Individual skill

pho-audit-solver

Solve Public Health Observatory algorithmic transportability audits using an HTTP portal API. Covers release resolution, cohort construction, and a catalog of reusable statistical modules (fixed-effects jackknife, ridge/elastic-net CV, wild cluster bootstrap, grouped conformal, PCA clustering, source perturbation, GMM mediation, and sensitivity surfaces) with exact output formatting against a provided answer template.

experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_023/fewshot/naive/fewshot_attempt_01/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
121
Repository last updated
Oct 29, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# PHO Audit Solver

This skill equips you to solve Public Health Observatory (PHO) algorithmic audit tasks. Every task follows the same core pattern: read a prompt plus `analysis_request.json` and `answer_template.json`, gather evidence from the PHO web portal, run the declared statistical modules, and return one JSON object conforming to the template.

**What this skill covers**

- Navigating the PHO portal API to pull publication records
- Resolving final releases with revision and timestamp precedence
- Building analytic cohorts (complete, balanced, broad, dual-source, machine-learning)
- Implementing every statistical module that appears across the PHO audit family: fixed-effects OLS with jackknife inference, ridge and elastic-net nested cross-validation, PCG32/xorshift wild cluster bootstrap, grouped split conformal calibration, covariance PCA with farthest-first k-means, exhaustive source/time perturbation with Shapley attribution, difference GMM mediation, and partial-R2 sensitivity surfaces
- Formatting output exactly to an answer template, applying controlled decision rules

**What this skill does not cover**