Individual skill
pho-registered-audit
Complete a Public Health Observatory (PHO) registered algorithmic audit. Resolve final releases/revisions from the read-only PHO portal, build the declared cohorts, run the six registered audit modules deterministically (delete-one-cluster jackknife / two-step GMM, nested leave-group-out ridge or elastic-net, restricted-null wild cluster bootstrap-t, grouped split conformal, trajectory PCA + deterministic k-means, exhaustive source/year/group perturbation), apply the robustness gates, and emit exactly one JSON object conforming to answer_template.json. Use when a task names the PHO portal at <TASK_ENV_BASE_URL>, ships analysis_request.json + answer_template.json, and demands a reproducibility/transportability audit with a controlled decision.
experiments/claude_code_glm_5_2_max/reports/skills/task_group_023/self/self_attempt_01/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 · 11,411 bytesSKILL.mdcore · 11,411 bytesSKILL.mdcore · 11,411 bytesreferences/contract.mddoc · 7,006 bytesreferences/modules.mddoc · 12,968 bytesreferences/portal.mddoc · 9,406 bytes
Read excerpt
# Public Health Observatory — Registered Algorithmic Audit
This skill completes any **PHO registered algorithmic audit** task. Every such task has the
same shape: a read-only portal is the sole evidence source; an `analysis_request.json`
declares the protocol (geography, years, outcome/exposure, cohorts, audit modules, gates,
decision rule); an `answer_template.json` fixes the response contract (keys, orders,
lengths, types, precision, enums). The domain varies (state longevity, county mediation,
country burden, state diabetes, county diabetes dynamics) but the **operating procedure is
constant**. Follow it exactly.
## What you receive
- `prompt.txt` — restates the gates and the submission constraint (one JSON object, no narrative).
- `payloads/analysis_request.json` — the protocol (the "what to compute").
- `payloads/answer_template.json` — the contract (the "how to format").