AutoSci: Skill for Claude Code

.claude/skills/novelty/SKILL.md

novelty is a skill for Claude Code from skyllwt/AutoSci. It costs 40 tokens per session (2,729 once invoked), scanned A, original, MIT.

A research check that compares an idea or method with prior work using web search, Semantic Scholar, the project wiki, arXiv preprints, and a review model. It produces a novelty score, related work, differences, and recommendations.

In plain words
What is it for?
Use it to assess a written idea, a wiki idea page, or a paper title or arXiv link, either quickly or with an additional review step, and optionally save the score to a wiki page.
Why use it?
It helps determine whether an idea appears new and identifies existing work that may overlap with it.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

This is skyllwt/AutoSci's own configuration. It tells Claude Code how to work on AutoSci 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 AutoSci configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 tools/fetch_s2.py search "<method-keywords>" --limit 20.

About the project

AutoSci is an AI research platform organized around a wiki, with an agent that supports stages of scientific work such as reading, experimentation, writing, and retaining knowledge across projects. It is for people building or using AI-assisted research workflows, with Claude Code, Codex, and OpenCode adaptations available. The catalogue add-ons extend those agent-specific workflows.

skyllwt/AutoSci · 1,663 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to skyllwt/AutoSci. 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/skyllwt/AutoSci/main/.claude/skills/novelty/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/skyllwt/AutoSci

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 novelty

README.md
[![agentmods](https://agentmods.dev/badge/skills/skyllwt/autosci/novelty.svg)](https://agentmods.dev/skills/skyllwt/autosci/novelty)
Your own site
<a href="https://agentmods.dev/skills/skyllwt/autosci/novelty"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/novelty.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,729 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 $0.00040 $0.02729
Opus 5 $0.00020 $0.01365
Sonnet 5 $0.00008 $0.00546
Haiku 4.5 $0.00004 $0.00273

Measured 9d ago against content hash 3ae4d8a8c765, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

novelty 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 9d 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/novelty/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/novelty

Verify the novelty of a research idea or method using multiple sources. Searches WebSearch, Semantic Scholar, existing wiki work, and arXiv recent preprints, then Review LLM cross-verifies. Outputs a novelty score (1-5), closest prior work, differentiation points, and next-step recommendations. Can be used standalone or called by /ideate Phase 4.

Inputs

  • target: one of the following:
    • free-text description of the idea (a paragraph or a few sentences)
    • slug of an ideas/ page in the wiki (e.g. sparse-lora-for-edge-devices)
    • paper title or arXiv URL (check novelty of that paper's method)
  • --quick: fast mode, skip Review LLM cross-verify (Step 3), search only
  • --verbose: output full search results, not just summaries
  • --write (optional, default off): persist the resulting novelty_score to the target's frontmatter. Only takes effect when target is an idea slug (i.e. wiki/ideas/{slug}.md exists). Free-text targets and paper-novelty checks remain read-only regardless of this flag. Treat as a user-owned flag — /ideate Phase 4 sets it explicitly when calling /novelty; do not infer it from repo state.

Outputs

  • Novelty Report (output to terminal):
    • Novelty Score (1-5)
    • List of closest prior work (top 3-5)
    • Differentiation points versus each prior work
    • Review LLM cross-verify assessment (unless --quick)
    • Recommended action: proceed / modify / abandon
  • Idea page write (only when --write is set AND target is an idea slug): updates wiki/ideas/{slug}.md frontmatter novelty_score field via tools/research_wiki.py set-meta. No other field is touched.

Wiki Interaction

Reads

  • wiki/papers/*.md — search existing papers for similar methods
  • wiki/concepts/*.md — check concept overlap
  • wiki/methods/*.md — check for already-cataloged methods that overlap with the candidate
  • wiki/ideas/*.md — check for duplication with existing ideas (especially failure_reason of failed ideas)
  • wiki/graph/context_brief.md — global context to assist search

Read the full file on GitHub · 218 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. 9d ago First seen · 218 lines · 40 tokens per session scan A 3ae4d8a8c765

Subscribe to this mod's changes

novelty is a skill published in the GitHub repository skyllwt/AutoSci (1,663 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 2,729 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens