robust-lit-review: Skill for Claude Code

.claude/skills/lit-review/SKILL.md

robust-lit-review is a skill for Claude Code from htlin222/robust-lit-review. It costs 31 tokens per session (3,265 once invoked), scanned A, original, MIT.

An automated workflow for systematic literature reviews, which are structured searches and evaluations of published research. It can brainstorm a topic, search for studies, filter and validate them, write the review, and render the result.

In plain words
What is it for?
Use it to refine search terms, run a complete literature review, check borderline articles and claims, audit the review process, and prepare the final document.
Why use it?
It organizes the many stages of a literature review so studies and decisions are less likely to be missed. An optional human-review mode pauses at nine points where judgment is important.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

This is htlin222/robust-lit-review's own configuration. It tells Claude Code how to work on robust-lit-review itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything robust-lit-review configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/htlin/robust-lit-review.

Reuse

Borrowing it

Nothing to install: this file belongs to htlin222/robust-lit-review. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/htlin222/robust-lit-review/main/.claude/skills/lit-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/htlin222/robust-lit-review

Made for: Claude Code.

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.

agentmods badge for robust-lit-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/htlin222/robust-lit-review/lit-review/github.svg)](https://agentmods.dev/skills/htlin222/robust-lit-review/lit-review)
Your own site
<a href="https://agentmods.dev/skills/htlin222/robust-lit-review/lit-review"><img src="https://agentmods.dev/badge/skills/htlin222/robust-lit-review/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.

agentmods 80×15 button for robust-lit-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/htlin222/robust-lit-review/lit-review"><img src="https://agentmods.dev/badge/skills/htlin222/robust-lit-review/lit-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,265 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.03265
Opus 5 $0.00015 $0.01632
Sonnet 5 $0.00006 $0.00653
Haiku 4.5 $0.00003 $0.00327

Measured 11d ago against content hash 370ec9ded026, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

robust-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 11d 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.

.claude/skills/lit-review/SKILL.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Robust Literature Review Pipeline

You are orchestrating a world-class automated systematic literature review. This is the single entry point for all operations.

Available Commands

The user can request any of these modes:

Command What it does
/lit-review Full pipeline: topic -> search -> filter -> validate -> write -> render
/lit-review --hitl Full pipeline with Human-in-the-Loop mode (9 checkpoints)
/brainstorm-topic Brainstorm and refine search terms before running

Human-in-the-Loop Mode (--hitl)

When enabled, the pipeline pauses at 9 checkpoints where human judgment matters most. Each checkpoint presents multiple-choice options via AskUserQuestion.

from litreview.pipeline.checkpoints import (
    format_checkpoint_for_user, CheckpointLog,
    cp1_search_strategy, cp2_borderline_articles, cp3_final_article_set,
    cp4_thematic_grouping, cp5_key_claims, cp6_prisma_audit,
    cp7_cover_letter, cp8_final_preview, cp9_publish_decision,
)
CP When Why human needed Default (auto-mode)
CP1 After query generation Wrong query = wrong review Strategy A
CP2 After filtering Borderline articles need domain judgment Review individually
CP3 After selection Missing landmark papers? Topic imbalance? Approve
CP4 Before writing Thematic structure shapes the narrative Approve structure
CP5 After writing LLM may hallucinate stats/dosing/p-values All correct
CP6 After PRISMA audit Some items may be legitimately N/A Auto-fix all
CP7 Cover letter Target journal affects framing Approve
CP8 Before render Last quality gate Render
CP9 Before publish Public action requires consent Publish

How to implement each checkpoint:

# 1. Generate checkpoint
cp = cp1_search_strategy(topic, suggested_queries)

# 2. Present to user (if --hitl enabled)
prompt_text = format_checkpoint_for_user(cp)
# Use AskUserQuestion tool with prompt_text

# 3. Record decision
cp.selected = user_response  # "A", "B", "C", etc.
log.record(cp)

# 4. Branch pipeline based on selection

Read the full file on GitHub · 335 lines

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.

  1. 11d ago First seen · 335 lines · 31 tokens per session scan A 370ec9ded026

Subscribe to this mod's changes

robust-lit-review is a skill published in the GitHub repository htlin222/robust-lit-review (55 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 3,265 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

Deep Research

Produce a deep, structured research report on a topic: decompose into key dimensions, analyze each with evidence and reasoning, synthesize cross-cutting insights, and surface open questions. Use for deep research, analysis, and literature/landscape reviews.

AgentEra/Agently · 53 tokens

cirq

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for…

LeonChaoX/qinyan-academic-skills · 67 tokens

qiskit

IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use…

LeonChaoX/qinyan-academic-skills · 73 tokens

modal

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

LeonChaoX/qinyan-academic-skills · 46 tokens

transformers

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…

LeonChaoX/qinyan-academic-skills · 63 tokens

geopandas-spatial

Geospatial and climate data analysis with geopandas and xarray. Use when: (1) geographic vector data analysis, (2) climate and weather NetCDF data, (3) spatial joins and overlay operations, (4) map visualization, (5) CRS transformations and area calculations. NOT for: satellite imagery ML (use rasterio/torchgeo)…

beita6969/ScienceClaw · 96 tokens