contained and quantitatively complete: units, sample/replication, and a measure of error or variability (SE, SED, or LSD) belong on the exhibit itself.
and footnote alone. State the crop, cultivar(s), environments (sites×seasons), N/replication, units (SI), and what the value is (mean? adjusted mean?).
defined in the caption — never bare means. For curves, show fitted line + CI and the data.
density); an AMMI/GGE biplot or Finlay–Wilkinson plot for G×E; observed-vs-simulated with the 1:1 line for model evaluation; time series vs. thermal time/phenology with weather overlays for development.
needless colour. Vector output (PDF/EPS) for print.
figure values are internally consistent and consistent with the text.
The right exhibit follows from the agronomic question. Pair each with the annotation an FCR reviewer expects.
| Question | Exhibit | Must annotate |
|---|---|---|
| Yield vs. N/water/density | fitted response curve + points | model, SED or CI, units |
| Genotype ranking | AMMI / GGE / Finlay–Wilkinson | environments labelled, % variance |
| Model performance | observed-vs-simulated, 1:1 line | RMSE, nRMSE, EF, n; validation only |
| Treatment means by environment | adjusted-means table | SED/LSD, α, df, replication |
Illustrative. A first-draft Table 2 for the maize MET lists raw plot means with a/b/c letters across all 5 N rates and no error term — two flags at once: letters on a quantitative dose hide the response shape, and raw means do not match the mixed-model output. The fix is two exhibits: an N response curve per environment with fitted line and SED bar (α = 0.05), plus an adjusted-means table with one SED column — both self-contained and reproducible from the script.
Treat this skill as an executable review pass, not a prose hint. First lock the crop system, environment structure, GxE logic, and yield or physiology endpoint; then judge whether the current manuscript answers the venue's real reader: agronomy reviewers who expect field-based, multi-environment evidence and crop-level general significance.
claim / evidence / risk / manuscript location rows, so the next agent can edit rather than rediscover the issue.resources/official-source-map.md has been checked for upload-week rules and the manuscript has one concrete fix for the largest venue-specific risk.【Main exhibit】what it shows + why this exhibit type
【Self-contained?】caption + labels + crop/cultivar + envs + N + units present? [Y/N]
【Error shown?】SED / LSD / CI with α stated? [Y/N]
【Accessible?】grayscale-legible + colourblind-safe? [Y/N]
【Article vs supplement】split decided
【Reproducible?】matches analysis output + data deposit? [Y/N]
【Next】fcr-reporting-and-data-policy../../resources/external_tools.md — plotting and G×E-biplot tooling../../resources/official-source-map.md — reporting expectations (units, weather vs. phenology)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.