lit-review-orchestrator
Master controller for the lit-review pipeline, driven by a document. Give it a .tex or .docx file describing an article — a full manuscript, an abstract, or a proposal — and it extracts a search plan, runs Undermind (an automated Playwright driver in Classic mode) and Google Scholar (SearchAPI.io), then merges, deduplicates, and screens the results. Only use this skill when explicitly requested — e.g., the user says "run lit-review-orchestrator", "lit-review-orchestrator", or "/lit-review-orchestrator". Do NOT auto-trigger on general literature review requests.
npx skills add kennethkhoocy/applied-micro-skills --skill lit-review-orchestrator --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Master controller for the lit-review pipeline. Given a .tex or .docx document describing an article (full manuscript, abstract, or proposal), it extracts a search plan, runs Undermind (an automated Playwright driver in Classic mode) and Google Scholar (SearchAPI.io), then merges, deduplicates, and screens the results. Output is a deduplicated, relevance-screened master list (JSON + RIS), plus the extracted search plan and all intermediate stage files. Only use this skill when explicitly requested—e.g., the user says "run lit-review-orchestrator", "lit-review-orchestrator", or "/lit-review-orchestrator". Do NOT auto-trigger on general literature review requests.
How it works
- Input: a .tex or .docx document describing the article.
- Pipeline: Stage 0 Extract derives the research question and queries; Stage 1 Undermind performs automated search; Stage 2/2b Deep Research (optional) and Google Scholar via Stage 4a; Stage 4b Supplementary sources (optional); Stage 4c Citation chain (optional); Stage 5 Dedup merges and enriches metadata; Stage 5b Verify cross-checks against OpenAlex / Crossref / Semantic Scholar; Stage 6 Screen re-ranks by relevance to the research question.
- It supports an agent-driven flow (no Anthropic API for reasoning steps) and an autonomous fallback that runs the full end-to-end process via orchestrator.py.
- The GUI and agent-driven guidance describe how to configure channels (undermind, deepresearch, scholar, scholarlabs, freesearch, websearch) and options (ssrn, nber, heinonline, forthcoming) and how to map results to stage outputs.
When to use it
Use only when explicitly requested, such as saying "run lit-review-orchestrator", "lit-review-orchestrator", or "/lit-review-orchestrator".
What it can touch
- Tools: claude-code, codex
- Executables: orchestrator.py, various stage scripts (e.g., extract_search_plan.py, undermind_search.py, deepresearch_search.py, scholarlabs_search.py, websearch_ingest.py, freesearch_search.py, lit_dedup.py, lit_screen.py)
- Outputs: OUT/stage1_.json, OUT/stage2b_.json, OUT/stage4a_*.json, OUT/stage5_merged.json, OUT/stage6_screened.json, and related intermediate files
Caveats
- License: MIT
- It explicitly requires an explicit trigger to run; will not auto-trigger on generic requests
- Documentation describes an autonomous fallback path via orchestrator.py for unattended runs
# Lit-Review Orchestrator Run the literature-review pipeline from a single command, starting from a document that describes your article. **Input**: a `.tex` or `.docx` document — a full manuscript, an abstract, or any text describing the article's content. **Output**: a deduplicated, relevance-screened master list (JSON + RIS), plus the extracted search plan and all intermediate stage files. ## Q
What does the lit-review-orchestrator skill do?
Master controller for the lit-review pipeline, driven by a document. Give it a .tex or .docx file describing an article — a full manuscript, an abstract, or a proposal — and it extracts a search plan, runs Undermind (an automated Playwright driver in Classic mode) and Google Scholar (SearchAPI.io), then merges, deduplicates, and screens the results. Only use this skill when explicitly requested — e.g., the user says "run lit-review-orchestrator", "lit-review-orchestrator", or "/lit-review-orchestrator". Do NOT auto-trigger on general literature review requests.
How do I install it?
Run `npx skills add kennethkhoocy/applied-micro-skills --skill lit-review-orchestrator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From kennethkhoocy/applied-micro-skills, a repository with 54 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.