Thesis data analysis plotting

Skill lihongqing2001-gif/chinese-thesis-production-skills/skills/thesis-data-analysis-plotting

Evidence-first Codex skills for guided Chinese STEM thesis production

Install

npx -y skills add lihongqing2001-gif/chinese-thesis-production-skills --skill thesis-data-analysis-plotting

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

13 days oldThe repository was created 13 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Plan, audit, and produce traceable thesis data analyses and publication-quality plots with OriginPro, Python, or R. Use for raw-data organization, statistics, fitting, error bars, axis and unit design, laboratory graph templates, multi-panel layouts, vector export, plot provenance, or when thesis figures are unreadable, distorted, inconsistent, or based only on screenshots.

SKILL.md

2.8 KB, as published. Nobody here has run it

Thesis Data Analysis and Plotting

Treat a graph as a reproducible analysis artifact, not as decoration.

Required inputs

Immutable raw numeric or native instrument data.
Sample/variable dictionary with units and replicate meaning.
Preprocessing and exclusion log.
Analysis plan covering summary, uncertainty, tests, fits, and comparisons.
plot-spec.json following references/plot-spec.md.
School or laboratory style profile.

Do not use a screenshot as final numeric evidence. Digitized literature or legacy-image data must remain a labeled candidate until independently verified.

OriginPro path

Read references/origin-workflow.md. Prefer a recorded manual workflow that any user can reproduce. Use the originpro Python package or LabTalk only when OriginPro is installed, the relevant version is known, and automation is tested on the target machine.

python scripts/validate_plot_spec.py plot-spec.json --project-root . --strict
python scripts/build_origin_workbook_plan.py plot-spec.json --output reports/origin-plan.md

If Origin is unavailable, generate the same plot from the same specification with Python/matplotlib or R/ggplot2. The evidentiary and visual requirements do not change.

Analysis rules

Define independent and technical replicates before statistics.
Display uncertainty when a quantitative comparison uses replicated measurements.
Preserve raw points where scientifically useful.
For fitting, report the model, parameter meanings, constraints, goodness-of-fit, and residual diagnostics.
Record every transformation and excluded observation with a reason.
Use axis ranges and baselines that represent the data honestly.

Read references/statistics-and-fits.md before adding significance marks or fitted curves.

Visual rules

Derive fonts, line widths, symbols, colors, and page width from the school/lab profile.
Confirm readability at final Word/PDF display size.
Preserve aspect ratio; never stretch a graph to fill a page.
Group panels only when they answer one comparison question.
Export an editable/vector file when compatible plus a high-resolution raster fallback.
Register the raw data, native project, exported figure, specification, and hashes in the figure manifest.

Route final caption, panel, and Word-layout checks to thesis-figure-table-audit.