agent-papers-cli: Skill for Claude Code

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

literature-review is a skill for Claude Code from collaborative-deep-research/agent-papers-cli. It costs 34 tokens per session (569 once invoked), scanned A, original, Apache-2.0.

Instructions for conducting a systematic review of academic research. This means searching for relevant papers in a structured way, removing duplicates, and comparing the strongest results.

In plain words
What is it for?
Research surveys and literature reviews using searches across academic sources, with paper details, summaries, outlines, and analysis of introductions, methods, and results.
Why use it?
They provide a repeatable process for defining the topic, finding papers, judging relevance, and reading important studies in depth.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is collaborative-deep-research/agent-papers-cli's own configuration. It tells Claude Code how to work on agent-papers-cli 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 agent-papers-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to collaborative-deep-research/agent-papers-cli. 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/collaborative-deep-research/agent-papers-cli/main/.claude/skills/literature-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/collaborative-deep-research/agent-papers-cli

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 literature-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/collaborative-deep-research/agent-papers-cli/literature-review.svg)](https://agentmods.dev/skills/collaborative-deep-research/agent-papers-cli/literature-review)
Your own site
<a href="https://agentmods.dev/skills/collaborative-deep-research/agent-papers-cli/literature-review"><img src="https://agentmods.dev/badge/skills/collaborative-deep-research/agent-papers-cli/literature-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 569 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.00569
Opus 5 $0.00017 $0.00284
Sonnet 5 $0.00007 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured 6d ago against content hash 3eb98a9fcdfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

literature-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 6d 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/literature-review/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conduct a systematic literature review on "$ARGUMENTS" using the paper and paper-search CLI tools.

1. Define Scope

Before searching, clarify with the user:

  • Topic boundaries and key terms
  • Year range (default: last 5 years)
  • Target venues or communities (if any)
  • Desired number of papers (default: 15-20 core papers)

Search with multiple query variations to maximize coverage:

paper-search semanticscholar papers "<main query>" --limit 20 --year <range>
paper-search semanticscholar papers "<synonym query>" --limit 20 --year <range>
paper-search semanticscholar papers "<related query>" --limit 20 --year <range>
paper-search google scholar "<topic>"

Deduplicate results by title/paper ID.

3. Triage

For each unique paper found:

paper-search semanticscholar details <paper_id>
paper skim <arxiv_id> --lines 2

Categorize as: highly relevant / somewhat relevant / not relevant.

4. Deep Analysis

For highly relevant papers:

paper outline <arxiv_id>
paper read <arxiv_id> introduction
paper read <arxiv_id> method
paper read <arxiv_id> results
paper read <arxiv_id> conclusion

Take structured notes on each paper: problem, method, key results, limitations.

5. Citation Graph Exploration

For seminal papers, find related work:

paper-search semanticscholar citations <paper_id> --limit 20
paper-search semanticscholar references <paper_id> --limit 20

Add any important papers discovered this way back to the triage step.

6. Produce Report

Organize findings by theme, not by paper. Include:

  • Overview of the field and its evolution
  • Key methods and approaches (with comparisons)
  • Main results and findings
  • Open questions and future directions
  • Complete reference list with paper IDs and URLs
  • BibTeX entries for all cited papers (use paper bibtex <arxiv_id> to generate)

Guidelines

  • Aim for breadth first: cover all major approaches before going deep on any one.
  • Note citation counts and venues to gauge paper impact.
  • Flag contradictory findings explicitly.
  • Distinguish between empirical results and theoretical claims.

Read the full file on GitHub · 79 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. 6d ago First seen · 79 lines · 34 tokens per session scan A 3eb98a9fcdfe

Subscribe to this mod's changes

literature-review is a skill published in the GitHub repository collaborative-deep-research/agent-papers-cli (50 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 569 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens