Individual skill

pho-algorithmic-audit

Solve Public Health Observatory (PHO) algorithmic transport/audit tasks. Read the task prompt plus analysis_request.json and answer_template.json from the task's input/payloads/, pull evidence only from the read-only PHO web portal, resolve one effective request, run the registered multi-module audit with exact reproducible numerics, and return exactly one JSON object conforming to answer_template.json. Use when a task names the PHO portal (<TASK_ENV_BASE_URL>), carries a PHO_* protocol_id and a declared set of audit modules in analysis_request.json, and asks for a single JSON answer conforming to an answer_template.json contract.

experiments/claude_code_glm_5_2_max/reports/skills/task_group_023/fewshot/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.

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 Audit

This skill solves the PHO "algorithmic transport / robustness audit" family of tasks. Every
task in the family has the same shape: a business question, a read-only evidence portal, an
`analysis_request.json` that registers a `protocol_id` plus ordered audit modules, an
`answer_template.json` that fixes the response contract, and a demand for **exactly one JSON
object** with no surrounding narrative.

The method is reusable; only the task-local bindings (entities, measures, years, geography,
sources, seeds, grids, cutoffs, output vocabulary) change per request. **Never carry solved
analytical values from one task into another** — recompute everything from the effective
request and the portal evidence.

## When to use this skill
Back to top