Individual skill
public-health-observatory-audits
Use for Public Health Observatory Web portal tasks that ask for registered algorithmic audits, transportability checks, robustness gates, PHO protocol IDs, or answer_template.json JSON submissions. This skill is especially relevant for state, county, and country PHO audits involving release resolution, cohorts, jackknife/bootstrap diagnostics, nested ridge or elastic-net validation, grouped conformal calibration, PCA clustering, source perturbation, GMM mediation, and controlled publication decisions.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_023/fewshot/opencode/fewshot_attempt_01/SKILL.md
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
- engineering 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 · 4,067 bytesSKILL.mdcore · 4,067 bytesSKILL.mdcore · 4,067 bytesreferences/portal-data.mddoc · 4,756 bytesreferences/protocol-profiles.mddoc · 18,371 bytesscripts/pho_common.pyruns · 18,380 bytes
Read excerpt
# Public Health Observatory Audits
Use this skill to solve PHO audit prompts against the read-only Observatory portal. The expected output is usually one JSON object matching `answer_template.json` exactly.
## Required Workflow
1. Read the user prompt, `analysis_request.json`, and `answer_template.json` completely.
2. Use the portal URL supplied by the task, usually `<TASK_ENV_BASE_URL>`. Fetch only authorized portal endpoints. For endpoint and release-resolution guidance, read [references/portal-data.md](references/portal-data.md).
3. Resolve one effective request contract before data access or computation. Apply exact `protocol_id` matching, direct bindings, overrides, and inheritance as described in the request and [references/protocol-profiles.md](references/protocol-profiles.md).
4. Compute every declared module in registered order. Preserve every declared order: entity, state, division, feature, coefficient, fold, grid, checkpoint, source group, subset, and output key order.
5. Evaluate decision gates on unrounded values after all modules are complete. Round only for reported JSON fields using the active request/template precision.
6. Return exactly one JSON object. Do not include markdown, prose, comments, `NaN`, `Infinity`, or extra provenance fields.
## Non-Negotiables