willoscar

Argument self-loop: maintain an argument ledger + premise consistency report for drafted sections. **Trigger**: argument self-loop, argument chain, premise c...

Download a small corpus of open-access arXiv survey/review PDFs about LLM agents and extract text for style learning. **Trigger**: agent survey corpus, ref c...

Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment. **Trigger**: cita...

Apply a `citation-diversifier` budget report by injecting *in-scope* citations into an existing draft (NO NEW FACTS), so the run passes the global unique-cit...

Raise citation diversity/density (NO NEW FACTS): generate an in-scope “citation budget” plan per H3 so drafts stop failing the global unique-citation gate an...

Build a retrieval-informed chapter skeleton (`outline/chapter_skeleton.yml`) from taxonomy/core scope before stable H3 decomposition. **Trigger**: chapter sk...

Add bias/risk-of-bias assessment fields to an extraction table and populate them consistently. **Trigger**: bias, risk-of-bias, RoB, evidence quality, 偏倚评估,...

Write H2 chapter lead blocks (`sections/S<sec_id>_lead.md`) that preview the chapter's comparison lens and connect its H3 subsections, without adding new fac...

Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys. **Tri...

Extract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of ge...