Paper Context Resolver Skill: Fill Repro Gaps

Looks up one specific paper detail, such as a dataset split or eval protocol, when a repo README leaves a reproduction gap.

Installs: 485K; on skills.sh
Stars: 486; on GitHub
Files: 2; besides SKILL.md
Updated: Sep 2026; last repo commit

paper-context-resolver is a narrow helper for README-first deep learning reproduction. When the README and repo files leave a gap that blocks reproduction, it resolves that one detail from primary paper sources and notes any conflict between the paper and the README. It separates direct evidence from inference.

SKILL.md says to use it only when a concrete question exists: dataset version or split, preprocessing, evaluation protocol, checkpoint mapping or runtime assumption. It is not for paper summaries, repo scanning, environment setup, running commands, or title-only lookups. It is optional and usually called by the main RigorPilot skill.

Good for

Researchers reproducing a paper from its GitHub repo
ML engineers stuck on a missing preprocessing or split detail
Anyone using the RigorPilot main skill who needs a paper check

Install paper-context-resolver

Claude Code

Copy this prompt.

Install the paper-context-resolver skill in Claude Code. Run this command:

npx skills add lllllllama/RigorPilot-Skills --all

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js 22.20+.

The README says the main skill, ai-research-reproduction, works alone, and to choose all skills for the companion entrypoints. The README lists this skill as one of two helpers that support orchestration, so install the set. The README tested the installer with skills@1.5.26 and Node 22.20.0, which it says is the minimum.

From the project README. Source.

What's in the skill

When it loads

Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.

Sections in SKILL.md

When to apply
When not to apply
Clear boundaries
Input expectations
Output expectations
Notes

Key facts

Author: lllllllama (RigorPilot-Skills)
Installs on skills.sh: 485,006 (Nov 2, 2026)
GitHub stars: 486 on lllllllama/rigorpilot-skills (Nov 2, 2026)
License: MIT
Last repo commit: Sep 23, 2026
What installs: SKILL.md plus 2 bundled files: agents/openai.yaml, references/paper-assisted-reproduction.md
skills.sh audits: Gen Agent Trust Hub: pass, Socket: pass, Snyk: warn
Part of: RigorPilot-Skills; a helper-tier skill that is optional and usually called by the main skill
Needs: Target repo metadata, a reproduction-critical question, README evidence and any known paper links
Reference: references/paper-assisted-reproduction.md

What it includes

Takes one reproduction-critical question
Needs repo metadata, the README evidence so far, and any paper links you already have.
Narrow the question
Finds the detail in primary paper sources
Returns a narrowed source list and a reproduction-relevant answer only.
Network · Resolve from paper sources
Notes any README-paper conflict
Does not override README guidance without documenting the conflict.
Record conflicts
Marks what is direct evidence and what is inferred
Output includes this distinction.
Separate evidence from inference

From the official docs

Permissions

Low risk

It reads your repo and paper sources and bundles no scripts. Check cited sources before you rely on a split or metric.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It looks outside your repo for answers
SKILL.md says it resolves details from primary paper sources. Check the cited sources for important numbers.

Technical details

Talks to	Paper sources, as SKILL.md says "primary paper sources"
Scopes	Reads your repo files and paper sources

Questions

What does paper-context-resolver do?

It resolves one narrow reproduction detail from primary paper sources when a repo README leaves a gap. It records conflicts between the paper and the README.

How do I install it?

Follow the install box at the top of the page. The README says to choose all skills for the companion entrypoints, so install the whole RigorPilot set.

When should I not use it?

For a general paper summary, repo scanning, environment setup, running commands, or when all you have is a paper title.

Does it replace the README?

No. It supplements README-first reproduction and does not override README guidance without recording the conflict.

How is it different from repo-intake-and-plan?

repo-intake-and-plan scans the repository and plans the smallest trustworthy reproduction. paper-context-resolver answers one paper question the repo cannot.

Is it safe?

The skill bundles one reference note and no scripts. It reads repo files and paper sources. Its skills.sh listing shows a Snyk warn, so look at the audit page before you install.

Information

updated Nov 2, 2026

Repository: lllllllama/rigorpilot-skills
Folder: skills/paper-context-resolver

lllllllama/rigorpilot-skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 3

RigorPilot-Skills README · github.com
paper-context-resolver SKILL.md · github.com
skills.sh listing · skills.sh