paper-context-resolver
๐ฏSkillfrom lllllllama/rigorpilot-skills
|A helper skill in the RigorPilot suite that resolves gaps between a deep learning repository's README and its associated research paper, helping agents understand the paper context needed for faithful reproduction.
Overview
Paper Context Resolver is a helper skill in the RigorPilot suite that bridges the gap between a deep learning repository's README and its associated research paper. When a README references results, hyperparameters, or methods without fully explaining them, this skill locates the relevant sections of the paper and provides the missing context so agents can make informed decisions during reproduction.
Key Features
- Gap detection - Identifies where the README assumes knowledge from the paper, such as unexplained hyperparameter choices, dataset splits, or evaluation metrics
- Paper section mapping - Locates the specific paper sections (methodology, experiments, ablations) that provide context for repository code and configurations
- Context synthesis - Produces concise summaries of relevant paper content that agents can reference during reproduction without reading the entire paper
- Integration with RigorPilot workflow - Designed to be called by the ai-research-reproduction orchestrator or used standalone when you need paper context for a specific code section
- Non-destructive operation - Purely informational; reads and synthesizes without modifying any repository files
Who is this for?
- Deep learning researchers reproducing papers where the code repository's documentation is sparse or assumes familiarity with the paper
- Research assistants who need to quickly understand which parts of a paper are relevant to specific sections of its companion codebase
- ML engineers working with research code who want to understand the theoretical justification behind specific implementation choices
Same repository
lllllllama/rigorpilot-skills(14 items)
Installation
npx vibeindex add lllllllama/rigorpilot-skills --skill paper-context-resolvernpx skills add lllllllama/rigorpilot-skills --skill paper-context-resolver~/.claude/skills/paper-context-resolver/SKILL.mdSKILL.md
More from this repository10
The primary explore-lane orchestrator in the RigorPilot suite that enables meaningful and potentially novel exploration on top of current deep learning research, with idea gating, bounded experiments, and candidate ranking.
The primary end-to-end orchestrator in the RigorPilot suite that guides AI agents through README-first reproduction of deep learning repositories, ensuring scientific rigor, comparability, and auditable outputs.
A RigorPilot explore-lane skill for candidate implementation, code transplanting, and stitching on isolated branches when the researcher has explicitly authorized exploratory work on top of current research.
A RigorPilot trusted-lane skill for research-safe debugging of deep learning experiments that analyzes failures first and applies patches only after explicit approval, preserving scientific comparability.
A RigorPilot trusted-lane skill that performs read-only project analysis on deep learning repositories, including model mapping, structure inspection, and risk surfacing, without making any edits.
A RigorPilot helper skill that scans deep learning repositories and extracts README commands to build an initial reproduction plan, typically invoked by the main reproduction orchestrator.
A RigorPilot trusted-lane skill for conservatively starting or verifying deep learning training runs, including resume handling, bounded monitoring, and generating durable training records.
A RigorPilot trusted-lane skill for conservatively setting up deep learning environments, including datasets, pretrained weights, checkpoints, and cache assumptions required for research reproduction.
A RigorPilot explore-lane skill for running small-subset probes, short-cycle trials, and ranked exploratory experiments when the researcher explicitly authorizes candidate-only exploration.
A RigorPilot trusted-lane skill for conservatively running documented evaluation, inference, smoke tests, and sanity checks in deep learning repositories without introducing unaudited changes.