Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Redistricting Analysis with the redistverse · brycewang-stanford | DecimalAI

scienceby brycewang-stanford

Redistricting Analysis with the redistverse

brycewang-stanford/redistricting-analysis

Source brycewang-stanford/Auto-Empirical-Research-Skills ↗License NOASSERTION

Redistricting analysis in R using the redistverse ecosystem.

SkillScore86Maintained

Automatic

Government & Public Sector pack

Last verified 8/8/2026

What it changes

Passed 19 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill86%

Checks it passed that the model alone missed

The response calls the draw function.
The response identifies the S3 class as adj.
The response recommends using the baf package.

and 10 more in the full report

9 fixed10 passed either way3 still failing0 broke

Pass-rate lift: +41 pp
Tokens: +39%
Agent turns: 0%
Response time: -36%

Model gemini-3.6-flashMeasured 8/8/2026v119 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-redistricting-analysis/SKILL.md https://app.decimal.ai/s/brycewang-stanford-redistricting-analysis/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-redistricting-analysis, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/brycewang-stanford-redistricting-analysis/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-redistricting-analysis

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-redistricting-analysis/SKILL.md https://app.decimal.ai/s/brycewang-stanford-redistricting-analysis/SKILL.md

Raw file: /s/brycewang-stanford-redistricting-analysis/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-redistricting-analysis.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

To obtain official Census Bureau Block Assignment Files (BAF) for state legislative redistricting reconciliation in R, which package provides a direct function to download these BAF files?

What was checked, without and with the skill
Checked	Without skill	With skill
The response recommends using the baf package.	Missed	Passed

case-20 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md51 lines18 files

Redistricting Analysis with the redistverse

A comprehensive reference for redistricting analysis in R using the redistverse ecosystem (library(redistverse) loads redist, redistmetrics, ggredist, geomander, sf, and adj).

Standard Analysis Pipeline

Load data — Download pre-built precinct map + demographics + elections via alarmdata, or assemble your own sf object and build a redist_map. → 12-alarmdata.md
Prepare adjacency — Verify and edit the adjacency graph (remove water-body edges, fix topological errors). → 08-adj.md, 09-geomander-adjacency.md
Set constraints — Define population tolerance, county-split penalties, VRA hinge constraints, compactness. → 02-redist-constraints.md
Simulate — Run redist_smc() (recommended) or MCMC to generate an ensemble of valid plans. → 01-redist-simulation.md
Validate — Check convergence (summary()), R-hat, effective sample size, and plan diversity. → 01-redist-simulation.md
Score — Compute compactness, partisan fairness, splits, and other metrics across the ensemble. → 04–06 redistmetrics references
Visualize & compare — Map plans, plot metric distributions, compare enacted plan to the baseline. → 07-ggredist.md

Quick Navigation

Package / Topic	Reference
`redist_map`, `redist_smc`, `redist_mergesplit`, `redist_flip`, `redist_plans`, diagnostics	01-redist-simulation.md
`redist_constr`, `add_constr_splits`, `add_constr_grp_hinge`, all soft constraints	02-redist-constraints.md
`redist_enumpart`, `redist_shortburst`, `redist_cyclewalk`, `init_particles`	03-redist-advanced.md
`redistmetrics` — Polsby-Popper, Reock, spanning tree, `prep_perims`, `comp_*` functions	04-redistmetrics-compactness.md
`redistmetrics` — efficiency gap, mean-median, bias, declination, `part_*` functions	05-redistmetrics-partisan.md
`redistmetrics` — county splits, segregation, competitiveness, incumbents, `plan_parity`, `group_frac`	06-redistmetrics-other.md
`ggredist` — `geom_district`, party color scales, cartographic palettes, `theme_map`	07-ggredist.md
`adj` — adjacency graph construction, edge operations, coloring, Laplacian	08-adj.md
`geomander` — adjacency construction, contiguity checks, `seam_rip`, edge editing	09-geomander-adjacency.md
`geomander` — `geo_match`, `estimate_down/up`, `block2prec`, spatial estimation	10-geomander-spatial.md
`geomander` — downloading VEST, ALARM, DRA, HEDA, `get_lewis` election data	11-geomander-data.md
`alarmdata` — `alarm_50state_map`, pre-built datasets, caching, `alarm_add_plan`	12-alarmdata.md
`PL94171` — Census P.L. 94-171 decennial data ingestion	13-pl94171.md
`censable` (data + state IDs), `easycensus` (ACS), `tinytiger` (TIGER shapefiles)	14-census-utilities.md
`baf` — download official Census Bureau block assignment files	15-baf.md
`rict` — `gt` summary tables: population, demographics, elections, compactness, splits	16-rict.md
`redistio` — interactive Shiny plan drawing (`draw()`) and adjacency editor (`adj_editor()`)	17-redistio.md

Key Data Structures

redist_map — an sf tibble with one row per precinct. Stores the adjacency graph, population column, number of districts, and population tolerance. Created by redist_map() or downloaded via alarm_50state_map(). Standard columns include pop, pop_black, pop_hisp, pop_asian, pop_white, pop_vap, pop_bvap, ndv (Democratic votes), nrv (Republican votes), and geometry.

Track record

Benchmark

19 / 22

test cases passed, vs 10 / 22 without

Adoption

Users: 2
Times used: 30

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / Auto-Empirical-Research-Skills

skills/22-christopherkenny-skills/skills/redistricting-analysis/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1Bundled 17 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Redistricting Analysis with the redistverse

Standard Analysis Pipeline

Quick Navigation

Key Data Structures

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills