Individual skill

pho-registered-algorithmic-audit

Operating procedure for Public Health Observatory (PHO) "registered algorithmic audit" tasks: a prompt.txt plus payloads/analysis_request.json (the registered protocol) and payloads/answer_template.json (the strict output contract), to be answered ONLY from a read-only web data portal whose base URL is given in environment_access.md. Use whenever the input pairs an analysis_request.json spec with an answer_template.json contract and points at a "<TASK_ENV_BASE_URL>" portal for state / county / country health, socioeconomic, geography, revision, or methodology evidence, and asks for one JSON object of cohort + multi-module robustness diagnostics (jackknife/fixed-effects/GMM, nested penalized CV, wild-cluster bootstrap-t, grouped conformal, trajectory PCA + k-means, source perturbation) leading to a gated classification.

experiments/claude_code_opus_4_8_xhigh/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: 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
legal Derived category
data Derived category
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 · 9,452 bytes
SKILL.mdcore · 9,452 bytes
SKILL.mdcore · 9,452 bytes
SKILL.mdcore · 9,452 bytes
references/audit_modules.mddoc · 7,884 bytes
references/output_contract.mddoc · 3,631 bytes
references/portal_reference.mddoc · 7,706 bytes
references/release_revision_and_cohorts.mddoc · 5,383 bytes
scripts/portal_fetch.pyruns · 5,470 bytes

Read excerpt


# PHO Registered Algorithmic Audit

## 1. Recognise the task

Every task in this family gives you three input artifacts and one deliverable:

- `input/prompt.txt` — the narrative framing and the decision the board wants.
- `input/payloads/analysis_request.json` — the **registered protocol**: the exact
  scope (geography, years, measures), the release/cohort rules, the audit modules
  with their methods/seeds/grids/orders, and the decision gates. This is the source
  of truth for *what to compute*.
- `input/payloads/answer_template.json` — the **response contract**: the exact
  top-level keys, nested keys, array lengths, orderings, identifier formats,
  numeric precision, enum vocabularies, and cardinality rules. This is the source