A multi-stage workflow for building a literature review, which is a structured summary and analysis of published research. It collects papers, organizes them by topic, creates synthesis documents, and checks that claims are supported by sources.

Use it to build a research corpus, collect papers by strand, synthesize themes, write direction papers, and review the final evidence trail.

It keeps a large or multi-topic review organized and makes the link between statements and research evidence traceable.

lit-review — Skill for Claude Code by neuromechanist/research-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add neuromechanist/research-skills --skill lit-review

Clone the repo

git clone --depth 1 https://github.com/neuromechanist/research-skills

Made for: Claude Code.

Or install manuscript, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/neuromechanist/research-skills/lit-review/github.svg)](https://agentmods.dev/skills/neuromechanist/research-skills/lit-review)

Your own site

<a href="https://agentmods.dev/skills/neuromechanist/research-skills/lit-review"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/lit-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/neuromechanist/research-skills/lit-review"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/lit-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,927 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00139	$0.02927
Opus 5.5	$0.00056	$0.01171
Sonnet 5.5	$0.00028	$0.00585
Haiku 4.5	$0.00014	$0.00293

Measured 1mo ago against content hash 9dc59fb1f0e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lit-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/manuscript/skills/lit-review/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Phase Literature Review Workflow

Orchestrate a rigorous, citation-grounded literature review across phases: angles to briefs, parallel paper collection, taxonomic synthesis, direction papers, and self-review loops. Every claim in a final document is traceable back to a paper-card.

When to Use

Building a corpus-grounded review paper or a set of direction documents
Multi-strand reviews where breadth + depth must be coordinated across distinct angles (e.g. tools strand, data strand, science strand)
Reviews where claim-to-evidence traceability matters (grant lit reviews, position papers, white papers)
Iterative reviews where new papers, refined angles, or updated synthesis must roll forward without losing prior work

When NOT to Use

Original research IMRAD writing. Use manuscript:manuscript-writing.
Peer review of a submitted manuscript. Use manuscript:paper-review.
Journal formatting. Use manuscript:manuscript-formatting.

Two modes

This skill covers two workflows:

Express mode (single-pass synthesis): thematic synthesis for an Introduction, Background section, or quick standalone review. See references/single-pass-synthesis.md. Pair with references/review-frameworks.md for PRISMA, PICO, SPIDER, scoping protocol, and risk-of-bias tools.
Full protocol (multi-phase): citation-traceable corpus reviews and direction papers. Use the Phase 0-4 workflow below.

When in doubt: if the user wants flowing prose for one section, use express mode; if they want a corpus with claim-to-card traceability, use the full protocol.

Workflow Phases

Phase 0: Briefs            -> _briefs/strand-*.md (one brief per strand)
Phase 1: Collection        -> research/collection/<strand>/<slug>/{card.md, source.{pdf,md}, meta.json}
                              + INDEX.md + <strand>.bib per strand
Phase 2: Synthesis         -> research/synthesis/{<strand>-ontology, gap-analysis, scope-diagram, <domain>-map}.md
Phase 3: Direction papers  -> direction-papers/<topic>-direction.md
Phase 4: Review loop       -> revised direction; may reopen Phase 1 with new gaps

Read the full file on GitHub · 189 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago Changed · +2 lines 9dc59fb1f0e4
2mo ago First seen · 187 lines · 139 tokens per session scan A 71d05d5ba888

Subscribe to this mod's changes

lit-review is a skill published in the GitHub repository neuromechanist/research-skills (51 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 139 tokens to every session and 2,927 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Research Scientific agenitc-ai ai-marketplace-tools ai-skills codex copilot

lit-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
lit-reviewneuromechanist/research-skills	Skill	51	yesterday	BSD-3-Clause	A	139	Claude Code
godot-optimizationjame581/GodotPrompter	Skill	933	6d ago	MIT	A	28	Claude Code
food-analyzermickpletcher/AI-Skills	Skill	20	3d ago	MIT	A	41	Claude Code, Codex
astrophotography-processingmickpletcher/AI-Skills	Skill	20	3d ago	MIT	A	44	Claude Code
scienceworld-measurement-takerzjunlp/SkillNet	Skill	1.4k	5d ago	MIT	A	81	Claude Code, Codex
scienceworld-threshold-evaluatorzjunlp/SkillNet	Skill	1.4k	5d ago	MIT	A	69	Claude Code, Codex
scienceworld-animal-identifierzjunlp/SkillNet	Skill	1.4k	5d ago	MIT	A	83	Claude Code, Codex