reviewing-ai-papers

reviewing-ai-papers is a skill for Claude Code from oaustegard/claude-skills. It costs 105 tokens per session (1,766 once invoked), scanned A, original, MIT.

A review method for AI and machine-learning papers, preprints, articles, and technical blog posts. It extracts practical implications for enterprise AI engineers.

In plain words
What is it for?
Use it to review material about retrieval-augmented generation, embeddings, fine-tuning, prompts, agents, or model deployment.
Why use it?
It turns dense AI research into implementation and operations considerations for engineering teams.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-and-reasoning plugin — 3 skills shipped together

Good fit Use it to review material about retrieval-augmented generation, embeddings, fine-tuning, prompts, agents, or model deployment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oaustegard/claude-skills/reviewing-ai-papers
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 oaustegard/claude-skills --skill reviewing-ai-papers
Clone the repo
git clone --depth 1 https://github.com/oaustegard/claude-skills

Made for: Claude Code.

Or install ai-and-reasoning, the plugin that ships this one along with the rest of its 3 skills.

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 reviewing-ai-papers

README.md
[![agentmods](https://agentmods.dev/badge/skills/oaustegard/claude-skills/reviewing-ai-papers/github.svg)](https://agentmods.dev/skills/oaustegard/claude-skills/reviewing-ai-papers)
Your own site
<a href="https://agentmods.dev/skills/oaustegard/claude-skills/reviewing-ai-papers"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/reviewing-ai-papers/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 reviewing-ai-papers

Your own site · 80×15
<a href="https://agentmods.dev/skills/oaustegard/claude-skills/reviewing-ai-papers"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/reviewing-ai-papers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,766 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00105 $0.01766
Opus 5 $0.00053 $0.00883
Sonnet 5 $0.00021 $0.00353
Haiku 4.5 $0.00011 $0.00177

Measured 4d ago against content hash 0127ca2c5a4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reviewing-ai-papers 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 4d 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/ai-and-reasoning/skills/reviewing-ai-papers/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewing AI Papers

When users request analysis of AI/ML technical content (papers, articles, blog posts), extract actionable insights filtered through an enterprise AI engineering lens and store valuable discoveries to memory for cross-session recall.

When NOT to use this skill

The subject matter has to be machine learning. Adjacent asks that are not:

Situation Use
"Does this text read as AI-written?" declauding
Register or voice pass on a draft declauding
Review a pull request or a diff code-review
A paper outside ML read it directly; this skill's lens will not fit

"AI" appearing in the request is not the trigger — AI being the topic of the document is.

Contextual Priorities

Technical Architecture:

  • RAG systems (semantic/lexical search, hybrid retrieval)
  • Vector database optimization and embedding strategies
  • Model fine-tuning for specialized scientific domains
  • Knowledge distillation for secure on-premise deployment

Implementation & Operations:

  • Prompt engineering and in-context learning techniques
  • Security and IP protection in AI systems
  • Scientific accuracy and hallucination mitigation
  • AWS integration (Bedrock/SageMaker)

Enterprise & Adoption:

  • Enterprise deployment in regulated environments
  • Building trust with scientific/legal stakeholders
  • Internal customer success strategies
  • Build vs. buy decision frameworks

Analytical Standards

  • Maintain objectivity: Extract factual insights without amplifying source hype
  • Challenge novelty claims: Identify what practitioners already use as baselines. Distinguish "applies existing techniques" from "genuinely new methods". The procedure for this is "The ablation the paper did not run" below. Run it; do not improvise a judgement
  • Separate rigor from novelty: Well-executed study of standard techniques ≠ methodological breakthrough
  • Confidence transparency: Distinguish established facts, emerging trends, speculative claims
  • Contextual filtering: Prioritize insights mapping to current challenges

Read the full file on GitHub · 193 lines

Files

What ships with it

1 file 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.

  1. 4d ago Changed · +53 lines 0127ca2c5a4e
  2. 9d ago First seen · 140 lines · 105 tokens per session scan A 987643461014

Subscribe to this mod's changes

reviewing-ai-papers is a skill published in the GitHub repository oaustegard/claude-skills (148 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 1,766 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

laravel-ai-sdk

Use when integrating AI agents, tool calling, embeddings, structured output, or streaming in Laravel 13 via the laravel/ai package.

fusengine/agents · 35 tokens

aws-generative-ai-developer

Build Amazon Bedrock and serverless generative AI applications using Lambda, API Gateway, Step Functions, EventBridge, S3, DynamoDB, SQS, Guardrails, and IAM. Prefer this for serverless GenAI app design and implementation; prefer aws-agentcore for AgentCore runtime, aws-bedrock-agent-security-governor for deep Bedrock…

VincentChuWaiChow/vanguard-frontier-agentic · 93 tokens

dspy-haystack-integration

Use for integrating DSPy with Haystack, optimizing Haystack prompts, improving retrieval pipelines, and extracting DSPy prompts.

OmidZamani/dspy-skills · 32 tokens

llm-app-patterns

Provides architectural patterns for LLM-powered applications and AI assistants, including prompt engineering, RAG, agent loops, conversation management, and evaluation. Use when building AI-based features, chatbots, or complex AI system architectures.

tranhieutt/software_development_department · 50 tokens

expert-ai-engineer

AI/ML engineering specialist — LLM integrations, prompt design, RAG pipelines, embeddings, evals, fine-tuning decisions, agent architectures. Use for any task involving model APIs, prompts, vector stores, or ML tradeoffs. Normally invoked by model-router.

mehtab78/skills · 59 tokens

dspy

DSPy: declarative LM programs, auto-optimize prompts, RAG.

kevinnft/ai-agent-skills · 19 tokens