AutoSci: Skill for Claude Code

.claude/skills/rebuttal/SKILL.md

rebuttal is a skill for Claude Code from skyllwt/AutoSci. It costs 34 tokens per session (3,964 once invoked), scanned A, original, MIT.

A rebuttal-writing skill that turns review comments into numbered concerns, checks their supporting evidence, and drafts responses.

In plain words
What is it for?
Use it to prepare plain-text or rich-text replies to paper reviews, including follow-up stress tests and formats for venues such as ICLR, NeurIPS, ICML, ACL, or CVPR.
Why use it?
It helps organize scattered reviewer feedback and test whether each response is supported by the available research.

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/research_wiki.py log wiki/ \.

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 · 1,666 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/rebuttal/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 rebuttal

README.md
[![agentmods](https://agentmods.dev/badge/skills/skyllwt/autosci/rebuttal/github.svg)](https://agentmods.dev/skills/skyllwt/autosci/rebuttal)
Your own site
<a href="https://agentmods.dev/skills/skyllwt/autosci/rebuttal"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/rebuttal/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 rebuttal

Your own site · 80×15
<a href="https://agentmods.dev/skills/skyllwt/autosci/rebuttal"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/rebuttal.svg" alt="Reviewed on agentmods" width="80" 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 3,964 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 $0.00034 $0.03964
Opus 5 $0.00017 $0.01982
Sonnet 5 $0.00007 $0.00793
Haiku 4.5 $0.00003 $0.00396

Measured 10d ago against content hash 13beaf247273, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

rebuttal 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 10d 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/rebuttal/SKILL.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/rebuttal

Parse review comments, atomize each concern (Rvx-Cy numbering) and map it to a wiki idea or method, check whether evidence is sufficient (tracing back to wiki experiments), simulate reviewer follow-up questions with Review LLM (stress-test, scored 1-5), and generate a formal plain-text rebuttal and a rich-text rebuttal. Safety checks ensure no fabrication, no overpromise, full coverage.

Inputs

  • review: source of review comments, one of:
    • file path (e.g. raw/reviews/reviewer1.txt, raw/reviews/meta-review.md)
    • multiple file paths (comma-separated: raw/reviews/R1.txt,raw/reviews/R2.txt,raw/reviews/R3.txt)
    • directly pasted review text
  • --paper-slug (optional): slug of the associated paper in wiki/outputs/, used to locate PAPER_PLAN
  • --venue (optional): target conference/journal (ICLR / NeurIPS / ICML / ACL / CVPR); affects rebuttal format and word limits
  • --stress-test (optional, enabled by default): Review LLM simulates reviewer follow-up; disable with --no-stress-test
  • --format (optional, default formal): output format
    • formal: formal plain-text rebuttal (suitable for pasting directly into submission system)
    • rich: rich-text version (with wiki [[links]], detailed analysis, improvement plan)

Outputs

  • wiki/outputs/rebuttal-{slug}.md — rich-text rebuttal (with [[wikilinks]], evidence tracing, analysis tables)
  • wiki/outputs/rebuttal-{slug}.txt — formal rebuttal (plain text, suitable for pasting into submission system)
  • wiki/ideas/*.md / wiki/methods/*.md — if a concern exposes an evidence gap, append a suggestion to the relevant section (## Risks / ## Lessons learned for ideas; ## Limitations for methods)
  • wiki/log.md — append log entry

Wiki Interaction

Reads

  • wiki/ideas/*.md — map concerns to ideas, check linked experiments and novelty argument
  • wiki/methods/*.md — map concerns to methods, check Mechanism / Procedure / Limitations
  • wiki/experiments/*.md — find experiment results supporting ideas (via linked_idea)
  • wiki/papers/*.md — find citation context for referenced papers
  • wiki/concepts/*.md — understand the conceptual background of method-related concerns
  • wiki/outputs/PAPER_PLAN.md — understand paper structure (from /paper-plan, if --paper-slug provided)
  • wiki/graph/context_brief.md — global context
  • wiki/graph/edges.jsonl — idea-experiment-paper-method relationships
  • .claude/skills/shared-references/cross-model-review.md — Review LLM stress-test independence

Read the full file on GitHub · 345 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. 10d ago First seen · 345 lines · 34 tokens per session scan A 13beaf247273

Subscribe to this mod's changes

rebuttal is a skill published in the GitHub repository skyllwt/AutoSci (1,666 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 3,964 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

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

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