Pp Scientific Consensus

<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/other/scientific-consensus/SKILL.md,
     regenerated post-merge by tools/generate-skills/. Hand-edits here are
     silently overwritten on the next regen. Edit the library/ source instead.
     See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->

Scientific Consensus — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the scientific-consensus-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:

   npx -y @mvanhorn/printing-press-library install scientific-consensus --cli-only

2. Verify: scientific-consensus-pp-cli --version
3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

go install github.com/mvanhorn/printing-press-library/library/other/scientific-consensus/cmd/scientific-consensus-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

Scientific Consensus turns large collections of papers into actionable evidence. It scores consensus across sources (consensus), classifies studies by design and renders evidence pyramids (evidence), detects gaps and controversies, and persists everything to a local SQLite store you can query offline with --json. Fully keyless; optional AI keys upgrade summarization.

When to Use This CLI

Use Scientific Consensus when an agent or researcher needs to know what the evidence says about a claim, not just find papers. It is the right tool for evidence synthesis, consensus scoring, study-design classification, gap/controversy detection, and topic monitoring across biomedical and general scientific literature. It excels when offline persistence and agent-native JSON matter.

Anti-triggers

Do not use this CLI for:

• Do not use for retrieving the full text PDF of a specific paper (use the publisher or Europe PMC full-text directly).
• Do not use for non-scholarly web search or news.
• Do not use as a citation manager replacement for writing (use Zotero); it exports BibTeX but does not manage libraries.
• Do not treat heuristic consensus/quality scores as peer-reviewed conclusions.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Evidence intelligence

• consensus — Answer 'what does the evidence say about X' with a Consensus Score, Confidence Score, and Evidence Strength across all sources.

  Reach for this when an agent needs an evidence-backed yes/no/mixed verdict instead of a raw paper list.

  scientific-consensus consensus "vitamin D reduces respiratory infections" --agent

• evidence — Classify retrieved studies by design (meta-analysis to case report) and render the evidence pyramid for a topic.

  Reach for this to judge whether a claim rests on RCTs/meta-analyses or just case series.

  scientific-consensus evidence "intermittent fasting weight loss" --agent

• compare — Run two consensus analyses side-by-side to compare competing claims or interventions.

  Reach for this when an agent must weigh two interventions or contradictory claims.

  scientific-consensus compare "statins reduce mortality" "statins increase diabetes risk" --agent

• reproducibility — Estimate reproducibility by detecting replication studies, sample sizes, and pre-registration cues.

  Reach for this to gauge how well-replicated a finding is.

  scientific-consensus reproducibility "power posing" --agent

• quality — Estimate overall study quality from design, venue prestige, sample-size cues, and citation mass.

  Reach for this for a quick quality signal before deep reading.

  scientific-consensus quality "omega-3 depression" --agent

Discovery

• gaps — Identify understudied populations, missing long-term/replication/RCT studies, and future directions for a topic.

  Reach for this to find what research is missing, not just what exists.

  scientific-consensus gaps "pediatric long covid" --agent

• controversies — Surface conflicting studies, contradictory conclusions, and rapidly changing evidence for a topic.

  Reach for this when the question is 'is this settled or disputed?'

  scientific-consensus controversies "saturated fat heart disease" --agent

• funding — Analyze funding patterns and funder concentration for a research topic.

  Reach for this to see who funds research on a topic (potential conflicts).

  scientific-consensus funding "e-cigarette safety" --agent

Utilities

• convert — Translate a DOI to a PMID or vice versa using the OpenAlex work index. Pass exactly one of --doi or --pmid; the other identifier is returned along with the title.

  Reach for this whenever an agent has one identifier type but needs the other (e.g. a citation tool wants a PMID, a DOI resolver gives you a DOI).

  scientific-consensus convert --doi 10.1136/bmj.i6583 --agent
  scientific-consensus convert --pmid 32939066 --agent

• batch — Run consensus analysis for multiple claims from one or more files (plain text, one claim per line, blank lines and # comments skipped). Accepts globs; duplicates are deduplicated. Returns a summary table or a flat JSON array, one item per claim.

  Reach for this when an agent must score many claims at once without shell-looping over consensus.

  scientific-consensus batch claims.txt --agent
  scientific-consensus batch claims*.txt --limit 20 --json

• report — Export an analyzed works report for a topic as an Excel (.xlsx) workbook: a Works sheet (one row per study with title, first author, year, DOI, PMID, venue, design, stance, stance confidence, citations, open access) and a Summary sheet (query metadata plus stance/design aggregates). Uses the same design/stance engine as consensus and evidence. Unlike export (raw JSONL/JSON API dumps), report writes analyzed, spreadsheet-ready results.

  Reach for this when a researcher wants to hand off results to Excel, Google Sheets, or any spreadsheet-based screening workflow.

  scientific-consensus report "vitamin D respiratory infections" --output report.xlsx
  scientific-consensus report "microplastics" -o mp.xlsx --claim "microplastics harm human health" --limit 100 --agent

• citations — Build a citation network around a seed work (by --doi, --pmid, or --id): the works citing it (cited-by), the works it references (references), or both. Bounded by --depth (max 2 hops) and --max-nodes (hard cap). --json returns flat nodes + edges arrays ready for a web graph renderer; the human default is a compact summary.

  Reach for this to trace influence, find high-impact neighbors, or feed a network-visualization tool.

  scientific-consensus citations --doi 10.1136/bmj.i6583 --agent
  scientific-consensus citations --id W2741809807 --depth 2 --max-nodes 80 --direction cited-by --agent

Trends

• emerging — Detect the fastest-growing research areas and exploding publication trends.

  Reach for this to spot hot research areas before they peak.

  scientific-consensus emerging --field neuroscience --agent

• drift — Compare a field's topic distribution between two year windows to spot emerging and fading subtopics.

  Reach for this to see how a field's focus shifted over time.

  scientific-consensus drift "machine learning genomics" --from 2015 --to 2025 --agent

• watch — Monitor a topic and report major new publications since the last run.

  Reach for this to keep an agent or researcher current on a fast-moving topic.

  scientific-consensus watch "GLP-1 cardiovascular outcomes" --agent

Command Reference

authors — Search and retrieve authors

• scientific-consensus-pp-cli authors get — Get a single author by OpenAlex ID
• scientific-consensus-pp-cli authors search — Search authors

funders — Research funders

• scientific-consensus-pp-cli funders — Search funders

institutions — Search and retrieve institutions

• scientific-consensus-pp-cli institutions get — Get a single institution by OpenAlex ID
• scientific-consensus-pp-cli institutions search — Search institutions

sources — Journal (source) metadata

• scientific-consensus-pp-cli sources get — Get a journal (source) by ISSN or OpenAlex ID
• scientific-consensus-pp-cli sources search — Search sources (journals)

topics — Research topics

• scientific-consensus-pp-cli topics — Search topics

works — Search and retrieve scholarly works

• scientific-consensus-pp-cli works get — Get a single work by OpenAlex ID, DOI, or PMID
• scientific-consensus-pp-cli works search — Search scholarly works

convert — DOI ↔ PMID identifier translation

• scientific-consensus-pp-cli convert --doi <doi> — Look up the PMID (and title) for a DOI
• scientific-consensus-pp-cli convert --pmid <pmid> — Look up the DOI (and title) for a PMID

batch — Batch consensus over claim files

• scientific-consensus-pp-cli batch <file|glob> [...] — Run consensus analysis for every claim in one or more files (blank lines and # comments skipped; globs and duplicate files are handled automatically)

report — Excel report export

• scientific-consensus-pp-cli report <query> --output <file.xlsx> — Export analyzed works (design + stance classified) as a two-sheet Excel workbook; --claim overrides the stance target, --filter narrows with an OpenAlex filter, --limit caps the works analyzed

citations — Citation-network graph

• scientific-consensus-pp-cli citations --doi <doi> — Build a citation graph from a DOI seed
• scientific-consensus-pp-cli citations --pmid <pmid> — Build a citation graph from a PMID seed
• scientific-consensus-pp-cli citations --id <W...> — Build a citation graph from an OpenAlex ID seed