Individual skill

pho-algorithmic-audits

Use for Public Health Observatory portal tasks that require a JSON-only answer from analysis_request.json and answer_template.json, especially PHO_* protocol_id audits, registered multi-module statistical audits, release/cohort reconciliation, bootstraps, grouped validation, PCA/clustering, source perturbation, or controlled decision gates.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_023/fewshot/cc/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.

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 · 4,388 bytes
SKILL.mdcore · 4,388 bytes
SKILL.mdcore · 4,388 bytes
references/protocols.mddoc · 16,880 bytes
scripts/pho_common.pyruns · 17,769 bytes

Read excerpt


# Public Health Observatory Algorithmic Audits

Use this skill when a task asks you to solve a Public Health Observatory audit from a web-only/read-only portal and local `analysis_request.json` plus `answer_template.json`.

## First Moves

1. Read the prompt, `analysis_request.json`, and `answer_template.json` completely.
2. Read [references/protocols.md](references/protocols.md) when the request has a `protocol_id`, asks for a registered algorithmic audit, or uses PHO portal publication/revision language.
3. Identify the task environment base URL from the prompt placeholder, environment notes, or runtime context. Query only the allowed read-only portal endpoints.
4. Build one effective request before fetching or computing anything:
   - Activate a bundled protocol profile only when the `protocol_id` is an exact case-sensitive match.
   - Apply direct request keys and `*_overrides` with exact-path deep merge rules from the protocol reference.
   - Treat arrays as full replacements, not patches or concatenations.
   - Reject unresolved aliases, unknown override targets, and incompatible types rather than guessing.