bootloops-research

Links

• github.com/BootLoops-ai/skills
• https://www.bootloops.ai
• plugins/bootloops-research/plugin.json (manifest)

Skills · 5

lit-review

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 direction…

prose-lint

use before circulating any scientific text, human- or LLM-drafted, a clarity and integrity linter: hype vocabulary, empty sentence structures, agentless prose, number discipline, and honesty failures; one pass is never enough.

prove-protocol

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-check

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…

referee-sim

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.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

Category

Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Keywords

science · verification · protocols · agent-skills · bootloops

Related by publisher and keywords

• bootloops-protocolsBootLoops-ai

  The BootLoops protocol layer: seven disciplines for trustworthy quantitative work with agents, acceptance gates, integer-relation discipline, synthetic-truth controls, provenance bookkeeping, timing discipline, sources-only reading, tool stewardship.

• drug-discovery-agent-skillsK-Dense-AI

  Agent Skills for small-molecule and protein therapeutics: target validation and human genetics, bioactivity and chemical space, generative design and retrosynthesis, docking, free energy and dynamics, ADMET and PK translation, protein, antibody, degrader and oligonucleotide design, and the clinical and regulatory record.

• rootloomqingye-lab

  Portable Rootloom Agent Skills for inspectable code changes and evidence-backed review with bounded project and artifact context.

• wcodefrancis-du

  Read repositories, edit code and run checks with wcode through local or remote MCP connections.

• pstackvinayshah1998

  Rigorous, verifiable engineering workflows for portable AI agents.

• taiwan-scientific-agent-skillsrangching

  臺灣學術界適用的繁體中文科學 Agent Skills 庫（中英雙語對照），衍生自 K-Dense Scientific Agent Skills。Ready-to-use scientific Agent Skills for Taiwan academia (zh-Hant-TW / English).