Orchestrate continual learning by delegating transcript mining to agents-memory-updater and writing durable memory to local JSON (never root AGENTS.md Learned sections). USE WHEN continual learning, mine prior chats, maintain agent memory, or the stop hook triggers this skill.

**Naming:** [Open Gauss vs Huawei DBMS](../../../docs/reference/opengauss-naming.md).

Skill for deterministic AutoResearch readiness planning. Use when adding, validating, or documenting opt-in autoresearch.yaml controls, stage-gate readiness, evidence-grounded claims, artifact readiness reports, or AutoResearchClaw-inspired workflow checks in template projects.

Skill for the doctor infrastructure module providing repository-level diagnostics and safe, reversible automated repair. Use when the local checkout is acting up, before opening a bug, when onboarding a fresh clone, or as a periodic health probe. Every mutation is backed up under .doctor/backups/ and journalled in .doctor/actions.jsonl so any change can be undone byte-for-byte.

Skill for the documentation infrastructure module providing figure management, image handling, markdown integration, and API glossary generation. Use when managing research figures, inserting images into manuscripts, auto-numbering figures, or generating API documentation.

Skill for the fonds module — discovery, validation, scope, and private-sidecar symlink sync for the top-level fonds/ directory (archival collection units such as bibliographies, contact registries, and dataset catalogs). Use when discovering fonds (discover_fonds), resolving a fond path (resolve_fond_root), validating fond structure (validate_fond_structure), building FondInfo dataclasses (build_fond_info), checking PUBLIC_FOND_NAMES for CI-safe scope (public_scope.py), syncing private lifecycle fonds into the template checkout (sync_private_fond_links / linking.py), checking whether a path is a managed fond symlink (is_managed_symlink), or adding new public fonds exemplars. Distinct from projects/ (executable research code); fonds are passive data stores requiring fonds.yaml + data/ (not src/ + tests/).

Prose analysis utilities for research manuscripts and prose-focused projects. Provides readability metrics (Flesch, Flesch-Kincaid, Gunning Fog), heading-outline structural analysis, editorial quality flags (passive voice, hedge words, citation density, long sentences), aggregate ManuscriptReport across a manuscript directory, and a CLI (metrics/outline/quality/report). Use when analyzing manuscripts for readability, building editorial dashboards, validating heading structure, extracting citation keys from prose, or wiring prose-quality gates into the pipeline.

Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, and publication readiness validation. Use when publishing research, generating citations, minting DOIs, or preparing submissions.

Skill for the reporting infrastructure module providing pipeline reporting, error aggregation, executive summaries, dashboard generation, test reporting, and multi-project reports. Use when generating build reports, aggregating errors, creating visual dashboards, or producing executive summaries across projects.

Skill for the scientific infrastructure module providing numerical stability checks, performance benchmarking, scientific documentation generation, implementation validation, and module/workflow templates. Use when benchmarking functions, checking numerical stability, validating scientific implementations, or creating scientific module scaffolds.

Prompt blocks for `infrastructure.llm` or project `synthesis.py` after literature search.

Complements [manuscript-claim-verification](../manuscript-claim-verification/SKILL.md) (claim truth) by focusing on **stability of artifacts**.

Deterministic harness for Meta → Target → Feedback generation loops with public/private task splits. Implements contracts inspired by [hexo-ai/sia](https://github.com/hexo-ai/sia); does not vendor upstream code.

When intent is clear, open the matching child `SKILL.md` directly. When ambiguous, use the routing table, then load exactly one child skill.