Individual skill

pho-registered-audit

Complete a Public Health Observatory (PHO) registered multi-module algorithmic audit. Read the per-task analysis_request.json (the protocol) and answer_template.json (the output contract), pull evidence only from the read-only PHO portal, resolve final releases and cohorts independently, run the declared audit modules deterministically with their seeds/grids/checkpoints, apply the gate decision rule, and return exactly one JSON object with no narrative outside it. Use whenever a task pairs an analysis_request.json + answer_template.json with a PHO Web portal and asks for a registered, reproducible audit returned as one JSON object.

experiments/claude_code_glm_5_2_max/reports/skills/task_group_023/self/self_attempt_02/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: Yes
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
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 · 6,074 bytes
references/audit_modules.mddoc · 11,417 bytes
references/output_contract.mddoc · 6,182 bytes
references/portal_and_evidence.mddoc · 9,989 bytes

Read excerpt


# PHO Registered Algorithmic Audit

## When to use

Use this skill when a task gives you, in an `input/` directory:

- `prompt.txt` — the framing question,
- `payloads/analysis_request.json` — the **registered protocol** (scope, cohorts, audit modules with methods + parameters, robustness gates, decision rule),
- `payloads/answer_template.json` — the **output contract** (required keys, array lengths, ordering rules, enum values, numeric precision),

and asks you to complete a registered, reproducible, multi-module audit using a read-only Public Health Observatory (PHO) Web portal, returning the result as one JSON object.

This skill is **task-agnostic**. Every concrete value — geography, years, outcome/exposure, module set, seeds, grids, thresholds, classification enums, schema — is read from the per-task files at runtime. **Never bake in a value seen in a prior task.** Prior tasks illustrate the *shape* of the work; they do not supply answers.