template-comprehensive-assessment

# Comprehensive assessment ## Natural invoke - "Audit the whole repo for template_active_inference, template_autoresearch_project, template_code_project, template_prose_project, and template_template" (example names only — the authoritative public roster is [`docs/_generated/active_projects.md`](../../_generated/active_projects.md)) - "Full health check — tests, docs, manuscript, pipeline" - "What's broken across all active projects?" ## Inputs to confirm - **Project(s)** — names from [`docs/_generated/active_projects.md`](../../_generated/active_projects.md) or "all active". - **Scope** — single project vs multi-project (one pytest process per project test dir). ## Workflow Work through: 1. **Tests** — appropriate pytest invocations; one project test dir per project. Coverage: infra ≥60%, project ≥90% unless CI exception. No mocks ([`docs/rules/testing_standards.md`](../../rules/testing_standards.md)). 2. **Architecture** — thin orchestrators in `scripts/`; algorithms in `projects/<n>/src/` or `infrastructure/`. No cross-project imports. 3. **Documentation** — meaningful dirs have accurate AGENTS.md + README.md; links resolve; link `_generated/active_projects.md`, do not duplicate roster. 4. **Manuscript** — Pandoc-crossref + `.bib` → [`docs/guides/manuscript-semantics.md`](../../guides/manuscript-semantics.md). Registry `labels.yaml` + `[[FIG:]]` → [manuscript-cross-references](../manuscript-cross-references/SKILL.md). Validate markdown; PDF/logs if outputs exist....