Agent Plugins Marketplace
← All plugins

bootloops-research

v1.0.0

The BootLoops research skills: heavier machinery for specific tasks — proving with agents (adversary-first pipelines), pre-circulation referee audit, the literature review behind a novelty claim, bibliography verification, and the scientific-prose linter.

CodexClaude CodeAgent Plugins4 Skills

By Matthew D. SchwartzLicense: CC-BY-4.0 AND MIT11 GitHub starsUpdated 2 days ago

Directory evidence

Runtimes
Codex, Claude Code, and Agent Plugins
Parsed components
4 skill or MCP entries
Source updated
Oct 1, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install bootloops-research for Codex and Claude Code

Installs for the current user
codex plugin marketplace add BootLoops-ai/skills
codex plugin marketplace upgrade bootloops
codex plugin add bootloops-research@bootloops

Paste and run these commands in a terminal with Codex. They add and refresh the bootloops catalog, then install this plugin.

Compatibility: the page URL and API slug “bootloops-research” remain stable.

  • Codex: bootloops-research@agent-plugin-marketplace → bootloops-research@bootloops

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/BootLoops-ai/skills

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/bootloops-research/.

Plugin files

plugins/bootloops-research/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── plugin.json
├── skills/lit-review/SKILL.md
├── skills/prove-protocol/SKILL.md
├── skills/ref-check/SKILL.md
└── skills/referee-sim/SKILL.md

Included Skills4

lit-reviewskills/lit-review/SKILL.md

Deep literature review behind a research project's novelty claims — a protocol whose one job is to prevent shortcuts. It demands the papers be actually read (nothing from memory), makes thoroughness falsifiable (read ledgers, search receipts, gap statements), tracks citation chains in both directions, and lists the places to look. Use before any novelty claim ships, when writing or reviewing a related-work section, and when refereeing.

prove-protocolskills/prove-protocol/SKILL.md

Multi-agent protocol for proving or refuting mathematical statements. Use when trying to prove a mathematical statement with agents, when a claimed lemma keeps dying under scrutiny, or when the true statement itself is still unknown (theory-finding regime).

ref-checkskills/ref-check/SKILL.md

Careful bibliography verification and entry-addition for papers — verify every author, title, journal, volume, pages, year, arXiv ID, and DOI against authoritative online sources (INSPIRE, arXiv, CrossRef/DOI, zbMATH, publisher) before anything enters or stays in a .bib file. Use whenever adding bib entries, auditing a bibliography, checking citations, fixing references, or when asked to "check the references". Encodes the report-then-fix pattern for full-file audits and the folklore-error traps (wrong years, truncated author lists, mislabeled keys).

referee-simskills/referee-sim/SKILL.md

Use before circulating any outward-facing scientific document — simulate the strongest standard objection from every audience it claims and verify the document answers each where that reader would look.

Plugin manifests3

plugins/bootloops-research/.codex-plugin/plugin.json
{
  "name": "bootloops-research",
  "version": "1.0.0",
  "description": "The BootLoops research skills: heavier machinery for specific tasks — proving with agents (adversary-first pipelines), pre-circulation referee audit, the literature review behind a novelty claim, bibliography verification, and the scientific-prose linter.",
  "author": {
    "name": "Matthew D. Schwartz",
    "url": "https://www.bootloops.ai"
  },
  "homepage": "https://www.bootloops.ai",
  "repository": "https://github.com/BootLoops-ai/skills",
  "license": "CC-BY-4.0 AND MIT",
  "keywords": [
    "science",
    "verification",
    "protocols",
    "agent-skills",
    "bootloops"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "BootLoops research skills",
    "shortDescription": "Proving with agents, referee audit, literature review, bibliography verification, prose linting.",
    "longDescription": "The BootLoops research skills: heavier machinery for specific tasks — proving with agents (adversary-first pipelines), pre-circulation referee audit, the literature review behind a novelty claim, bibliography verification, and the scientific-prose linter.",
    "developerName": "Matthew D. Schwartz",
    "category": "Productivity",
    "websiteURL": "https://www.bootloops.ai"
  }
}
plugins/bootloops-research/.claude-plugin/plugin.json
{
  "name": "bootloops-research",
  "version": "1.0.0",
  "description": "The BootLoops research skills: heavier machinery for specific tasks — proving with agents (adversary-first pipelines), pre-circulation referee audit, the literature review behind a novelty claim, bibliography verification, and the scientific-prose linter.",
  "author": {
    "name": "Matthew D. Schwartz",
    "url": "https://www.bootloops.ai"
  },
  "homepage": "https://www.bootloops.ai",
  "repository": "https://github.com/BootLoops-ai/skills",
  "license": "CC-BY-4.0 AND MIT",
  "keywords": [
    "science",
    "verification",
    "protocols",
    "agent-skills",
    "bootloops"
  ]
}
plugins/bootloops-research/plugin.json
{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "bootloops-research",
  "version": "1.0.0",
  "description": "The BootLoops research skills: heavier machinery for specific tasks — proving with agents (adversary-first pipelines), pre-circulation referee audit, the literature review behind a novelty claim, bibliography verification, and the scientific-prose linter.",
  "author": {
    "name": "Matthew D. Schwartz",
    "url": "https://www.bootloops.ai"
  },
  "homepage": "https://www.bootloops.ai",
  "repository": "https://github.com/BootLoops-ai/skills",
  "license": "CC-BY-4.0 AND MIT",
  "keywords": [
    "science",
    "verification",
    "protocols",
    "agent-skills",
    "bootloops"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[bootloops-research on Agent Plugins Marketplace](https://pluginsmp.com/plugins/bootloops-research)