Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
hummat avatar

Papi Verify

  • 1 installs
  • 35 repo stars
  • Updated August 1, 2026
  • hummat/paperpipe

Verify code against a paper by mapping paper symbols to code variables, flagging mismatches like wrong sign/scale or shape bugs, and proposing minimal fixes and tests.

About

Checks whether a code implementation matches the equations and algorithms in a paper, building a symbol-mapping table and a mismatch list. A developer uses it to catch sign, scale, normalization, and shape errors when implementing from literature.

  • Symbol-mapping table with shapes and units
  • Mismatch/risk list plus a minimal fix plan and suggested tests

Papi Verify by the numbers

  • 1 all-time installs (skills.sh)
  • Ranked #984 of 1,352 Code Review & Quality skills by installs in the Skillselion catalog
  • Data as of Aug 2, 2026 (Skillselion catalog sync)
npx skills add https://github.com/hummat/paperpipe --skill papi-verify

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs1
repo stars35
Last updatedAugust 1, 2026
Repositoryhummat/paperpipe

What it does

Verify code against a paper by mapping paper symbols to code variables, flagging mismatches like wrong sign/scale or shape bugs, and proposing minimal fixes and tests.

Files

SKILL.mdMarkdownGitHub ↗

Verify Code Against Paper

You are given:

  • Code (or a code excerpt), plus paper excerpts (paste papi show ... --level ... output above, or reference exported files).

Project context (optional): $ARGUMENTS

Rules

  • Prefer equations/LaTeX over summaries when there's a conflict.
  • If a claim is not supported by provided excerpts, say: "Not supported by provided excerpts."
  • For supported claims, include a short quote snippet (<= 15 words) and cite as:

(paper: <name>, arXiv: <id if present>, source: summary|equations|tex|notes, ref: section/eq/table/figure if present)

Output

1) Symbol mapping table: paper symbol/definition → code variable/tensor (include shapes/units if stated) 2) Mismatches / risks (bulleted): missing terms, wrong sign/scale/normalization, shape bugs, hidden assumptions 3) Fix plan: minimal code changes (or patch sketch) + suggested asserts/tests to lock correctness

End with: Cited papers: <comma-separated paper names and/or arXiv IDs>

For general CLI commands, see /papi.

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.