agentleFS
Sign inStart free
AlessandroCaforioAlessandroCaforio/Academic-Writing/.claude/skills/generate-maps/SKILL.md

generate-maps

Skill17 starsChanged 9 months agoMITView on GitHub

Regenerate all CZ choropleth maps for the thesis (Frey et al. style)

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the map generation command:

    line 24
  2. Very specific:

    If no arguments are provided, use all.

    line 32
  3. Distinctive:

    If the thesis needs recompilation (because figure files changed), run:

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Generate Maps

Regenerate all commuting-zone choropleth maps used in the thesis. Maps follow the visual style of Frey, Berger & Chen (2018) "Political Machinery": borderless CZ polygons, thin state boundary overlays, sequential warm palette for task displacement, diverging blue-red for ideology.

Arguments

  • (no args) — regenerate all 4 standard figures
  • election-td — only the 2x2 election-year TD maps
  • election-ideo — only the 2x2 election-year ideology maps
  • allyears-td — only the 2x4 all-years TD maps (appendix)
  • allyears-ideo — only the 2x4 all-years ideology maps (appendix)
  • single --year YYYY --var COLNAME — one full-size map

Steps

  1. Run the map generation command:
cd /Users/alessandro/Projects/Tesi && python3 -m src.geo_viz <COMMAND>

Where <COMMAND> is one of: all, election-td, election-ideo, allyears-td, allyears-ideo, single --year YYYY --var td_cz.

If no arguments are provided, use all.

  1. Report which figures were saved to results/figures/.
  2. If the thesis needs recompilation (because figure files changed), run:
cd /Users/alessandro/Projects/Tesi/thesis && tectonic main.tex 2>&1 | tail -5

Output Files

CommandOutput
election-tdfig_cz_map_td_elections.pdf/.png
election-ideofig_cz_map_ideo_elections.pdf/.png
allyears-tdfig_cz_map_td_all_years.pdf/.png
allyears-ideofig_cz_map_ideo_all_years.pdf/.png
singlefig_cz_map_{var}_{year}.pdf/.png

Dependencies

  • src/geo_viz.py — MapEngine class
  • data/reference/cz_boundaries.geojson — CZ polygons (722 CZs, Albers projection)
  • data/reference/state_boundaries.geojson — State outlines (49 states)
  • results/panels/cz_analysis_panel.csv — CZ-level panel data

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free