Auto Paper Response

SkillDev tools

Internal Harness instruction source for auto-paper-response. Route through visible Harness aliases instead of invoking directly.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Auto Paper Response skill

What this skill tells your AI

The instructions your AI receives, as published by linzhe001/harness-research in .agents/skills/auto-paper-response/SKILL.md and read by ahel’s review.

Purpose

Handle reviewer comments and response letters without changing the paper's claim boundary. This branch is optional and should not be entered by the main auto-paper loop unless the operator asks for rebuttal or revision-response work.

Required Inputs

  • reviewer comments or decision letter
  • current claim_register.md
  • current citation_support_bank.md
  • current patch or revision plan when available
  • operator-approved commitments or non-negotiable boundaries

Outputs

Write under auto_paper_output/<paper_id>/:

  • reviewer_comment_map.md
  • response_strategy.md
  • revision_commitment_register.md
  • response_letter.md

Rules

  • Do not promise experiments, analyses, citations, releases, or revisions that are not done or explicitly approved.
  • Do not introduce new claims to satisfy reviewers; route new claim pressure to argument and citation first.
  • Keep response commitments traceable to artifacts, patch ledger rows, or operator gates.
  • If a reviewer asks for unsupported scope expansion, return USER_GATE or route to the owning phase instead of writing around the issue.

Signals

GitHub stars
86
Forks
9
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
auto-paper-response
Source
github.com/linzhe001/harness-research