Write Literature Review
Iterative OpenAlex literature review: seed, citation-expand, screen, rank, synthesize
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · cc02405
Ran the bundled pipeline live against OpenAlex: it returned eight real, deduped papers on biochar soil carbon with verified DOIs, actual venues (Chemosphere, Environmental Science & Technology) and true citation counts (4494, 3100), then ranked them into a reproducible table. A no-skill baseline recalls papers from memory and risks fabricated or stale citations; this fetches and ranks verifiable records with machine-readable JSONL/CSV artifacts. Search, dedupe, and rank subcommands all executed cleanly with no API key required.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Write Literature Review does
An iterative literature-review workflow that drafts keywords, builds a seed set from live OpenAlex title-and-abstract matches, expands by backward/forward citations, screens to saturation, ranks, and writes a review grounded only in included references. Triggers when the user wants a real literature review or citation-expansion survey on a research topic, not a quick reading list.
How to install Write Literature Review
git clone https://github.com/Zsun79/LitReviewSkill
mkdir -p ~/.claude/skills
cd LitReviewSkill && cp -r skills/write-literature-review ~/.claude/skills/
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Write Literature Review
-
/write-literature-reviewIterative OpenAlex literature review: seed, citation-expand, screen, rank, synthesize
It also activates on plain-language prompts like these:
-
Write me a real literature review on biochar soil carbon -
Build a seed set of papers on this topic and expand by citations -
I need a ranked reading list on this topic with verified DOIs
Frequently asked questions
- Is the Write Literature Review skill free?
- Yes. The skill itself is free from Zsun79/LitReviewSkill. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Write Literature Review work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Works. Ran the bundled pipeline live against OpenAlex: it returned eight real, deduped papers on biochar soil carbon with verified DOIs, actual venues (Chemosphere, Environmental Science & Technology) and true citation counts (4494, 3100), then ranked them into a reproducible table. A no-skill baseline recalls papers from memory and risks fabricated or stale citations; this fetches and ranks verifiable records with machine-readable JSONL/CSV artifacts. Search, dedupe, and rank subcommands all executed cleanly with no API key required.
- What is the Write Literature Review SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Write Literature Review?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Write Literature Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.