Individual skill
pho-algorithmic-transport-audit
Solve Public Health Observatory registered algorithmic-transport audit requests — a prompt plus analysis_request.json and answer_template.json whose evidence comes only from the Observatory Web portal. Use whenever a PHO audit task asks you to resolve portal publications/cohorts, run a declared set of reproducible statistical audit modules (delete-cluster/jackknife fixed effects or GMM/mediation, nested ridge or elastic-net CV, restricted-null wild cluster bootstrap, grouped split conformal, trajectory PCA + deterministic k-means + stability, source/year/group perturbation, partial-R2 sensitivity), and return exactly one JSON object conforming to the template. Carries method only; binds every task-local value from the effective request and never carries solved values across invocations.
experiments/claude_code_glm_5_2_max/reports/skills/task_group_023/fewshot/fewshot_attempt_02/SKILL.md
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 11, 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 · 6,583 bytesSKILL.mdcore · 6,583 bytesreferences/effective_request.mddoc · 2,068 bytesreferences/module_families.mddoc · 4,068 bytesreferences/numerical_conventions.mddoc · 13,578 bytesreferences/portal_evidence.mddoc · 4,816 bytesreferences/reporting_contract.mddoc · 2,015 bytes
Read excerpt
# Public Health Observatory Algorithmic-Transport Audit
## When to use
Activate when a request consists of:
- a **prompt** directing you to the Observatory Web portal at `<TASK_ENV_BASE_URL>` (resolved from `environment_access.md`),
- an **`analysis_request.json`** declaring the audit: a `protocol_id` or `request_id`, scope (geography, years, reference year), cohorts, an ordered set of audit modules, reproducibility bindings, a `reporting` block, and a `decision_rule`,
- an **`answer_template.json`** fixing the output contract,
and asks for **exactly one JSON object** computed only from portal evidence, with no narrative.
This covers state-level, county-level, and country-level PHO audits (longevity/transport, mediation/transport, robustness/transport, panel/transport, burden-revision). Do not activate for unrelated tasks, and do not activate on family membership or subject-matter similarity alone — a declared protocol id, when present, is the exact activation key.
