research

Per-topic coherence auditor for the research workflow. Given a single topic file path, assesses logical progression, transition smoothness, abstraction-level consistency, intro/setup adequacy, and heading-vs-content match. Returns a structured list of findings keyed to line numbers, with recommended AUDIT severities. Does NOT edit any files — the orchestrating `/research-audit-coherence` skill applies the AUDIT comments.

Web-verification worker for the four research-audit skills. Given a list of `<!-- CONFIDENCE: low -->` and `<!-- CONFIDENCE: medium -->` markers plus the surrounding claims, runs WebSearch + WebFetch to verify each one, and returns a structured per-marker decision (verified / failed / partial / contradiction-found) along with reference-update payloads. Does NOT edit any project files — the orchestrating audit skill does the actual edits.

Per-topic quality auditor for the research workflow. Given a single topic file path, assesses depth-vs-scale, sourcing adequacy, citation presence, reference verification, and example concreteness. Returns a structured list of findings keyed to line numbers, with recommended AUDIT severities. Does NOT edit any files — the orchestrating `/research-audit-quality` skill applies the AUDIT comments.

Web-research worker for the research workflow. Given a single RESEARCH directive (query, scale, sources, sources_detail, related), runs WebSearch + WebFetch loops to find and verify sources, then returns a structured report of vetted citations, verbatim quote snippets keyed to citation slugs, per-claim confidence assessments, contradictions between sources, and URL verification status. Does NOT write topic content — synthesis is the orchestrating skill's job. Read-only with respect to the project; touches the network only.

Per-topic glossary candidate extractor for the research workflow. Given one topic file, scans for explicitly defined terms, domain jargon, and key concepts, then returns a structured candidate list with definitions derived from how each term is used in the file. Does NOT edit any files — the orchestrating `/research-glossary-sync` skill merges candidates across topics and writes the glossary.

Add new chapter stubs to an existing topic directory in a research project. Use when a topic already exists as a directory and you want to introduce additional chapters. Argument: topic directory name (relative to research/content/).

Add a new topic (directory + chapter stubs) to an existing research project. Use when the project already exists and you want to introduce a new top-level topic area. Arguments: topic name (required), optional summary to seed scoping.

Audit research topics for narrative flow and coherence. Produces AUDIT directive comments for the refine phase. Arguments: optional topic path.

Audit research topics for cross-topic contradictions and inconsistent terminology. Produces AUDIT directive comments for the refine phase. Arguments: optional topic path.

Audit research topics for gaps relative to the research plan. Produces AUDIT directive comments for the refine phase. Arguments: optional topic path.