agentsclimarketplace

Researchskills

Skill dahliasan/researchskills/skills/researchskills

Pack router for researchskills. Use when the user is unsure which research skill to run, asks for research help generally, or says "/researchskills". Routes to manuscript-writing, manuscript-markdown, manuscript-collab, figure-design, ggplot-maps, manuscript-submission, literature-review, research-red-team, aic-model-selection, discover-papers, protocol, find-pdf, pp-scite, research-project-ops, r-editor-setup, zotero, zotero-mcp, or zotseek. Does not reimplement those skills.From its SKILL.md

Install
npx -y skills add dahliasan/researchskills --skill researchskills

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.4 KB, as published. Nobody here has run it

/researchskills — pack router

Pick the narrowest sibling skill. Then load and follow that skill.

Route

IntentSkill
Draft, revise, storyboard, or audit manuscript prosemanuscript-writing
Roundtrip DOCX ↔ Markdown (default MD↔Word path)manuscript-markdown
CriticMarkup collab, address review comments, or export Word without agent commentsmanuscript-collab
Plan, create, revise, or audit a scientific figurefigure-design
Build R/ggplot2 maps (sf, polar CRS, basemaps, rasters)ggplot-maps
Critically stress-test a whole research project, simulate reviewer 2, or run a replication pre-mortemresearch-red-team
AIC/AICc model selection, Δ/weights, nested near-ties, primary inferenceaic-model-selection
Adapt a manuscript to a journal or prepare a submission packagemanuscript-submission
Literature workflow, synthesis, citation checkliterature-review
Find papers / OpenAlex / brain-dump searchdiscover-papers
Build or refine PROTOCOL.md from a research questionprotocol
Get a PDF for a DOI or paperfind-pdf
Scite Smart Citations, search, tallies, assistant, reference-checkpp-scite
Scaffold / audit / hand off a research repo (PROJECT.md, METHODS.md, STATUS.md)research-project-ops
Install / doctor R env in Cursor or VS Code (packages, Air, radian, httpgd)r-editor-setup
Zotero library day-to-day (prefer MCP if present, else local API)zotero
Install/configure 54yyyu Zotero MCPzotero-mcp
Semantic search over Zotero PDFs (ZotSeek plugin)zotseek

Rules

  1. Prefer literature-review for review-shaped work; prefer discover-papers for one-off search.
  2. Use research-red-team for an opposing project-wide scientific lens; use manuscript-writing audit mode for manuscript-only coherence and prose checks.
  3. Use aic-model-selection for AIC/AICc tables, Δ/weights, nested near-ties, and primary inference choice; do not expand it into a general stats skill.
  4. Do not invent a second prose skill; always manuscript-writing.
  5. Default MD↔DOCX conversion to manuscript-markdown (never pandoc first; never as a prose twin).
  6. Use figure-design for visual design QA; use ggplot-maps for R map recipes. Keep analytical decisions with the analysis owner.
  7. Use manuscript-submission for venue rules, reporting compliance, declarations, and package preflight. For Word file emit during packaging, invoke manuscript-markdown.
  8. Zotero: zotero for session work; zotero-mcp for 54yyyu/zotero-mcp install/config; zotseek for ZotSeek semantic. If backends are down, say so and continue without Zotero where possible.
  9. Use r-editor-setup for R + Air editor tooling; do not bury that in ggplot-maps or analysis scripts.

Exit

Name the chosen skill and invoke it.

Keep looking

Skills are one crate of 627,801. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.