skilld
All skills
oaustegard avatar

/reviewing-ai-papers

@51c9333
by Oskar Austegardoaustegard/claude-skills150 stars
6

Analyzes an AI/ML publication — paper, preprint, article, technical blog post — and extracts what an enterprise AI engineer should do about it. Use when someone supplies a URL or document on RAG, embeddings, fine-tuning, prompt engineering, agents, or LLM deployment and asks "review this paper", "what do you make of this", "is this worth adopting", or "summarise the method and its limits". The subject matter must itself be machine learning.

Ask your Agent

Use this Skill: https://skilld.dev/gh/oaustegard/claude-skills/reviewing-ai-papers

This session only. Nothing lands on disk.

CHANGELOG.md

≈315 tokens on demand. Your agent reads this file only when SKILL.md points to it.

reviewing-ai-papers - Changelog

All notable changes to the reviewing-ai-papers skill are documented in this file. The format is based on Keep a Changelog.

[0.4.0] - 2026-09-08

Other

  • reviewing-ai-papers 0.4.0: the ablation the paper did not run (#790)

[0.4.0] - 2026-09-08

Added

  • "The ablation the paper did not run": a four-step check over the paper's own ablation tables, with a required output block, replacing the untooled "challenge novelty claims" guidance. Cites two diagnosed misses — SPD/hLLM (arXiv:2609.01807), whose decoder is never ablated and whose Hungarian solve is matched by a sort, and TTT-Embed (arXiv:2608.12569), whose residual query vector is never compared against label-free constructions of the same object.

[0.3.0] - 2026-08-25

Added

  • add line numbers, markdown ToC, and other files listing
  • Delete VERSION files, complete migration to frontmatter
  • Migrate all 27 skills from VERSION files to frontmatter

Fixed

  • limit markdown ToC to h1/h2 headings only

Other

  • top skills: separate by omission, and correct the guidance that said otherwise (#777)
  • Remove _MAP.md files, direct agents to tree-sitting for code navigation (#545)

Source: SKILL.md on GitHub

Third-party checks

2 warnings13d4 checks · Risk SAFE
  • Gen Agent Trust Hub13d

    The skill analyzes external research papers and stores insights in a persistent memory. The lack of sanitization and boundary markers for external data creates a risk of indirect prompt injection where malicious instructions in a paper could be stored in the agent's long-term memory.

  • Socket13d

    No alerts

  • Snyk13d

    Risk: MEDIUM · 1 issue

  • Runlayer7mo

    2/2 files flagged

Provenance

Signed by skilld at 51c9333. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 3 weeks ago

Capability

metadata
{
  "version": "0.4.0"
}

README badge

README badge for oaustegard/claude-skills/reviewing-ai-papers