Menu

Individual skill

pho-algorithmic-audits

0upvotes

Solve Public Health Observatory portal audit tasks that provide analysis_request.json and answer_template.json, including state, county, and country health/socioeconomic algorithmic audits with strict release resolution, reproducible cohorts, regression, resampling, conformal calibration, PCA, clustering, perturbation, and controlled JSON decisions. Use this skill whenever a prompt mentions the Public Health Observatory portal, PHO protocol_id values, registered audit modules, or asks for one JSON answer from portal evidence.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_023/fewshot/opencode/fewshot_attempt_03/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 11, 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

# Public Health Observatory Algorithmic Audits

Use this skill to complete one Observatory audit from the provided prompt, `analysis_request.json`, `answer_template.json`, and the read-only portal named in the prompt. The answer must be computed fresh from that request and portal evidence.

## Required References

- Read [references/portal-and-data.md](references/portal-and-data.md) before network access or release resolution.
- Read [references/protocol-methods.md](references/protocol-methods.md) when `analysis_request.json` contains one of the exact protocol IDs listed there, or when the task resembles the country burden audit.
- Read [references/statistical-primitives.md](references/statistical-primitives.md) before implementing any model, bootstrap, PCA, clustering, conformal, or perturbation module.
- Optionally import helpers from [scripts/pho_audit_helpers.py](scripts/pho_audit_helpers.py) instead of rewriting common linear algebra, PRNG, PCA, k-means, ARI, CSV, and rounding code.

## Non-Negotiables

- Use only the task prompt, the two payload JSON files, and the authorized Observatory portal evidence. Do not use cached solved outputs, evaluator assumptions, or outside datasets.
Back to top