From research-workspace
Compares a known set of papers (from Zotero, Obsidian, or manual list) into a compact comparison matrix for review-writing decisions, avoiding per-paper summary dumps.
How this skill is triggered — by the user, by Claude, or both
Slash command
/research-workspace:literature-triage-matrixThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Produce a single comparison table over a set of papers, optimized for
Produce a single comparison table over a set of papers, optimized for review-writing decisions. The matrix lets the user (or a downstream writing skill) see at a glance which papers cluster together by method, which carry the load on a particular claim, and which can be cited in passing vs deeply engaged.
This skill avoids the common AI failure mode of "give me a summary of each paper" — which produces N independent bullet lists that the user then has to manually compare.
Trigger phrases:
Not for:
paper-memory-builder.In priority order (cheapest to most expensive):
Manual paper list — a Markdown bullet list of titles + DOIs (or arXiv IDs) the user pastes directly into the chat. Lowest-friction entry; works without any other research-hub setup. Treat each line as one row in the matrix; fill cells from your own knowledge
? and ask
the user.Example minimal input:
- "Memory enables ToM-like behaviour in LLM poker agents", arXiv:2604.04157
- "Multi-agent LLM social learning", arXiv:2604.02677
- "Triadic Loop alignment framework", arXiv:2604.18850
.research/literature_matrix.md — if it already exists, parse it
first. Append-only by convention; only re-emit a row if the
underlying paper changed materially.
Obsidian cluster notes under raw/<cluster>/*.md — these have
structured frontmatter (title, authors, year, doi) plus
research-hub-generated Summary / Key Findings / Methodology / Relevance sections. Read these first; they're cheaper than PDFs.
Zotero collection metadata via local API (fast) — add child note contents only if Obsidian doesn't have the paper.
NotebookLM downloaded briefs under .research_hub/artifacts/ —
if the user has already generated a brief on the cluster, mine it
for cross-paper comparisons.
Raw PDFs — only as last resort, and only the abstract + first 2 pages + conclusion. PDFs are token-expensive.
Write to <project-root>/.research/literature_matrix.md. Append by
default; rewrite the whole table only if the user explicitly says
"regenerate from scratch".
Markdown table columns (customize per request, but default is):
| Citation | Question | Method | Data / study area | Main claim | Evidence | Limitation | Relevance | Use as |
|---|---|---|---|---|---|---|---|---|
| Smith 2024 | How does adaptation affect flood risk? | mesa-based ABM, 10k agents | Houston synthetic | Adaptation cuts loss 18% | simulation | single basin, no validation | High — direct precedent | Lit review §2 |
| Jones 2023 | Hydraulic coupling in flood ABMs | Coupled ABM-2D | Galveston | Coupling reduces RMSE 22% | empirical | calibration window narrow | Medium — methods | Methods §3 |
Column meanings:
Smith 2024); leaving full
citation to Zotero.High / Medium / Low + one-phrase justification..research/literature_matrix.md first; only emit rows
for papers not already covered or whose underlying note changed.Summary section over re-reading
the PDF.Smith 2024 (10.1234/abcd) instead of pasting
paragraphs.After writing the matrix, print:
[literature-triage-matrix]
Wrote/appended: .research/literature_matrix.md
Papers in matrix: 12 (4 new this run)
Skipped (already in matrix, unchanged): 8
Read full PDF for: 1 (Smith 2024 — no Obsidian note found)
Suggested next: review High-relevance rows in .research/literature_matrix.md
.paper/ — that's paper-memory-builder's territory.? in unknown columns and a note: (Obsidian note incomplete — run research-hub auto with --max-papers 1 to enrich, or fill manually).npx claudepluginhub wenyuchiou/ai-research-skills --plugin research-workspaceGenerates structured literature reviews on research topics via Corbis searches, organizes into themes with synthesized prose, outputs as Markdown, LaTeX section, or standalone document with BibTeX citations.
Use this skill for "write a literature review", "synthesize papers", "review the literature", "summarize research findings", "identify research trends", "gap analysis", "thematic review", "systematic review", "scoping review", "narrative review", "compare studies", "research synthesis", or when the user wants to synthesize multiple papers into a cohesive literature review.
Synthesizes academic paper corpora in Zotero into theoretical maps, thematic clusters, and debate identifications. For deep literature analysis before writing.