Individual skill
pho-algorithmic-audits
Solve Public Health Observatory web-portal audit tasks that provide analysis_request.json and answer_template.json, including state, county, and country public-health release resolution, cohort construction, regression, GMM, ridge or elastic-net validation, wild-cluster bootstrap, grouped conformal calibration, PCA clustering, perturbation audits, and controlled JSON decisions.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_023/fewshot/deepagents/fewshot_attempt_02/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
- 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 · 5,347 bytesSKILL.mdcore · 5,347 bytesSKILL.mdcore · 5,347 bytesSKILL.mdcore · 5,347 bytesreferences/protocol-methods.mddoc · 20,837 bytesscripts/pho_tools.pyruns · 10,852 bytes
Read excerpt
# PHO Algorithmic Audits
Use this skill for Public Health Observatory tasks that require computing a structured JSON answer from the read-only portal. The portal evidence, the active `analysis_request.json`, and the active `answer_template.json` are the authority. Do not reuse solved values from any prior task.
## Required Workflow
1. Read the prompt, `analysis_request.json`, and `answer_template.json` completely.
2. Resolve one effective request before any data access or computation:
- Use an exact protocol profile only when `protocol_id` exactly matches the case-sensitive identifier in [protocol-methods.md](references/protocol-methods.md).
- Apply direct keys by exact path. A root `<section>_overrides` targets `<section>`, `module_overrides.<module>` targets that exact module, and `reporting_overrides` targets reporting.
- Deep-merge objects, replace arrays whole, and replace explicit scalars only at their exact paths. Reject unknown targets, inferred aliases, positional patches, and type coercion.
3. Load only authorized portal data through `<TASK_ENV_BASE_URL>`:
- Inspect `/catalog` and `/methodology` if schema or current policy is unclear.
- Prefer CSV exports such as `/download?dataset=state_health&format=csv`; add query filters only when they exactly match portal filter names.