Individual skill
public-health-observatory-audits
Use this skill for Public Health Observatory tasks that require solving registered state, county, or country audit analyses from a read-only PHO Web portal and returning a strict JSON answer_template result. Trigger on prompts mentioning PHO, Public Health Observatory, protocol_id values such as PHO_STATE_TRANSPORT_AUDIT_V1, PHO_COUNTY_MEDIATION_TRANSPORT_V1, PHO_STATE_ROBUSTNESS_TRANSPORT_V1, PHO_COUNTY_PANEL_TRANSPORT_V1, or country burden revision audits, especially when the task asks for publication/cohort resolution, jackknife, nested ridge or elastic-net, wild bootstrap, grouped conformal calibration, PCA clustering, source perturbation, or controlled decisions.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_023/fewshot/cc/fewshot_attempt_02/SKILL.md
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.
- 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 · 4,510 bytesSKILL.mdcore · 4,510 bytesSKILL.mdcore · 4,510 bytesSKILL.mdcore · 4,510 bytesSKILL.mdcore · 4,510 bytesreferences/protocol-workflows.mddoc · 17,799 bytesreferences/statistical-methods.mddoc · 7,457 bytesscripts/check_answer_shape.pyruns · 2,330 bytesscripts/pho_snapshot.pyruns · 2,161 bytes
Read excerpt
# Public Health Observatory Audits
Use this skill to solve PHO audit prompts from the supplied portal and payload files. The task is usually graded as exact structured data, so prioritize deterministic evidence resolution, declared ordering, unrounded internal calculations, and exact JSON shape over narrative explanation.
## First Pass
1. Read the user's prompt, `analysis_request.json`, and `answer_template.json`.
2. Extract the portal base URL from the prompt. Do not hardcode a training URL.
3. Identify the workflow:
- If `analysis_request.json` has a recognized `protocol_id`, read `references/protocol-workflows.md` and use only that exact protocol profile.
- If there is no recognized `protocol_id` but the template is a country burden revision audit, read the country workflow in `references/protocol-workflows.md`.
- For formulas, tie-breaking, PRNGs, PCA, clustering, and validation, read `references/statistical-methods.md`.
4. Resolve one effective request before fetching or computing data. Apply any direct keys and `_overrides` sections to the exact canonical target; deep-merge objects, replace arrays whole, replace scalars exactly, and reject unknown targets or type coercions.
5. Fetch portal evidence, preferably with CSV downloads: