
Paper Context Resolver
When you're trying to reproduce a deep learning paper and the README doesn't quite tell you which dataset split they used or how they mapped their checkpoints, this skill fills that specific gap by pulling answers from the paper itself. It's designed as a helper that gets called only when you hit a concrete reproduction blocker, not for general paper summaries or to second-guess what the repo already documents. The useful bit is that it explicitly flags conflicts between what the paper says and what the README claims, which happens more often than it should. Think of it as a surgical reference lookup rather than a research assistant.
- skills.sh installs
- 493.3K
- GitHub stars
- 486
- last updated
- Aug 21, 2026
Install
$ npx -y skills add lllllllama/rigorpilot-skills --skill paper-context-resolver --agent claude-codeInstalls into .claude/skills of the current project.
Files
paper-context-resolver
Use this as the Rigor Paper Context helper. The installed slug remains
paper-context-resolver for compatibility.
When to apply
- README and repo files leave a reproduction-critical gap.
- The gap concerns dataset version, split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumptions.
- The main skill needs a narrow evidence supplement instead of a full paper summary.
- There is already a concrete reproduction question to answer.
When not to apply
- The README already gives enough reproduction detail.
- The user wants a general paper explanation rather than reproduction support.
- The goal is to override README instructions without documenting the conflict.
- The only available input is a paper title and there is no concrete reproduction gap yet.
Clear boundaries
- This skill is optional.
- This skill is helper-tier and should usually be orchestrator-invoked.
- It supplements README-first reproduction.
- It does not replace the main orchestration flow.
- It does not summarize the whole paper by default.
Input expectations
Sponsors
Details
- Repository
- github.com/lllllllama/rigorpilot-skills
- Categories
- Documentation, Data Science & ML, Video & Audio Editing
- First seen
- Jul 14, 2026