Research

Use when comparing a draft against specific prior work head to head — checking whether a baseline was trained at the same scale, whether protocols match, how many seeds each ran, or what a competitor actually reports. Triggers on "compare this paper to X", "how does our method differ from Y", "is the baseline comparison fair", "did they train at the same scale", or a shortlist of papers from a gap sweep.

Use when working with a researcher on a long-running research project across many sessions — opening or closing a session, choosing a direction, method or scope, deciding whether to ask or act, planning what to run next, or writing up a result. Also when a published number failed to reproduce, a session ended with no record, a decision got made unilaterally, a write-up did not land, or the work has drifted from the research questions.

Research industry approaches to practices discussed in the conversation and assess their fit for the decisions at hand.

Discuss ideas and design choices before implementation, without editing files.

Holistic review of planning artifacts bundle (Spec.md + ImplementationPlan.md + CodeResearch.md) with configurable single-model, multi-model, or society-of-thought execution. Catches cross-artifact consistency issues before implementation begins.

SOP wrapping vault_search — BM25 full-text search across vault pages.

SOP wrapping vault_lint — run batch validation, report issues, optionally

SOP for source page creation — write immutable source page capturing

SOP wrapping vault_query_graph — traverse knowledge graph from a node

SOP for auditing wikilink coverage — scans all edges and reports which

SOP for wiki page creation/update — create or update a synthesized wiki

SOP wrapping vault_add_edge — create a typed relationship between two

Tactic for vault health upkeep — lint, orphan resolution, merge candidates,

SOP for creating a variable page in the causal model — documents a measurable

SOP for generating a causal model validation report — summarize coverage,

Strategy for validating ontology consistency — check hierarchy, detect

SOP for producing argument synthesis reports — aggregate evidence, resolve

Quick web scanning for landscape understanding. Import of web-browsing/web-search

Deep web full-text retrieval via Apify RAG browser. Import of web-browsing/web-research

Map the complete validity envelope of a claim across all relevant dimensions,

Synthesize breakpoints across dimensions into a coherent validity envelope

Determines whether validation has reached saturation — no new weaknesses

'Tactic: Sequential perspective evaluation with divergence aggregation.

Paper AI summary report via alphaxiv get_paper_content. Import of literature-engine/paper-search