Individual skill

pho-algorithmic-audits

Solve Public Health Observatory web-portal algorithmic audit tasks from analysis_request.json and answer_template.json, including exact PHO state, county, panel, mediation, robustness, and country-burden audit profiles. Use when a task asks Codex to resolve PHO releases and cohorts and return controlled JSON with clustered inference, nested ridge or elastic-net validation, wild bootstrap, grouped conformal calibration, PCA/k-means stability, mediation, GMM, sensitivity, or perturbation modules.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_023/fewshot/codex/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.

agent Repository topic
ai Repository topic
benchmark Repository topic
llm Repository topic
self-evolving Repository topic
self-learning Repository topic
skills Repository topic
security Derived category

Files and excerpt

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

Browse files

SKILL.mdcore · 5,095 bytes
SKILL.mdcore · 5,095 bytes
agents/openai.yamlasset · 260 bytes
references/protocol-profiles.mddoc · 21,738 bytes
scripts/pho_math.pyruns · 17,102 bytes

Read excerpt


# PHO Algorithmic Audits

## Operating Rules

Use this skill for PHO web-portal audit tasks only. Treat the active prompt, `analysis_request.json`, `answer_template.json`, and the task portal as the only task evidence.

Do not reuse solved values, states, counts, coefficients, random checkpoints, classifications, or arrays from prior examples. The examples only establish reusable method semantics. Bind all entities, measures, years, source filters, grids, seeds, replicate counts, thresholds, labels, and output vocabulary from the active request.

Do not include `protocol_registry_record` or other provenance fields in the submitted JSON unless the active `answer_template.json` explicitly requires them.

Read [references/protocol-profiles.md](references/protocol-profiles.md) before computing any audit module. Use [scripts/pho_math.py](scripts/pho_math.py) as an optional pure-Python helper for linear algebra, robust covariance, PRNGs, quantiles, PCA, k-means, ARI, and silhouette calculations.

## One-Pass Workflow