---
name: Lit Screen
slug: lit-screen
category: AI Engineering
description: "Screens paper abstracts against a research prompt, producing a relevance score (1-10), paper type, methodology, and relationship to the user's work. Part of a literature review pipeline, used when explicitly requested."
github: "https://github.com/kennethkhoocy/applied-micro-skills/tree/main/plugins/applied-micro/skills/lit-review-orchestrator/lit-screen"
language: Python
stars: 48
forks: 0
install: "npx degit https://github.com/kennethkhoocy/applied-micro-skills/tree/main/plugins/applied-micro/skills/lit-review-orchestrator/lit-screen ~/.claude/skills/lit-screen"
installs_to: ~/.claude/skills/lit-screen
source_path: plugins/applied-micro/skills/lit-review-orchestrator/lit-screen/SKILL.md
collection_size: 25
category_size: 2451
collection_url: "https://dirskills.com/collections/kennethkhoocy/applied-micro-skills"
added: 2026-08-11T07:21:20.043Z
last_synced: 2026-08-11T07:21:20.043Z
canonical_url: "https://dirskills.com/skills/lit-screen"
---

# Lit Screen

Screens paper abstracts against a research prompt, producing a relevance score (1-10), paper type, methodology, and relationship to the user's work. Part of a literature review pipeline, used when explicitly requested.

**Install:**

```bash
npx degit https://github.com/kennethkhoocy/applied-micro-skills/tree/main/plugins/applied-micro/skills/lit-review-orchestrator/lit-screen ~/.claude/skills/lit-screen
```

## README

# lit-screen (Stage 6 -- Abstract Screening)

Screen every paper's abstract against the original research prompt. In the
orchestrator's agent-driven flow the relevance judgment is produced by **Opus
subagents** through the `--emit-tasks` / `--ingest-results` seam (no API key); a
standalone run uses the in-script Claude Sonnet API path instead. Produces a
relevance score (1-10), rationale, and structured tags for each paper.

## Usage

```bash
python ~/.claude/skills/lit-screen/scripts/lit_screen.py \
  --input stage5_merged.json \
  --query "your research prompt here" \
  -o stage6_screened.json
```

## CLI Flags

| Flag | Default | Description |
|------|---------|-------------|
| `--input` | (required) | Input JSON from Stage 5 (dedup output) |
| `--query` | (required) | Research query/prompt to screen against |
| `-o, --output` | `stage6_screened.json` | Output JSON path |
| `--model` | `claude-sonnet-4-6` | Anthropic model ID (autonomous fallback) |
| `--concurrency` | `5` | Max simultaneous API requests (autonomous fallback) |
| `--emit-tasks PATH` | — | Agent-driven: write per-paper screening tasks and stop (no API) |
| `--ingest-results PATH` | — | Agent-driven: merge Opus screening results and write all outputs (no API) |

## Output Schema

Each paper gets these fields added:

```json
{
  "screening_score": 8,
  "screening_rationale": "Directly examines board composition changes...",
  "paper_type": "empirical",
  "identification_strategy": "DiD",
  "relationship": "direct competitor"
}
```

## Output Files

1. **JSON**: `stage6_screened.json` -- full paper list with screening fields
2. **JSON**: `stage6_filtered.json` -- papers with score >= 4 only
3. **XLSX**: `stage6_screened.xlsx` -- all papers, sorted by screening_score descending
4. **XLSX**: `stage6_filtered.xlsx` -- filtered papers (score >= 4), sorted by score descending
5. **RIS**: `stage6_screened.ris` -- for import into reference managers
6. **BIB**: `stage6_screened.bib` -- BibTeX entries for papers with score >= 5

## Environment Variables

| Var | Required | Description |
|-----|----------|-------------|
| `ANTHROPIC_API_KEY` | Fallback | Standalone-run screening (Sonnet API). The agent-driven flow screens with Opus subagents and needs no key. |

## Field Values

- **screening_score**: 1 (irrelevant) to 10 (highly relevant); 0 = no abstract
- **paper_type**: `theoretical` or `empirical`
- **identification_strategy**: `natural experiment`, `IV`, `DiD`, `RDD`, `structural`, `descriptive`, `N/A`
- **relationship**: `foundational/must-cite`, `same method different context`, `same context different method`, `direct competitor`, `methodological reference`, `tangential`