Menu

Individual skill

pho-algorithmic-audit

Complete a Public Health Observatory (PHO) registered algorithmic-audit task — gather read-only portal evidence, resolve declared releases and cohorts, run every declared audit module faithfully, apply the decision rule mechanically, and return exactly one JSON object conforming to answer_template.json with no narrative.

experiments/claude_code_glm_5_2_max/reports/skills/task_group_023/self/self_attempt_03/SKILL.md

Read pinned source

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
Instructions only
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

# PHO Registered Algorithmic Audit

## When to use

Use this skill when a task is a Public Health Observatory "algorithmic audit" / "registered audit" / "publication audit" brief. Recognition signals (all four present):

- A `prompt.txt` framing a PHO publication-board or briefing decision (transportability, reproducibility, calibration, stability, burden stratification, mediation).
- An `analysis_request.json` declaring a protocol: geography scope, years, outcome/exposure, cohort definitions, a set of audit modules with named statistical methods, a decision rule, and reporting precision.
- An `answer_template.json` fixing the exact response contract (required top-level keys, sub-keys, array lengths, cardinality rules, ordering, enum values, types, precision).
- A `environment_access.md` defining the read-only portal base URL and an allow-list of GET endpoints, plus the instruction to return one JSON object conforming to the template with no narrative.

If the three-file audit structure (prompt + analysis_request + answer_template) is absent, this skill does not apply — stop.

## Inputs are always a triple — read them together