Ready to supercharge your AI agents?

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

Draft Paper · brycewang-stanford | DecimalAI

documentationby brycewang-stanford

Draft Paper

brycewang-stanford/draft-paper

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

Draft sections of the sewage-house-prices academic paper. Handles section drafting for the Overleaf LaTeX manuscript, notation protocol, anti-hedging, and humanizer pass. This skill should be used when asked to "draft the paper", "write up the results", "write the intro", or draft any section of the manuscript.

NewMaintained

Automatic

Writing & Editing pack

Last verified 8/8/2026

What it changes

Passed 5 of 13 test cases with the skill, and 5 of 13 without it.

Without skill41%

With skill41%

Checks it passed that the model alone missed

Uses H float placement instead of htbp.
Targets 04_hydraulics_instrument.tex for drafting.
Uses TBD placeholders for missing empirical results.

and 2 more in the full report

4 fixed5 passed either way9 still failing4 broke

Pass-rate lift: 0 pp
Tokens: +75%
Agent turns: 0%
Response time: -12%

Model gemini-3.6-flashMeasured 8/8/2026v19 of 22 cases passed with skill · 13 comparable

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-draft-paper/SKILL.md https://app.decimal.ai/s/brycewang-stanford-draft-paper/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-draft-paper, 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-draft-paper/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-draft-paper

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

Please draft the section on our hydraulic capacity instrument (`instrument`). Which file in `docs/overleaf/` should this section target?

What was checked, without and with the skill
Checked	Without skill	With skill
Targets 04_hydraulics_instrument.tex for drafting.	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.md151 linessingle file

Draft Paper

Draft a section (or full draft) of the "Sewage in Our Waters" academic paper on the causal impact of sewage spills on house prices and rents in England.

Input: $ARGUMENTS — section name optionally followed by specific instructions or notes.

Project-Specific Context

Paper Structure

The manuscript lives in docs/overleaf/ with this structure:

_main.tex — Master document (KOMA-Script scrartcl, APA biblatex, libertinus font)
01_introduction.tex — Introduction
02_background_context.tex — UK sewage policy and institutional background
03_motivating_evidence.tex — Descriptive evidence and stylised facts
04_hydraulics_instrument.tex — Hydraulic capacity instrument
05_research_question.tex — Identification strategy and empirical specification
100_appendix_descriptives.tex — Appendix: descriptive statistics
101_appendix_results.tex — Appendix: supplementary results
102_appendix_dry_spills.tex — Appendix: dry spill analysis
103_appendix_data.tex — Appendix: data documentation
glossary.tex — Glossary of terms
refs.bib — Bibliography (APA style via biblatex)

Generated Output

output/tables/*.tex — Regression tables (modelsummary → LaTeX with tabularray)
output/figures/ — Figures (maps, event studies, scatter plots)
book/ — Quarto website with exploratory analysis (.qmd files)

Econometric Approaches

The paper uses multiple identification strategies:

Hedonic regressions — Cross-sectional: spill count/hours (continuous + bins) × prior/full period, with LSOA FE
Repeat sales — Within-property variation (Palmquist 1982 approach)
Long difference — 250m grid-level changes, weighted/unweighted × all/exposed grids
News/media DiD — Google Trends and LexisNexis media coverage as treatment
Upstream/downstream — Directional spillover via river network topology

Track record

Benchmark

5 / 13

test cases passed, vs 5 / 13 without

Adoption

Users: 2
Times used: 32

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/41-sticerd-eee-sewage-econometrics-check/skills/draft-paper/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1

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

Draft Paper

Project-Specific Context

Paper Structure

Generated Output

Econometric Approaches

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills