Auto Paper Data
SkillDev toolsInternal Harness instruction source for auto-paper-data. Route through visible Harness aliases instead of invoking directly.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Auto Paper Data skill
What this skill tells your AI
The instructions your AI receives, as published by linzhe001/harness-research in .agents/skills/auto-paper-data/SKILL.md and read by ahel’s review.
Purpose
Prepare availability and reproducibility statements from verified project facts. This branch does not invent dataset access, license state, ethics approval, code release status, compute details, or artifact permanence.
Required Inputs
- project data locations and release policy
- code repository or package status when known
- license, embargo, or access restrictions
- ethics, consent, IRB, or human-subject boundaries when applicable
- reproducibility materials such as configs, seeds, checkpoints, and commands
Outputs
Write under auto_paper_output/<paper_id>/:
data_availability_statement.mdcode_availability_statement.mdreproducibility_checklist.mdethics_boundary.md
Rules
- If availability, licensing, ethics, or release status is unclear, write a
USER_GATEitem instead of filling a plausible statement. - Separate current verified facts from planned future releases.
- Do not state that data or code is public unless the artifact or operator approval proves it.
- Route new evidence claims back to argument, citation, or harden.
Gate Ledger
Report a Gate ledger entry with commands run, artifacts written, unresolved
availability or ethics facts, any USER_GATE or NOT_RUN reason, and the next
owner before handoff.
Signals
- GitHub stars
- 86
- Forks
- 9
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
auto-paper-data- Source
- github.com/linzhe001/harness-research