litreview

v2.9.0

Academic literature orientation skill. Turns a research question into a strategically planned mini literature review, delivered as a researcher-friendly Word document (.docx). Searches via free keyless APIs by default (PubMed E-utilities + OpenAlex) with the Consensus MCP as an optional enhancement lane when connected. Grill-me intake (research question + framework hint + tentative depth) before recon search; second forcing checkpoint after Phase 2 confirms framework + sub-areas + depth. Configurable depth (5/10/20 queries) controls coverage vs. speed. Output is a 'launching pad' — orientation guide, not a finished review. Implements research-pack Agent Integrity Rules: 1 q/sec sequential execution, lane check (no plan-tier detection), three-count tracking (sent/received/cited). Source spec: megaprompts/09-litreview-megaprompt.md (PR #657). Sibling of pulse (research-pack shape).

Claude Code

by Alireza RezvaniMIT24.2kupdated 10 hours ago

Source

$ git clone https://github.com/alirezarezvani/claude-skills

Clone the source, then follow the repository's marketplace instructions for your runtime. The plugin root is research/litreview/ inside the repository.

Layout

research/litreview/

└── .claude-plugin/plugin.json

Manifests1

research/litreview/.claude-plugin/plugin.json

{
  "name": "litreview",
  "description": "Academic literature orientation skill. Turns a research question into a strategically planned mini literature review, delivered as a researcher-friendly Word document (.docx). Searches via free keyless APIs by default (PubMed E-utilities + OpenAlex) with the Consensus MCP as an optional enhancement lane when connected. Grill-me intake (research question + framework hint + tentative depth) before recon search; second forcing checkpoint after Phase 2 confirms framework + sub-areas + depth. Configurable depth (5/10/20 queries) controls coverage vs. speed. Output is a 'launching pad' — orientation guide, not a finished review. Implements research-pack Agent Integrity Rules: 1 q/sec sequential execution, lane check (no plan-tier detection), three-count tracking (sent/received/cited). Source spec: megaprompts/09-litreview-megaprompt.md (PR #657). Sibling of pulse (research-pack shape).",
  "version": "2.9.0",
  "author": {
    "name": "Alireza Rezvani",
    "url": "https://alirezarezvani.com"
  },
  "homepage": "https://github.com/alirezarezvani/claude-skills/tree/main/research/litreview",
  "repository": "https://github.com/alirezarezvani/claude-skills",
  "license": "MIT",
  "skills": [
    "./skills/litreview"
  ],
  "source": {
    "spec": "megaprompts/09-litreview-megaprompt.md",
    "build_pattern": "Path B (direct conversion). Research-pack shape. Implements Agent Integrity Rules + cross-search intelligence + interactive checkpoint per megaprompt spec.",
    "sibling_of": "research/pulse (research-pack shape; pulse currently lives in engineering/ and will move to research/ in a future cleanup PR)"
  }
}