/SKILL.md
Generate rigorous mathematical HTML presentations from academic papers. Use when the user wants to create a presentation from a paper, convert arXiv LaTeX to slides, build educational content from research papers, or asks to explain a paper with full mathematical rigor. Triggers on requests involving paper explanation, arXiv presentation, theorem exposition, or mathematical pedagogy from research.
npx skillsauth add rnkarmakar/rnkarmakar.github.io paper-presentationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Transform academic paper LaTeX source into comprehensive, mathematically rigorous HTML presentations suitable for audiences with no assumed domain knowledge.
Execute phases sequentially. For detailed instructions on each phase, see references/workflow-phases.md.
Collect and validate inputs:
Extract mathematical structure:
For each core concept in the paper:
Build concept chains from basics to paper's formulation:
For each main result:
If the paper has applications:
Before writing proof sketches:
For each proof:
See references/proof-sketch-guide.md for classification criteria.
Generate single self-contained HTML file:
Execute iterative refinement:
success_count = 0
while success_count < 3:
# Spawn verifier subagent
verification = verify_output(html_output, criteria_from_references)
if verification.all_pass:
success_count += 1
else:
success_count = 0
refinement_prompt = verification.suggested_refinements
# Spawn refiner subagent
html_output = refine_output(html_output, refinement_prompt)
return html_output
See references/verification-criteria.md for the complete checklist.
Single HTML file containing:
<style> tags<script> tagsdevelopment
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.