PluginBench
Skill
Review
Audit score 70

paper-context-resolver

lllllllama/rigorpilot-skills

Resolve reproduction-critical paper details when README and repo files leave gaps.

What is paper-context-resolver?

A helper skill for deep learning repo reproduction that fills narrow, specific gaps by extracting reproduction-critical details from primary paper sources. Use it when you have a concrete reproduction question about dataset splits, preprocessing, evaluation protocols, checkpoints, or runtime assumptions that the README doesn't answer.

  • Identifies reproduction-critical gaps between README/repo files and paper requirements
  • Extracts specific details: dataset splits, preprocessing steps, evaluation protocols, checkpoint mappings, runtime assumptions
  • Documents conflicts between README guidance and paper specifications
  • Provides narrowed source lists and evidence-backed answers
  • Distinguishes direct evidence from inference in findings

How to install paper-context-resolver

npx skills add https://github.com/lllllllama/rigorpilot-skills --skill paper-context-resolver
Claude Code
Cursor
Windsurf
Cline

How to use paper-context-resolver

  1. 1.Identify the specific reproduction-critical question (dataset split, preprocessing, evaluation protocol, etc.)
  2. 2.Gather existing README and repo file evidence
  3. 3.Provide the paper link or metadata if available
  4. 4.Run the skill with the target repo metadata and concrete reproduction question
  5. 5.Review the narrowed source list and reproduction-relevant answer
  6. 6.Check for any documented README-paper conflicts

Use cases

Good for
  • Determining the exact dataset split used in a paper when the repo README is vague
  • Finding preprocessing parameters or evaluation metrics not documented in the repository
  • Resolving checkpoint naming or model weight mapping discrepancies
  • Clarifying runtime assumptions (batch size, hardware, precision) from the original paper
  • Recording conflicts when README instructions differ from paper methodology
Who it's for
  • Deep learning researchers reproducing published work
  • ML engineers implementing paper-based systems
  • Repository maintainers documenting reproduction steps
  • Anyone needing precise paper details for reproducibility verification

paper-context-resolver FAQ

When should I use this instead of just reading the paper myself?

Use it when you have a concrete reproduction gap and need the skill to narrow down which paper sections contain the answer, document conflicts with the README, and distinguish evidence from inference.

Can this skill summarize the entire paper?

No. It focuses only on reproduction-critical details. For general paper explanations, use a different approach.

What if the README already answers my question?

Don't use this skill. It's designed to fill gaps when the README is insufficient, not to override or replace README guidance.

Does this skill execute commands or set up environments?

No. It only extracts and documents paper details relevant to reproduction. Environment setup and command execution are out of scope.

What happens if there's a conflict between the README and the paper?

The skill explicitly documents the conflict and notes it in the output, helping you decide which source to follow.

Full instructions (SKILL.md)

Source of truth, from lllllllama/rigorpilot-skills.


name: paper-context-resolver description: 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.

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

  • target repo metadata
  • reproduction-critical question
  • existing README or repo evidence
  • any already known paper links

Output expectations

  • narrowed source list
  • reproduction-relevant answer only
  • explicit README-paper conflict note when applicable
  • clear distinction between direct evidence and inference

Notes

Use references/paper-assisted-reproduction.md.