data-profile-and-plot
/data-profile-and-plot
Table data profile and publishing grade mapping skills: statement of line particle size and caliber before doing profile(Lines/Missing/Repeat/ Type/Distribution), cleaning logs, diagram specifications (types)/Axis/Units/Error stick./seed),Final check with a stand-alone script “The figure is consistent with the figure.”。♪ When the user wants ♪ EDA、It is used for cleaning, drawing, reporting or multi-pane comparison.
- Author
- jiangfeng-strathclyde ↗
- Repository
- Athena ↗
- Licence
- MIT
- Last repository change
- 13.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Table data profile and publishing grade mapping skills: statement of line particle size and caliber before doing profile(Lines/Missing/Repeat/ Type/Distribution), cleaning logs, diagram specifications (types)/Axis/Units/Error stick./seed),Final check with a stand-alone script “The figure is consistent with the figure.”。♪ When the user wants ♪ EDA、It is used for cleaning, drawing, reporting or multi-pane comparison.
Triggers from the description
Original author description
Table data profile and publishing grade mapping skills: statement of line particle size and caliber before doing profile(Lines/Missing/Repeat/ Type/Distribution), cleaning logs, diagram specifications (types)/Axis/Units/Error stick./seed),Final check with a stand-alone script “The figure is consistent with the figure.”。♪ When the user wants ♪ EDA、It is used for cleaning, drawing, reporting or multi-pane comparison.
How it works
- Trigger scene
- Process (five steps, in order not to jump)
- Chart specification (publishing level)
- Red Line
- Output
- Analysis of results of collaboration skills analyze-results;Chart of the paper paper-figur
SKILL.md preview
--- license: MIT name: data-profile-and-plot description: >- Table data profile and publishing grade mapping skills: statement of line particle size and caliber before doing profile(Lines/Missing/Repeat/ Type/Distribution), cleaning logs, diagram specifications (types)/Axis/Units/Error stick./seed),Final check with a stand-alone script “The figure is consistent with the figure.”。♪ When the user wants ♪ EDA、It is used for cleaning, drawing, reporting or multi-pane comparison. version: 1.0.0 --- # Data Profile & Plot(Parsing + (publishing grade drawings) ## Trigger scene - “Take a look at this. CSV/Parquet/SQLite What do you look like?”“Draw a comparison.”“Reporting Chart”; - Papers/Results maps, melting maps, multi-pane maps in the report; - Any tabular data tasks that need to be cleaned up before they can be visualized. ## Process (five steps, in order not to jump) 1. **Declares particle size (grain)**:What's a line? What's the only key? Follow up. join Do you think it'll blow up? `PROFILE.md` First row; particle size is unclear. 2. **Profile**:Number of rows, missing rates, repeat keys, type extrapolation, key column distribution (segment instead of average), time/Group coverage. Output. `PROFILE.md` + Machine reading `profile.json`。 3. **Purge Log**:(b) Deleting samples must keep the original lines and be noted, and should not be allowed to be lost in silence. 4. **Diagram specification first**:Prescription Specifications——Charts, figuresx/y Meaning and unit, range of coordinates (not to cut misdirection), error rod caliberstd / sem / Runtime Variation)seed and n、Colour-blind friendly palettes, vector output. 5. **Independent Validation**:Another script, which is not consistent with the original data recalculation figure for each mark and the statistics. FAIL;Diagrams must contain n With the caliber statement. ## Chart specification (publishing level) - Default matplotlib/seaborn Pure style; forbidden 3D (a) Pie charts, information-free gradients background; - Fonts ≥ (a) The minimum word number of the periodical; the multi-faceted uniform coordinates scale or a visible indication of different scales; - The comparison map must contain a baseline and uncertainty zone; seed Curves shall not be drawn to conclusions; - Output PDF/SVG Vector + 300dpi PNG backups;file names with calibre suffix (e.g. `_scene-held-out`)。 ## Red Line - Non-compilation of data, non-refilling of points, no extrapolation of undetected areas; absence of measurements leads to a lack of measurements; - Inconsistent axle creates a perception of difference; if the magnitude must be cut, it is clearly marked break; - “No significant differences”These words require statistical permission:|Δ| Falling in a variable zone between run-times and p>0.05 (b) To be able to write; - When the figure is not in line with the text, the figure is closed and the data pipe is fixed before the chart is fixed. ## Output - `PROFILE.md` / `profile.json`; - `CLEANING_LOG.md`; - `figures/`(Vector + PNG)and `figure_spec.yaml`; - `verify_figures.py`(Independent recalculation of scripts. ## Analysis of results of collaboration skills `analyze-results`;Chart of the paper `paper-figure`;Digital audits `paper-claim-audit`; Remote sensing domain calibre `remote-sensing-workbench`。
Versions
The database has no other skills named data-profile-and-plot.
Database snapshot: 13.11.2026 · package version 93b82e962ca8 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90plot-eda
Design an exploratory data analysis workflow for a dataset. Use when asked to "explore this dataset", "run an EDA", or "what is in this data". - 100plot-styling
This skill should be used when the user asks to "plot data", "make a plot for a paper", "make a publication plot", "create a journal-quality plot", "matplotlib for a figure", "use seaborn", "use plotnine", "use ggplot in Python", "improve plot quality", "style my plot", "clean… - 90clean-recon
Audit existing data cleaning code — find missing validation, silent data loss, and quality gaps. Use when asked to "audit our data cleaning", "are we losing data silently", or "find data quality gaps". - 100data-quality-profile
Profiles a CSV or Parquet table (types, missing values, ranges, duplicates, extreme values, mixed types) and compares two snapshots of the same table for drift (schema changes, missing-value shifts, distribution shift measured with PSI). Use when someone asks whether a dataset… - 90data-analyst-workflow
Use when coordinating an end-to-end data analysis workflow, or when a request spans data cleaning, data quality, feature engineering, SQL, or business intelligence reporting. - 98data-analysis
End-to-end quantitative data work — cleaning, exploration, statistical testing, modeling, visualization, and reproducible scripting in Python or R. Handles messy CSVs, survey data, time series, panel data, and small-to-medium datasets. Produces analysis scripts and a written…