Individual skill

pho-audit-protocols

Complete multi-module algorithmic audit protocols for the Public Health Observatory data portal. Use when a task requires running registered PHO protocol modules (fixed-effects jackknife, nested ridge/elastic-net CV, wild cluster bootstrap, grouped conformal, trajectory PCA+k-means, source perturbation, or controlled decision gates) against the read-only PHO web portal at the task environment base URL. Covers state, county, and country-level analyses with deterministic PRNGs, release resolution, and audit-grade reproducibility requirements.

experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_023/fewshot/codex/fewshot_attempt_03/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 Protocols

Execute multi-module algorithmic audits using the Public Health Observatory (PHO) read-only data portal.

## Workflow

1. Read the task prompt and the attached analysis_request.json and answer_template.json.
2. Download all required datasets from the portal as CSV via `GET /download?dataset={name}&format=csv`.
   Base URL is `<TASK_ENV_BASE_URL>` from the prompt.
3. Resolve releases: for each (entity, year, measure, filter) combination, select greatest
   revision, then latest released_at, then lowest record id. See [references/release_resolution.md](references/release_resolution.md).
4. Build the cohort(s) specified by the request (balanced, broad, dual-source, primary, etc.).
5. Execute every audit module in the order declared by the request.
6. Apply the controlled decision gate evaluation.
Back to top