template-deep-research

# Deep research Template-native research workflow. This skill routes to existing repository systems instead of running an autonomous external agent suite. ## Natural invoke - "Research this topic and build the source corpus" - "Do a literature review with citation keys" - "Fact-check these manuscript claims" - "Guide me from vague research interest to answerable question" - "Plan a systematic review with inclusion and exclusion criteria" ## Inputs to confirm - **Research goal** - question, audience, and expected deliverable. - **Mode** - full, quick, lit-review, fact-check, guided, or systematic-review. - **Corpus source** - arXiv, Crossref, local JSON corpus, provided papers, or project artifacts. - **Project target** - if results feed a manuscript, use `docs/_generated/active_projects.md`. ## Workflow 1. **Question framing** - turn vague topics into scoped research questions, explicit in/out boundaries, and search terms. Guided mode asks before converging. 2. **Source discovery** - use `infrastructure.search.literature` and project-local corpora; record query, backend, date, DOI/arXiv IDs, and failures. 3. **Source verification** - resolve every candidate reference against Crossref / OpenAlex / arXiv with the deterministic reference-existence gate before it enters the corpus; reject `fabricated`/`mismatch` records, surface `unverifiable`/`unchecked` honestly, and never invent unavailable bibliographic fields. This is the tier-0 anti-leakage step: flag the gap, do not...